Advance

TAKEDA Fumiaki

    Department of Electronic Engineering and Computer Science　Professor/Manager
Last Updated :2024/04/25

Researcher Information

Degree

  • Ph.D（The University of Tokushima）

J-Global ID

Research Interests

  • 機械工学   システム工学   System Engineering   

Research Areas

  • Manufacturing technology (mechanical, electrical/electronic, chemical engineering) / Control and systems engineering

Association Memberships

  • 高速信号処理応用技術学会   計測自動制御学会   システム制御情報学会   電気学会   日本機械学会   

Published Papers

  • 食品検査の効率化について
    竹田史章
    キャノンITソリューション 2020/09 [Invited]
  • AIを応用した一次産業製品の高度検査および知的選別システムの事例紹介
    竹田史章
    FOOMA 技術ジャーナル 14 (2) 17 - 33 2020/02 [Invited]
  • Generation Method of the Trigger Signal for a Full Automatic Capture Device to the Harmful Animals with Color and Infrared Depth Image
    TAKEDA Fumiaki
    高速信号処理応用技術学会 18 (1) 21 - 32 2016/12 [Refereed]
    ダウンロード
  • TAKEDA Fumiaki
    Transactions of the JSME The Japan Society of Mechanical Engineers 82 (835) 1 - 11 2187-9761 2016/03 [Refereed]
     
    Up to now, we discuss a non-linear recognition system for the carved seal of the steal, which has several problems for the image processing and recognition for this research theme such as reflection, roundness, whole carved seal image and partial one. Sometimes these cause miss-recognition for the carved seal. We newly adopt the neural network to this carved seal recognition. This NN has radial based function as an output function for the localization of the recognition range. We discuss the recognition ability according to the several conditions such as lighting and editing method of the learning data for the NN using image of the steal ball for the pinball game. First, we analyze them from a viewpoint of the advanced image processing and construct the neuro recognition system for the carved seal. Finally, we show its effectiveness and feasibility by the simulation with image of the carved seal of the pinball.
    ダウンロード
  • Hironobu Satoh; Fumiaki Takeda
    IEEJ Transactions on Industry Applications 132 (7) 701 - 708 0913-6339 2012 [Refereed]
     
    A screw hole is incorrectly molded if the pin on the mold is broken when the plastic is molded by injection molding. Sampling inspection is carried out manually to identify the incorrectly molded screw hole. In the sampling inspection, the incorrectly molded screw hole on the molded plastic frame is rarely overlooked. Therefore, the development of a system for the high-precision identification of the incorrectly molded screw hole is required. The purpose of this study is to develop a screw-hole inspection system that distinguishes between a correctly molded screw hole and an incorrectly molded one. In this paper, a screw-hole inspection system is proposed. There is a need to capture clearly the screw hole on an uneven plastic frame and therefore, a multi-camera system is used. The proposed system consists of several Web cameras with the individual adjustable focus. Moreover, the inspection of the screw holes is performed using an inspection algorithm that is developed for a multi-camera system. When 2548 correctly molded screw holes and 2940 incorrectly molded screw holes were inspected by the proposed system, the inspection success rate was 100.0%. Finally, we have verified its effectiveness by performing an experiment. © 2012 The Institute of Electrical Engineers of Japan.
  • Hironobu Satoh; Fumiaki Takeda; Yuhki Shiraishi; Rie Ikeda
    ELECTRONICS AND COMMUNICATIONS IN JAPAN SCRIPTA TECHNICA-JOHN WILEY & SONS 94 (2) 42 - 50 1942-9533 2011/02 [Refereed]
     
    We have developed a behavior detection system using a neural network (NN). The system detects dangerous behaviors such as nearly falling out of bed and actual falling out of bed. For detection, the system uses pictures captured by a web camera. The system classifies subjects' behavior into five states using a NN. The five states are "lying in bed," "starting to sit up in bed," "sitting in bed," "almost falling from the bed," and "having fallen from the bed." Then, we define states of almost falling and having fallen from the bed as dangerous behavior. The states of lying in bed, starting to sit up in bed, and sitting in bed are defined as safe behavior. We propose a final detection rule by which the system classifies their behavior into two states. Finally, the detection ability of the system is evaluated. From the experiment's results, the detection rate of dangerous behavior is shown to be 81.7% using the proposed system. (C) 2011 Wiley Periodicals, Inc. Electron Comm Jpn, 94(2): 42-50, 2011; Published online in Wiley Online Library (wileyonlinelibrary.com). DOI 10.1002/ecj.10296
  • Nobuyuki Nakatani; Yuhki Shiraishi; Fumiaki Takeda
    2011 4th International Conference on Modeling, Simulation and Applied Optimization, ICMSAO 2011 2011 [Refereed]
     
    In the agricultural market, uniform appearance quality of products is becoming more important. In this paper, we propose a total surface inspection and sorting system of oval-shaped agricultural product for fully automated ranking operation under uniformed criteria. The system consists of conveyance part, image acquisition part, and classification part. The conveyance part uses sensor-driven independent driving system. In the image acquisition part, photographs of the object are taken from six different angles simultaneously. The classification part identifies the size, shape, and damage existence of the object. The experiment is performed using red peppers. This experiment is to confirm the effectiveness of conveyance and classification performance of the system and to make possible latent problems tangible. © 2011 IEEE.
  • Hironobu Satoh; Takayuki Ohkura; Fumiaki Takeda
    2011 4th International Conference on Modeling, Simulation and Applied Optimization, ICMSAO 2011 2011 [Refereed]
     
    Recently, accidents such that seniors fall down from the bed in care facilities or hospitals are increased. To prevent these accidents, we have developed the awakening behavior detection system using Neural Network. In this paper, it is a problem that the detection success rate of the current system using captured image in the clinical site is not enough. So, we analyze the captured image in the clinical site. From the result of the histogram analysis, it proves that the fluctuation of brightness quantity makes decrease the detection capability. Therefore, to decrease the influence of the brightness quantity, the histogram of the captured image should be equalized. Finally, we show that the histogram equalization reduces fluctuation of brightness quantity numerically. © 2011 IEEE.
  • Yuhki Shiraishi; Fumiaki Takeda
    2011 4th International Conference on Modeling, Simulation and Applied Optimization, ICMSAO 2011 2011 [Refereed]
     
    Up to now, most fruit and vegetables are sorted manually by visual comparison with a standard table. Manual sorting of fruit and vegetables causes long and tough work every harvest and the individual difference of sorting criteria. To overcome the problems, we have proposed a whole surface inspection system of fruit and vegetables with uniform selection criteria especially for prolate spheroid-shaped ones. The proposed system is constructed by a sensor-driven independent conveyance system, which separates one target from the group of them. After the whole surface of the separated target is captured using six cameras, the size, the shape, and the bruise of the target are inspected by using the captured images, respectively. In this paper, the inspection ability of the proposed system is evaluated and analyzed by using red and green bell peppers and yellow paprika. © 2011 IEEE.
  • Yuhki Shiraishi; Fumiaki Takeda
    IEEJ Transactions on Electronics, Information and Systems Institute of Electrical Engineers of Japan 131 (2) 404 - 410 1348-8155 2011 [Refereed]
     
    In this research, we have developed a sorting system for fishes (shown in Fig. 1), which is comprised of a conveyance part, a capturing image part, and a sorting part. In the conveyance part, we have developed an independent conveyance system in order to separate one fish from an intertwined group of fishes. © 2011 The Institute of Electrical Engineers of Japan.
  • SATOH Hironobu; TAKEDA Fumiaki
    IEEJ Transactions on Electronics, Information and Systems The Institute of Electrical Engineers of Japan 130 (2) 310 - 316 0385-4221 2010/02 
    To prevent a person from falling of a bed, we have developed an awakening behavior detection system using a neural network (abbreviated as NN). However, the detection ability of unknown persons is not sufficient compared to that of learned persons. In this research, to improve the detection ability of unknown persons, we apply an online tuning system using a continuous learning of the NN to the detection system. In the online tuning system, only a few additional data of a new target person are used for the continuous learning, where the weights of the NN converged in the initial learning are used as the initial weights for the continuous learning. In this paper, first, we verify that the individual differences among persons affect the detection ability. Second, we demonstrate that the detection ability is improved by executing the online tuning. Thus, we verify the effectiveness of the online tuning of the awakening behavior detection system.
  • Nobuhisa Yamanaka; Hironobu Satoh; Fumiaki Takeda
    International Journal of Intelligent Systems Technologies and Applications 9 (3-4) 286 - 299 1740-8873 2010 [Refereed]
     
    Recently, accidents such that seniors fall down from the bed in hospitals are increased. To prevent these accidents, we have developed an awakening detection system using neural network. In this paper, we adopt a face extractive method to execute more detail extraction of the objective person’s image from the background. We show its feasibility with experimental results. In addition, to confirm the detection capability in the clinical site, the detection experiment using the captured image in the clinical site is conducted. From the result, the detection success rate was low. So, we analyse the captured image in the clinical site. From the analysis of the histogram, it proves that the fluctuation of brightness quantity make decrease the detection capability. Therefore, to decrease this influence, the histogram of the captured image is equalised. Finally, it is verified that the histogram equalisation reduces the effect of fluctuation of brightness quantity. © 2010 Inderscience Enterprises Ltd.
  • Shingo Tamura; Yuhki Shiraishi; Fumiaki Takeda
    International Journal of Intelligent Systems Technologies and Applications 9 (3-4) 274 - 285 1740-8873 2010 [Refereed]
     
    For the automation of visual inspection for printed labels, which are coated with rubber and curl, we have developed a camera-based portable experimental device of automatic inspection in this research. By experiments, we have verified that the experimental device surely detect the failures such as the stain, the patchiness, the spread and the chip detected by using lowdimensional feature vectors unless the conveyance errors occur. Thus, we consider a necessity to develop a mechanism repressing the occurrence of the conveyance errors. To solve the problem, we have extended the experimental device to an improved one for the automatic inspection as a prototype. From the result of the verification experiment using the prototype, we have also verified that the conveyance error hardly occurs. © 2010 Inderscience Enterprises Ltd.
  • Yuhki Shiraishi; Fumiaki Takeda
    DISTRIBUTED COMPUTING, ARTIFICIAL INTELLIGENCE, BIOINFORMATICS, SOFT COMPUTING, AND AMBIENT ASSISTED LIVING, PT II, PROCEEDINGS SPRINGER-VERLAG BERLIN 5518 203 - 210 0302-9743 2009 [Refereed]
     
    For the automatic inspection for printed labels, which are covered with rubber-like coatings and Curl, we have developed a camera-based portable inspection system. In this paper, we explained the developed system, and especially discuss the inspection method of the spread and chip of the printed labels using neural networks. The experimental results confirm the validity of the proposed method for the spread and chip of alphanumerics.
  • Hironobu Satoh; Fumiaki Takeda
    DISTRIBUTED COMPUTING, ARTIFICIAL INTELLIGENCE, BIOINFORMATICS, SOFT COMPUTING, AND AMBIENT ASSISTED LIVING, PT II, PROCEEDINGS SPRINGER-VERLAG BERLIN 5518 272 - 279 0302-9743 2009 [Refereed]
     
    We have developed an awaking behavior detection system using a neural network (abbreviated as NN). However, the detection ability of unknown people is not sufficient with compared to that of learned people. In this research, to improve the detection ability of unknown people, we apply an online tuning system using a continuous learning of the NN for the detection system. In the online tuning system, only a few additional data of a new objective person are used for the continuous learning, where the weights of the NN converged in the initial learning are used as the initial weights for the continuous learning. In this paper, to verify an ability of the online tuning system, we compare detection ability of the converged initial learning with that of the converged online tuning.
  • Hironobu Satoh; Fumiaki Takeda; Yuhki Shiraishi; Rie Ikeda
    IEEJ Transactions on Electronics, Information and Systems Institute of Electrical Engineers of Japan 128 (11) 8 - 1656 1348-8155 2008 [Refereed]
     
    We have developed a behavior detection system using a neural network (NN). The system detects dangerous behaviors that are almost falling from a bed and having fallen from the bed. The system uses captured pictures with a WEB camera for detection. The system classifies their behavior into five states using the NN. Five states are lying in the bed, being sitting up in the bed, sitting in the bed, almost falling from the bed and having fallen from the bed. Then, we define almost falling and having fallen from the bed as dangerous behavior. Moreover, we define lying in the bed, being sitting up in the bed, sitting in the bed as safety behavior. We proposed a final detection rule by which the system classifies their behavior into two states. Finally, a detection ability of the system is evaluated. From the experiment results, the detection rate of dangerous behavior is shown 81.7% using the proposed system. © 2008 The Institute of Electrical Engineers of Japan.
  • Yuhki Shiraishi; Fumiaki Takeda
    Artificial Life and Robotics 13 (1) 199 - 202 1433-5298 2008 [Refereed]
     
    To unlock the full potential of evolution in digital media, a Tierra-like system using network-type assembly-like language has been constructed. In the system, like Avida, digital creatures, self-replicating programs, live in a discrete 2D torus space and an interaction between creatures is restricted locally. Bearing a genetic network in mind, network structure is introduced. In the previous works, it is shown that the possibility that the network-type model has more potential of evolution than a linear-type model like Avida in a simple environment. In this paper, to study the potential of evolution more precisely, we model the effects of environment other than creatures. As one of the simplest models of such environment, the cost of execution, i.e. executing time, is introduced. The difficult environment to live in costs high to execute instructions, the easy environment does low. In computer experiments, we have investigated the influence of change in environment by analyzing the process of evolution and diversity of the system. Experimental results show that the network-type system keeps more stable diversity than the linear-type system does, even when the environment changes drastically. This indicates the possibility that the network-type system has more potential of evolution than the linear-type system has. © International Symposium on Artificial Life and Robotics (ISAROB). 2008.
  • Masato Nakai; Hironobu Satoh; Fumiaki Takeda
    2008 WORLD AUTOMATION CONGRESS PROCEEDINGS, VOLS 1-3 IEEE 77 - 82 2008 [Refereed]
     
    In this research, we have proposed a fish sorting system to aim at automatic sorting. It is constructed with a conveyance part, a capturing image part and a recognition part, respectively. Especially, we have adopted a flexible sorting system using Neural Network (NN) in the recognition part. We have developed an independent conveyance system. The independent conveyance system can convey one piece of fish from several intertwined fishes. We adopt Two-Dimensional Fast Fourier Transform (2DFFT) for generating input of the NN. We suppose the converted data by the 2DFFT is invariable to the rotation of the fish. In this paper, we examine the recognition capability and conveyance capability.
  • Yuhki Shiraishi; Fumiaki Takeda
    2008 WORLD AUTOMATION CONGRESS PROCEEDINGS, VOLS 1-3 IEEE 95 - 100 2008 [Refereed]
     
    To unlock the full potential of evolution in digital media, we have developed a 2D artificial life system using network-type assembly language and investigated the evolvability of the developed system by computer experiments. In this paper, the structure and features of the developed system are addressed and especially the effects of drastic change of environment by introducing costs of instructions to the system are studied. The experimental results show that the network-type system keeps more stable diversity than the linear-type system. This indicates the possibility that the network-type system has more potential of evolution than the linear-type system.
  • Yuhki Shiraishi; Fumiaki Takeda
    ISDA 2008: EIGHTH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS DESIGN AND APPLICATIONS, VOL 3, PROCEEDINGS IEEE COMPUTER SOC 381 - + 2008 [Refereed]
     
    For the automatic inspection of printed labels, which are covered with rubber-like coatings and curl, we have developed a portable inspection system using a Web camera. In this paper, we explained the developed system and the verification experiments. The experimental results show that the developed system detects stains whose size is larger than or equal to 0.1 by 0.1 mm and patchiness whose width is larger than or equal to 0.3 mm unless conveyance errors occur using a VGA (640x480) Web camera.
  • Taiki Matsubara; Hironobu Satoh; Fumiaki Takeda
    2008 WORLD AUTOMATION CONGRESS PROCEEDINGS, VOLS 1-3 IEEE 71 - 76 2008 [Refereed]
     
    Recently, accidents such that seniors fall down from the bed in care facilities or hospitals are increased. To prevent these accidents, we propose an awaking detection system using Neural Network(NN) in hospital use. In this paper, to increase detection capability of the proposed system, the feature extractive method is contrived with including dynamic information and static one. Furthermore, we adopt a face extractive method into our proposed system to execute more detail extraction of the objective person's picture from the background. We show its feasibility with experimental results.
  • Lina Mi; Fumiaki Takeda
    INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL ICIC INTERNATIONAL 3 (1) 97 - 110 1349-4198 2007/02 [Refereed]
     
    In this paper, an individual identification system based on dynamic feature of signature pressure is introduced first. Then uniformed characters are proposed as register characters for the system, instead of traditionally employed individual signature,to address the problem of great difference in the recognition capabilities of the system for different registrants. To evaluate the effectiveness of the proposed method, twenty people are selected as target registrants and the recognition capabilities of the original signature-based systems are studied and compared with that of the uniformed-register-characters-based systems in experiment section. The results show that with the uniformed register characters, the proposed system seems to have important merit on the stability in terms of recognition capabilities for different registrants.
  • Fumiaki Takeda; Yuhki Shiraishi; Takeo Sanechika
    INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL ICIC INTERNATIONAL 3 (1) 211 - 222 1349-4198 2007/02 [Refereed]
     
    Domiciliary oxygen therapy uses oxygen concentrators, which sound alarms in the event of trouble, and the kind of alarm depends on that of the trouble. To lessen the burden on caregivers, we have proposed a system classifying alarm sounds using a multilayer perceptron neural network and transmitting the recognized trouble to a monitor center in a hospital by phone cable. This system has been constructed by a digital signal processor board as an external unit. The difference among kinds of alarm sounds are characterized by the length of alarm sounds and that of alarm periods. Therefore, a short-time Fourier transform is used as a feature extraction method. Experiments using real-world devices indicate that the proposed system works well under noisy conditions.
  • SHIRAISHI Y.
    Proc. of the 7th Int. Conf. on Optimization : Techniques and Applications, 2007 2007 [Refereed]
  • 野崎 幸弘; 前川; 峻徳; 竹田; 史章; 曽禰 元隆
    高速信号処理応用技術学会誌 高速信号処理応用技術学会 10 (2) 54 - 59 2007 [Refereed]
  • 野崎 幸弘; 前川; 峻徳; 竹田; 史章; 曽禰 元隆
    高速信号処理応用技術学会誌 10 (2) 48 - 53 2007 [Refereed]
  • DEVELOPMENT OF AWAKENING BEHAVIOR DETECTION SYSTEM NURSING INSIDE THE HOUSE
    Rie Ikeda; Hironobu Satoh; Takeda Fumiaki
    International Conference on Intelligent Technology 2006 65 - 70 2006 [Refereed]
  • Development of High-speed Intelligent Sorting System for Dry Fishes on Photography Environment
    Masaya Kagawa; Hironobu Satoh; Fumiaki Takeda
    International Conference on Intelligent Technology 2006 229 - 233 2006 [Refereed]
  • SUN Baiqing; TAKEDA Fumiaki
    Transactions of the Institute of Systems, Control and Information Engineers THE INSTITUTE OF SYSTEMS, CONTROL AND INFORMATION ENGINEERS (ISCIE) 19 (7) 274 - 283 1342-5668 2006 [Refereed]
     
    In this paper, in order to improve rejection capabilities of the paper currency recognition system for unknown currency patterns on promise of ensuring recognition capabilities for known currency patterns, a feed-forward neural network (FNN) with Gaussian activation function is proposed. The proposed activation function is a ridge-like function. Moreover, a hybrid-learning algorithm for optimizing the width parameters of the Gaussian function is proposed. In the network the Gaussian activation function instead of the sigmoid function is employed in all units of hidden and output layers. The algorithm consists of two steps, one is exploring local minima by employing the gradient descent search, and the other is extricating the search from local minima, in which a random search with the downhill simplex method is employed. The results of simulation reveal the potential effectiveness of the proposed activation function and the algorithm. The system with the proposed activation function and the proposed algorithm can recognize known currency patterns and reject the unknown currency patterns effectively.
  • 佐藤 公信; 竹田; 史章; 東; 幸靖; 西蔭 紀洋
    高速信号処理応用技術学会誌 高速信号処理応用技術学会 9 (1) 48 - 54 2006 [Refereed]
  • 佐藤 公信; 竹田 史章; 香川 真也
    高速信号処理応用技術学会誌 高速信号処理応用技術学会 9 (1) 42 - 47 2006 [Refereed]
     
    いりこニューラルネットワーク知的高速選別システム独立駆動系
  • Ikeda Rie; Satoh Hironobu; Saeki Yoshihiro; Shiraishi Yuhki; Takeda Fumiaki
    Proceedings of the Annual Conference of the Institute of Systems, Control and Information Engineers The Institute of Systems, Control and Information Engineers 6 214 - 214 2006 
    高齢者の多くはその動作が緩慢である。病院内や福祉施設において快適な日常生活を送るため、常に高齢者を介護する必要が発生しつつある。しかし、長時間高齢者を介護することは難しい。そこで、画像識別システムを用いることで高齢者の行動をモニタするシステムを開発する必要性が要求されている。本論文では、人間の主な動作の1つである「寝る・起きる」という行為をニューラルネットワークを用いて検知を行うシステムを構築する。また、その識別能力について検証を行う。
  • Ueta Kenji; Omori Takeo; Katayama Takatoshi; Saeki Yoshihiro; Takeda Fumiaki
    Proceedings of the Annual Conference of the Institute of Systems, Control and Information Engineers The Institute of Systems, Control and Information Engineers 6 210 - 210 2006 
    現在、入院患者の食事の摂取量計測は栄養士の手計算で行われているため、患者毎に異なるメニューや摂取量を記録する作業は膨大な手間を要する。そこで、著者らは栄養士に代わり上記の作業を行う食事摂取量計測システムを開発してきた。しかし、パソコンや機械の操作が苦手な人には本システムは操作が難しいと予想される。そこで、本論文では本システムのマンマシンインタフェイス(MMI)の改良を行い、本システム内の旧MMIと新MMIの操作性の比較実験を行い、有用性を検証する。
  • Kubo Kazuya; Satoh Hironobu; Takeda Fumiaki; Inoue Keiji
    Proceedings of the Annual Conference of the Institute of Systems, Control and Information Engineers The Institute of Systems, Control and Information Engineers 6 208 - 208 2006 
    現在、医療機関での内視鏡等を用いての内臓疾患の診断は、医師の目視によって判断されている。しかし、患者によって個人差が生じるために、患部を特定するには経験に加え高度な医療技術が必要とされている。そこで本論文では柔軟性があり汎化能力のあるニューラルネットワーク(NN)を用いた画像診断システムを構築することによって患部識別の支援を検討する。提案システムにより、正常部位および患部の特定実験を実施し、提案システムの有用性を検討する。
  • Takaoka Kyohei; Sanechika Takeo; Shiraishi Yuhki; Takeda Fumiaki
    Proceedings of the Annual Conference of the Institute of Systems, Control and Information Engineers The Institute of Systems, Control and Information Engineers 6 213 - 213 2006 
    現在、在宅酸素療法に使用される酸素濃縮器は問題発生時に数種類のアラーム音を発生する。しかし、アラームが鳴ったとしても、患者自身が問題に対処できない場合がある。そこで、ニューラルネットワークを用いた汎用性の高い音識別システムを提案し、酸素濃縮器のアラーム音を識別する。酸素濃縮器の問題発生を自動識別し基地局へ通信することで、介護の負担を軽減することができる。酸素濃縮器のアラーム音識別システムの実用性に関する検証を行い、本システムの有用性を示す。
  • Oonishi Takahisa; Satoh Hironobu; Kagawa Masaya; Nishikage Toshihiro; Takeda Fumiaki
    Proceedings of the Annual Conference of the Institute of Systems, Control and Information Engineers The Institute of Systems, Control and Information Engineers 6 80 - 80 2006 
    現在、いりこの選別は手作業で行われているが、知識および経験また体力などを要する作業であり、高齢化や作業員不足などの問題を抱えている。そこで、それらの問題を解決するため選別作業工程を機械化し、自動化および高精度化が要求されている。本論文ではニューラルネットワークを用いた知的高速いりこ選別システムにおける識別性能について検討を行い、いりこ画像からの特徴抽出処理に2次元高速フーリエ変換を用いることの有効性を述べる。
  • Nakayama Tomoe; Saiki Shouhei; Satoh Hironobu; Takeda Fumiaki
    Proceedings of the Annual Conference of the Institute of Systems, Control and Information Engineers The Institute of Systems, Control and Information Engineers 6 320 - 320 2006 
    近年、個人認証は技術の発展に伴いカードの偽造や情報漏洩が多発し、問題となっている。そのため、個人認証システムには高い認証および偽者排除能力が求められている。特に、現在注目されている個人認証は、バイオメトリクスを用いた認証方法である。 そこで、本研究ではこれまで著者らが提案してきた筆圧認証システムの偽筆排除能力を高めるためにテンプレート特定を目的として顔画像認証を導入し、ハイブリットシステムとしている。
  • Tamura Erina; Sato Hironobu; Kagawa Masaya; Takeda Fumiaki
    Proceedings of the Annual Conference of the Institute of Systems, Control and Information Engineers The Institute of Systems, Control and Information Engineers 6 171 - 171 2006 
    現在、いりこの選別作業は人の手によって行われている。しかし、作業員不足などの問題がある。本研究では手作業で行われている工程を機械化し、選別作業の自動化および高精度化を目的とする。画像により、魚種の特定を行うには、複数のいりこが絡み合った状態では識別は不可能である。そこで著者３はこれまでに、撮像部までに1匹もしくは数匹に分離するために独立駆動系を提案している。本論文では、独立駆動系の基本性能を示し、いりこの分離搬送能力の検証を行う。
  • Konishi Yuuki; Higashi Yukiyasu; Nishikage Toshihiro; Takeda Fumiaki
    Proceedings of the Annual Conference of the Institute of Systems, Control and Information Engineers The Institute of Systems, Control and Information Engineers 6 100 - 100 2006 
    現在、プラスチック部品は工場で生産され、最終工程では、手作業により傷やバリなどの監査が行われている。しかし、人材不足など様々な問題が滞積している。そこで本研究では、それらの問題を解決するため、ニューラルネットワークを応用した監査システムを提案する。提案システムにより、手作業の工程を機械化し、監査の高精度化を行うことが期待できる。本論文では、提案システムの基本性能と有効性を検討する。
  • Hironobu Satoh; Fumiaki Takeda; Yoshihiro Saeki; Rie Ikeda; Yuhki Shiraishi
    PROCEEDINGS OF THE SECOND IASTED INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE ACTA PRESS ANAHEIM 164 - + 2006 [Refereed]
     
    The increase of accidents caused by falling from the bed in care facilities or hospitals is of great concern. Especially the senile or physically disabled elderly are injured by such accidents. To prevent the accidents from occurring, we propose an awakening behavior detection system using a neural network (NN). The proposed system detects when they almost fall from the bed, and makes it possible to lessen the burden of caregivers or nurses. The system uses pictures captured with the universal serial bus (USB) camera for detection without trespassing. In this paper, the system classifies their behavior into five states. Namely, they are lying in the bed, being sitting up in the bed, sitting in the bed, almost falling from the bed, and having fallen from the bed, respectively. At first, the experimental apparatus of the proposed system is designed and assembled. Then, the USB camera in the system is selected by testing one's performance in dark room and capturing area. As experimental results, the effectiveness of the proposed system is verified in the laboratory level.
  • A Study of Driver State Classification Using Invehicle Sensors by Neural Networks
    Y. SHIRAISHI; F. TAKEDA; T. NISHIKAGE; M. UECHI; K. SASAKI
    Proc. of the First World Congress of the Int. Federation for Systems Research, JAIST Press 2005 [Refereed]
  • H Satoh; F Takeda
    KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS, PT 1, PROCEEDINGS SPRINGER-VERLAG BERLIN 3213 866 - 873 0302-9743 2004 [Refereed]
     
    Recently, smaller and more effective recognition system is required in various fields. In our previous researches, the recognition system using neural network (NN) and DSP had been developed. In some research fields, such as biometrics, the target of the system was to recognize patterns whose data varied widely because of the difference of individuals and surroundings, but its recognition ability was not enough. So the online tuning system is proposed in this paper. The proposed system, which is consisted of DSP unit and the NN continuous learning and recognition parts, is used to recognize the patterns whose data varied widely. We discuss to adjust the recognition system to data varied widely by continuous leaning. In experiment, performance of the online tuning system is checked, and we attempt to apply the system to electromyograin (EMG) pattern recognition.
  • Y Matsumura; M Fukumi; N Akamatsu; F Takeda
    KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS, PT 1, PROCEEDINGS SPRINGER-VERLAG BERLIN 3213 891 - 897 0302-9743 2004 [Refereed]
     
    In this paper, we aim for construction of high-speed and high-accurate system using Fast Fourier Transform (FFT) for feature extraction, Simple-PCA (SPCA) for feature compression, and a neural network (NN) for recognition. In particular, we present a novel method based on Multiple PCA to improve recognition accuracy for EMG. From results of computer simulation, it is shown that our approach is effective for improvement in recognition accuracy and speed.
  • Development of a Intelligent input Interface using EMG for Mobile Terminal
    佐藤 公信; 竹田; 史章
    International Simulation and Gaming Association 1078 - 1088 2003 [Refereed]
  • Y Matsumura; Y Mitsukura; M Fukumi; N Akamatsu; F Takeda
    KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS, PT 1, PROCEEDINGS SPRINGER-VERLAG BERLIN 2773 623 - 630 0302-9743 2003 [Refereed]
     
    This paper tries to recognize EMG signals by using neural networks. The electrodes under the dry state are attached to wrists and then EMG is measured. These EMG signals are classified into seven categories, such as neutral, up and down, right and left, wrist to inside, wrist to outside by using a neural network. The NN learns FFT spectra to classify them. Moreover, we structuralized NN for improvement of the network. It is shown that our approach is effective to classify the EMG signals by means of computer simulations.
  • Tanaka Masahiro; Takeda Fumiaki; Ohkouchi Kazuya; Michiyuki Yasuyo
    Neural Networks Proceedings 3 1748 - 1753 1998/05 

    For the recognition of paper currencies by image processing, the two steps data processing approach can yield high performance. The two steps include "recognition" and "verification" steps. In the current recognition machine, a simple statistical test is used as the verification step, where univariate Gaussian distribution is employed. Here we propose the use of the probability density formed by a multivariable Gaussian function, where the input data space is transferred to a lower dimensional subspace. Due to the structure of this model, we refer the total processing system as a hybrid neural network. Since the computation of the verification model only needs the inner product and square, the computational load is very small. In this paper, the method and numerical experimental results are shown by using the real data and the recognition machine

  • Fumiaki Takeda; Toshihiro Nishikage
    IEEJ Transactions on Industry Applications 118 (3) 284 - 290 1348-8163 1998 [Refereed]
     
    Up to now, our group have proposed a new type of recognition method using neural network (NN) which is endowed with generalization and flexibility. Especially, this method is constructed by mask processing, mask optimization by genetic algorithm, and neuro-recognition board. In this paper, we discuss introduction of the NN to partial sensed pictures of the paper currency. However, the partial sensed pictures are different each other even though they are same category of the pattern recognition. When we recognize those pictures using a conventional single NN, it is supposed that the recognition ability is not enough in the market. Then we propose a new recognition system which is constructed by plural NNs linked as a cascade for the partial sensed pictures. First, we show a problem of recognition using the conventional single NN by the simulation results. Then, in order to solve the problem, we show a construction of the proposed recognition system. Finally, we discuss ability of the proposed system by the simulation results. © 1998, The Institute of Electrical Engineers of Japan. All rights reserved.
  • F Takeda; T Nishikage; S Omatu
    ARTIFICIAL INTELLIGENCE IN REAL-TIME CONTROL 1997 PERGAMON PRESS LTD 319 - 324 0962-9505 1998 [Refereed]
     
    We have proposed paper currency recognition system by a neural network (NN) to develop new types of the paper currency recognition machines. This system is constructed by some core techniques. One is the small scale neuro-recognition technique using masks. The one is the mask optimization technique using a genetic algorithm (GA). The last is the neuro-hardware technique using a digital signal processor (DSP). In this paper, in order to determine the excellent masks which can generate the characteristic values of the input image effectively, we adopt the GA to the mask optimization and tune the neuro-recognition system. We show the effectiveness of this technique using the Italy currency. Still more, we design some high speed neuro-recognition machines. Its recognition speed is ten times faster than current currency recognition machines. Finally, the feasibility and effectiveness of the neuro-recognition system is shown by using world wide currency. Copyright (C) 1998 IFAC.
  • Fumiaki Takeda; Kengo Terada; Sigeru Omatu
    Nippon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C 63 3933 - 3940 0387-5024 1997/01 
    We propose three core methods for paper currency recognition using the neural network. The first method is to create a small size neuro-recognition technology for paper currency using masks. The second method is to adapt the genetic algorithm to the mask determination. The last method is to develop a high speed neuro-recognition board using a DSP to realize the commercial products. In this paper, we unify three methods for paper currency recognition and realize the neuro-system technology. We show development and effectiveness in an experimental system using current banking machines.
  • TAKEDA Fumiaki; OMATU Sigeru; ONAMI Saizo
    Transactions of the Institute of Systems, Control and Information Engineers THE INSTITUTE OF SYSTEMS, CONTROL AND INFORMATION ENGINEERS (ISCIE) 8 (5) 196 - 203 1342-5668 1995/05 
    Recently, much research on application of neural network (NN) using genetic algorithm (GA) has been reported. In this paper, we apply GA to a neuro-pattern recognition system for paper currency with masks. We regard the position of the masked part as a gene on the input image. We operate crossover, mutation, and selection to some genes. By repeating a series of these operations, we can get effective masks for recognition of paper currency. We compare the ability of NN using the optimized masks by the GA with the one of NN using the random masks. Then we show that the GA is effective to mask optimization for the method of neuro-pattern recognition. Furthermore, we refer to a high-speed neuro-recognition board to realize the neuro-pattern recognition for paper currency in the commercial products.
  • F TAKEDA; S OMATU
    1995 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS, VOLS 1-5 I E E E 4367 - 4371 1995 [Refereed]
  • 「学位論文」知的情報処理応用による貨幣識別技術に関する研究
    竹田 史章
    徳島大学工学部システム工学専攻 1 - 104 1994/03 [Refereed]
  • F TAKEDA; S OMATU
    WCNN'93 - PORTLAND, WORLD CONGRESS ON NEURAL NETWORKS, VOL I LAWRENCE ERLBAUM ASSOC PUBL 241 - 244 1993 [Refereed]
  • FUKUMI Minoru
    IEEJ Transactions on Electronics, Information and Systems 112-C (8) 457 - 464 1992/08 [Refereed]
  • M FUKUMI; S OMATU; F TAKEDA; T KOSAKA
    IEEE TRANSACTIONS ON NEURAL NETWORKS IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC 3 (2) 272 - 279 1045-9227 1992/03 [Refereed]
     
    In pattern recognition, we must often deal with problems to classify a transformed pattern. In this paper, we propose a neural pattern recognition system which is insensitive to rotation of input pattern by various degrees. The system consists of a fixed invariance network with many slabs and a trainable multilayered network. To illustrate the effectiveness of the system, we apply it to a rotation-invariant coin recognition problem to distinguish between a 500 yen coin and a 500 won coin. The results show that our neural network approach works well for variable rotation pattern recognition problem.
  • FUKUMI Minoru; OMATU Sigeru; TAKEDA Fumiaki; KOSAKA Toshihisa
    Transactions of the Institute of Systems, Control and Information Engineers THE INSTITUTE OF SYSTEMS, CONTROL AND INFORMATION ENGINEERS (ISCIE) 5 (1) 9 - 17 1342-5668 1992/01 
    We have already presented a pattern recognition system insensitive to translation and rotation by 90° using neural networks. In this paper, we propose a pattern recognition system invariant to rotation of input pattern by any number of degrees. The system consists of a fixed invariance net with many slabs and a trainable multi-layered network. To illustrate the effectiveness of the system, we apply it to a variable rotation coin recognition problem between 500 yen and 500 won coins.
  • M FUKUMI; S OMATU; F TAKEDA; T KOSAKA
    1991 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3 INST ELECTRICAL ENGINEERS 1027 - 1032 1991 
    The authors propose a pattern recognition system which is insensitive to the rotation of the input pattern by various degrees. The system consists of a fixed invariance network with many slabs and a trainable multilayered network. To illustrate the effectiveness of the system, the authors apply it to rotation-invariant coin recognition of 500 yen and 500 won coins. The results of computer simulation show that a neural network approach will be useful in rotation-invariant pattern recognition.

Books etc

  • 先進的画像処理とAIと用いた鶏肉原料の夾雑物選別の自動化
    吾郷友亮; 竹田史章 (Joint work9 Vol.56 september2019)食品機械装置 2019/09
  • 運動の癖による個人認証技術－人の 動作解析による個人認証と行動認識－
    竹田史章 (Joint work高精度化する個人認証技術 －身体的、行動的認証からシステム 開発、事例、国際標準化まで－ pp.235-245 第4章第5節)NTS 2014/11
  • Paper Curroney Recognition Image Processing and Pattern Recognition
    Fumiaki Takeda (Joint work)Neural Network Systems, Techniques and Applications 1998/03

Conference Activities & Talks

  • 食品業界へのAIの導入  [Invited]
    竹田史章
    異業種交流会１２人会  2023/08
  • Present situation and future for the image processing and AI applied technology in the food processing
    竹田史章
    日本食品工業倶楽部  2023/07
  • 食品業界における検品・選別作業の自動化について  [Invited]
    竹田史章
    日本食品機械工業会  2023/06
  • 豆類を対象とした異物選別における非線形選別手法の提案  [Not invited]
    清水翔太; 竹田史章
    システム制御情報学会  2023/05
  • 金属部品を対象とした複数分割撮像によるAIマルチテンプレート外観検査システムの提案  [Not invited]
    山内隆聖; 竹田史章
    システム制御情報学会  2023/05
  • AI及び画像処理によるセラミックボール全面検査システムの提案  [Not invited]
    十九百淳; 竹田史章
    システム制御情報学会  2023/05
  • 豆類を対象としたAIによる焙煎レベルの判定システムの提案  [Not invited]
    叶悠人; 竹田史章
    システム制御情報学会  2023/05
  • ベアリングボールを対象としたAI検査システムの提案  [Not invited]
    池上祐哉; 竹田史章
    システム制御情報学会  2023/05
  • 豆類を対象としたAIによる異物選別システムの提案  [Not invited]
    森啓吾; 竹田史章
    システム制御情報学会  2023/05
  • ニューラルネットワークによるコーヒー豆類の焙煎度判定手法の提案  [Not invited]
    田中大地; 竹田史章
    システム制御情報学会  2023/05
  • 食品製造工程に使用される画像処理及びAI応用技術の現状と今後  [Invited]
    竹田史章
    日本食品工業倶楽部  2023/04
  • 食品製造工程に使用される画像処理技術の現状と未来  [Invited]
    竹田史章
    「食品ライン高度自動化推進プロジェクト」におけるFOOMA JAPAN 2022 公開討論会  2022/06
  • 森啓吾; 竹田史章; 菅野明弘; 藤原明宏
    システム制御情報学会  2022/05
  • 福田大河; 竹田史章
    システム制御情報学会  2022/05
  • 佐々木優也; 竹田史章; 菅野明弘; 藤原明宏
    システム制御情報学会  2022/05
  • 叶悠人; 竹田史章
    システム制御情報学会  2022/05
  • 池上祐哉 竹田史章
    システム制御情報学会  2022/05
  • 食品製造プロセスにおけるAI・センサデータの活用方法とその実践例  [Invited]
    竹田史章
    食品研究交流事業 令和３年度第２回講演会  2022/02
  • AIによる冷凍食品用原材料の異物検知とその部位特定システムの開発  [Not invited]
    金谷虹季; 竹田史章
    システム制御情報学会  2021/05
  • スマートファクトリを想定したAIマルチテンプレート方式による青果物状態判定システムの提案  [Not invited]
    福田大河; 竹田史章
    システム制御情報学会  2021/05
  • ドローンによる空撮動画を用いた壁面のAI状態判定システムの提案  [Not invited]
    佐々木優也; 竹田 史章
    システム制御情報学会  2021/05
  • AIを用いたプラスチックエアーダクトの表面検査システムの提案  [Not invited]
    竹田史章; 向井司
    システム制御情報学会  2021/05
  • ドローンによる空撮画像を用いた壁面のAI良否状態判定システムの提案  [Not invited]
    佐々木優也; 竹田史章
    高速信号処理応用技術学会  2021/03
  • AIによる鶏肉表面上の異物検知とその部位特定  [Not invited]
    金谷 虹季; 竹田史章
    高速信号処理応用技術学会  2021/03
  • AIマルチテンプレート方式による製菓状態判別システムの研究
    福田 大河; 竹田史章
    高速信号処理応用技術学会  2021/03
  • AIの概念とAIの導入による天然素材を含む加工食品の状態判定とスマートファクトリ化構想  [Not invited]
    竹田 史章
    高速信号処理応用技術学会  2021/03
  • 食品製造業におけるAIを利用した最新の自働化とスマートファクトリー  [Invited]
    竹田史章
    日本食品工業倶楽部  2020/08
  • AIを応用した一次産業製品の高度検査および知的選別システムの事例紹介  [Not invited]
    竹田史章
    （一社）日本食品機械工業会  2020/06
  • ドローンによる空撮画像を用いた害獣捕獲システムの対象抽出  [Not invited]
    竹田史章; 後藤大輝
    システム制御情報学会  2020/05
  • AIによる冷凍食品用原材料の異物検知とその部位特定  [Not invited]
    金谷虹季; 竹田史章
    システム制御情報学会  2020/05
  • AIマルチテンプレート方式による製菓状態判別システムの提案  [Not invited]
    村中元紀; 竹田史章
    システム制御情報学会  2020/05
  • 加工製菓状態認識における感性判断の自動化  [Invited]
    竹田 史章
    高速信号処理応用技術学会  2019/09
  • ドローンとセンサカメラによる地上対象の画像抽出  [Invited]
    竹田 史章
    高速信号処理応用技術学会  2019/09
  • 人間の感性判断（賢さ）をAIで実現 -AIの一次産業及び二次産業への応用事例報告  [Not invited]
    竹田 史章
    高速信号処理応用技術学会  2019/09
  • 人間の感性判断をAIで実現～AIの一次産業及び二次産業への導入とそのノウハウと事例報告～  [Invited]
    竹田 史章
    日本食品工業倶楽部  2019/06
  • 飛翔型ドローンによる空撮画像良否判定システム  [Invited]
    竹田 史章
    システム制御情報学会  2019/05
  • 人工知能を用いた搬送途上の製菓用非線形状態選別システム  [Invited]
    竹田 史章
    システム制御情報学会  2019/05
  • AIの力を借りた人の感性判断のマシンシステムでの実現  [Invited]
    竹田 史章
    広島県立総合技術研究所  2019/02
  • 一次産業におけるAI利活用  [Invited]
    竹田 史章
    広島県  2018/12
  • AIによるドクターへの経験・知見のコンピュータへの移植とその実応用例と効果の可能性  [Invited]
    竹田 史章
    日本泌尿器内視鏡学会  2018/11
  • 人工知能AIに見る基本原理とその実務応用の可能性例の紹介  [Invited]
    竹田 史章
    近畿大学工学部  2018/10
  • 先進的画像処理及びAIを用いた自律学習によるチキンの夾雑物検知システムの提案  [Invited]
    竹田 史章
    ２０１８高速信号処理応用技術学会研究会  2018/08
  • 害獣捕獲および監視用空撮マルチコプターの飛翔性能調査実験  [Invited]
    竹田 史章
    ２０１８高速信号処理応用技術学会研究会  2018/08
  • 光沢部品検査へのマルチニューロテンプレートシステムの応用  [Invited]
    竹田 史章
    高速信号処理応用技術学会2017年研究会  2017/08
  • 可視画像と赤外線深度画像のハイブリッド画像による害獣自動捕獲装置の提案  [Not invited]
    竹田 史章
    高速信号処理応用技術学会研究会  2016/08

Works

  • Research and Development for Intelligent Systems
    TAKEDA Fumiaki Software 2003 - Today
  • Research and Development for Intelligent Inspection Systems
    TAKEDA Fumiaki Software 2000 - Today
  • Function Generation Systems by Learning of the Neural Network
    TAKEDA Fumiaki Software 1999 - Today
  • ニューラルネットワークによる紙幣識別システムの改良
    1999 - Today
  • 筋活動電位による腕の挙動認識システムの開発
    2000
  • Development of a arm behavior recognition system using electromyogram
    2000
  • 食事摂取量計測システムの開発
    1999
  • Development of a measuring system for foods taking volume
    1999
  • Improvement of currency recognition system with neural network
    1999

MISC

Industrial Property Rights

  • 特願2023-019812:被験者の異常検知システム  2023年/02/13
    竹田史章
  • 特願2022-080633:球体の外観検査システム及び物体の外観検査システム  2022年/05/17
    竹田史章  学校法人 近畿大学
  • 特願2022-018017:コーヒー炒豆の焙煎度推定機能を備える焙煎度検査システムおよび焙煎度検査方法 出願日：2022/02/08  2022年/02/08
    竹田 史章, 上島珈琲株式会社  学校法人 近畿大学
  • 特願2022-018053:コーヒー豆類の良品識別機能を備える良品検査システムおよび良品検査方法  2022年/02/08
    竹田 史章, 上島珈琲株式会社  学校法人 近畿大学
  • 特願2020-152681:船舶の壁面検査用高度知能化検査システム  2020年/09/11
    テクノス三原株式会社, 竹田史章  テクノス三原株式会社
  • 特許第6628373号:マルチコプターを対象とする壁面トレース型飛行制御システム    2020/01/08
    竹田 史章, 向田尊俊  竹田 史章 向田尊俊
  • 特願22206701:食品検査システム、食品検査プログラム、食品検査方法および食品生産方法  2018年/01/31
    竹田 史章, 吾郷知亮, 塚本真也, 間宮 稔, 青木仁史  竹田 史章、吾郷知亮、塚本真也、
  • 特許第5889727号:電子機器の捺印シンボル検査装置、及びその方法    2016/02/26
    藤原 渉, 竹田 史章
  • 特許第5374787号:鋼球の刻印認識システム    2013/10/04
    竹田 史章  
    2016年9月に近畿大学に譲渡
  • 特許4812083:いりこ等の選別方法とその装置    2011/09/02
    竹田 史章  
    2016年9月に近畿大学に譲渡

Awards & Honors

  • 2021/05 システム制御情報学会 学生発表賞
     AIによる冷凍食品用原材料の異物検知とその部位特定システムの開発 
    受賞者: 金谷 虹季
  • 2020/05 システム制御情報学会 学生発表賞
     AIによる冷凍食品用原材料の異物検知とその部位判定 
    受賞者: 金谷虹季・近畿大学
  • 2020/05 システム制御情報学会 学生発表賞
     AIマルチテンプレート方式による製菓状態判別システムの提案 
    受賞者: 村中元紀・近畿大学
  • 2013 SITIS 2013 valuable contribution as workshop chair
  • 2011 ICMSAO 2011 Best Paper Award
     MYS
  • 2008 高知工科大学教員表彰（研究賞）
     JPN
  • 2007 高知工科大学教員表彰 設立１０周年表彰（研究賞）
     JPN
  • 2006 台湾ジャパンシンポジウム, 貢献賞
  • 2002 第３回システムインテグレーション部門講演会ベストセッション賞
     JPN
  • 2002 情報処理学会四国支部研究シンポジウム優秀賞
     JPN
  • 2001 システム制御情報学会論文賞
     JPN
  • 1996 新技術開発財団市村学術賞(功積賞)
     JPN
  • 1996 高度自動化技術振興財団研究業績表彰(本賞)
     JPN
  • 1995 計測自動制御学会論文賞
     JPN
  • 1995 日本機械学会関西支部賞(研究賞)
     JPN
  • 1994 徳島大学工業会賞
     JPN

Research Grants & Projects

  • AIを用いた養殖魚の食欲検知システムの構築及び設計
    福伸電機株式会社：
    Date (from‐to) : 2023/03 -2024/09 
    Author : 竹田史章
  • AIによる浴室内挙動検知システムを用いた見守り支援システムの構築及び設計
    福伸電機株式会社 古河産業株式会社：
    Date (from‐to) : 2023/03 -2024/02 
    Author : 竹田史章
  • 品川リフラクトリーズ株式会社：共同研究
    Date (from‐to) : 2021/06 -2023/06 
    Author : 竹田史章
  • AI実証検査システム構築の為のシステム設計と複数部品に対する汎用化のプログラム改造指導及び機能検証
    福伸電機株式会社：
    Date (from‐to) : 2022/12 -2023/05 
    Author : 竹田史章
  • AI実証検査システム構築の為のシステム設計とプログラム改造指導及び機能検証
    福伸電機株式会社：
    Date (from‐to) : 2020/04 -2023/03 
    Author : 竹田史章
  • 人工知能を用いた甲製品（豆入りチョコレート菓子）の不良品選別検査んい関わる検知システムの調査研究・スマートファクトリー構想実現に向けたエッジソリューション調査研究 実システム化に向けた現在の良否判定システムの改善及び基本動作の確認
    Date (from‐to) : 2019/04 -2022/06 
    Author : 竹田史章
  • UCC上島珈琲株式会社：受託研究
    Date (from‐to) : 2021/03 -2022/04 
    Author : 竹田史章
  • AI及び画像処理を用いた外観検査に関する知見供与と技術指導
    リョービ株式会社：受託研究
    Date (from‐to) : 2021/06 -2022/03 
    Author : 竹田史章
  • AI実証検査システム構築の為のシステム設計とプログラム改造指導及び機能検証
    福伸電機株式会社：受託研究
    Date (from‐to) : 2020/04 -2021/12 
    Author : 竹田史章
  • 江崎グリコ株式会社：受託研究
    Date (from‐to) : 2019/04 -2021/12 
    Author : 竹田 史章
  • 人工知能を用いた船舶の外観検査装置に関わる高度知能検査システムの実証機の開発と機能検証
    テクノス三原株式会社：受託研究
    Date (from‐to) : 2020/04 -2021/05 
    Author : 竹田史章
  • 人工知能を用いた樹脂系部品の状態判定システムの水平展開に対するシステムの改造指導
    高木デルタ化工株式会社：受託研究
    Date (from‐to) : 2020/04 -2021/04 
    Author : 竹田史章
  • AI応用による車用金属光沢部品の外観検査システムの実証機開発の研究
    福伸電機株式会社：受託研究
    Date (from‐to) : 2019/07 -2020/06 
    Author : 竹田 史章
  • 人工知能を用いた大学独自検査システムによる空撮画像良否判断に関する技術指導
    テクノス三原株式会社：受託研究
    Date (from‐to) : 2019/06 -2020/04 
    Author : 竹田 史章
  • 人工知能を用いた大学独自検査システムによる樹脂製自動車部品検査に関する技術指導
    高木デルタ株式会社：受託研究
    Date (from‐to) : 2019/06 -2020/04 
    Author : 竹田 史章
  • 冷凍食品の原料の異物位置特定及び異物形状認識の研究
    株式会社ニチレイフーズ：受託研究
    Date (from‐to) : 2019/05 -2020/04 
    Author : 竹田 史章
  • 人工知能を用いた金属製自動車部品のキズ検査に関わる検知システムの調査研究
    福伸電機：受託研究
    Date (from‐to) : 2018/07 -2019/06 
    Author : 竹田 史章
  • 人工知能を用いた船舶の外観検査に関わるシステム開発の調査
    テクノス三原：受託研究
    Date (from‐to) : 2018/04 -2019/03 
    Author : 竹田 史章
  • 人工知能を用いた車部品外観検査に係るシステムの研究
    高木デルタ：受託研究
    Date (from‐to) : 2018/04 -2019/03 
    Author : 竹田 史章
  • 近赤外線による深度画像を用いた害獣捕獲用インテリジェント起動信号生成手法
    日本学術振興会：H29年度科学研究費助成事業（基盤研究C)
    Date (from‐to) : 2017/04 -2019/03 
    Author : 竹田 史章
  • 飛翔型検査装置の自律トレース安定飛行制御システム の研究
    テクノス三原株式会社：受託研究費
    Date (from‐to) : 2017 
    Author : 竹田 史章
  • 冷凍食品の原料の異物付着検査システムの研究
    株式会社ニチレイフーズ：受託研究費
    Date (from‐to) : 2017 
    Author : 竹田 史章
  • 人工知能を用いた車部品外観検査に関わるシステム 開発の調査
    高木デルタ化工株式会社：受託研究費
    Date (from‐to) : 2017 
    Author : 竹田 史章
  • 電子機器の捺印シンボル検査装置、及び その方法
    Date (from‐to) : 2016 
    Author : 竹田 史章
  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research
    Date (from‐to) : 2003 -2004 
    Author : TAKEDA Fumiaki
     
    In this research, we propose an online tuning system for Electromyogram (EMG). EMG is minute electricity and it is easy to be influenced by noise. In some research fields, such as biometrics, the target of the system was to recognize patterns whose data varied widely because of the difference of individuals and surroundings, but its recognition ability was not enough. We designed the DSP unit for online tuning and verified them. The proposed system, which is consisted of DSP unit and the NN continuous learning and recognition parts, is used to recognize the patterns. Results of examination show recognition ability improved when the learning data were increased. We show possibility of online tuning whit DSP unit for EMG. Finally, we apply to machine, which is control three fingers hand.As a research achievement, six times presentation were given at each, international conferences and domestic conferences.
  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research
    Date (from‐to) : 2003 -2004 
    Author : FUKUMI Minoru; TAKEDA Fumiaki; YAMAMOTO Toru; MITSUKURA Yasue
     
    Recently, information terminals such as a cellular phone have been widely used. According to this, industrial standard of radio communication such as Bluetooth has been established. As a result, it would be possible to combine and to perform various interfaces. However, now a day, the device that has various operations of portable machines and tools and can control networks (call "total operation device" for short) has not been provided yet. Moreover, the wristwatch type is preferable in the viewpoint of operationality. Therefore, we investigate ElectroMyoGram (EMG) which is a signal generated from a living body with movement of a subject. First, time series data for EMG is measured by electrodes in the input part. Second, this data is amplified and A/D transform is performed in the signal processing part. Next, this amplified data is converted to Fourier power spectra. Finally, we evaluate various data in the learning-evaluation part. We aim for construction of a high-speed and high-accurate EMG recognition system which can do on-line learning using DSP training board. In order to achieve high accuracy, we used Fast Fourier Transform (FFT) for feature extraction, Simple-PCA (SPCA) for feature compression, and a neural network (NN) for recognition. In particular, we presented a novel method based on Multiple PCA to improve recognition accuracy for EMG. From results of computer simulation, it is shown that our approach is effective for improvement in recognition accuracy and speed. Furthermore, we used a genetic algorithm for condteracting a rule generation system which can improve recognition accuracy for EMG. This method yielded mathematical functions using input attributes selected by the genetic algorithms. These functions can achieve a high accuracy compared to conventional approach. Finally we tested noize elimination performance using wavelet transform. In this method, small components after the wavelet transform are eliminated and then signals are inversely transformed. These signals were used for EMG recognition and evaluated its accuracy.
  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research
    Date (from‐to) : 2000 -2001 
    Author : TAKEDA Fumiaki
     
    Up to now, Authors research have been focused on applications of neural networks (NNs) for banknotes recognition. Especially, we have clarified its effectiveness of neurorecognition system on industrial use by implementing the neuro-recognition system to various banking machines in spite of unfocused sensing data and various noised data. Recently, another demand on banknotes recognition will be appeared. Namely, it need the more number of banknotes to be recognized at the same time on the banking machines according to appearance of Euro banknotes. In order to solve this problem, we propose a neuro-templates matching method whose templates are constructed by plural NNs. We show its effectiveness by experiments for various foreign banknotes and Euro dummy. Furthermore, we also refer extension of the proposed method to human security using bio-paratnetric information such as palmprints, fingerprints, face image and so on. First stage, we research neuro tejuplate matching as recognition algorithms. Then, we show its effectiveness with various kinds of simulation using foreign banknotes andEuro ones. At the same time, Vie re design DSP board and implement this proposed algorithms to this DSP board. Second stage, we apply this recognition algorithms and DSP board to individual recognition with pen pressure and inspection system for fallen rice. Then we show the effectiveness and usefulness of this algorithm on the real time systems.
  • インターネット上での生体情報を用いた個人認証システムの開発
  • 行動認識型離床認識システムの開発
  • ニューロ応用による搬送物自動監査システムの研究と開発
  • ニューラルネットワークを用いた画像認識による食事摂取状態のレベル分類システムの研究と開発
  • デジタルシグナルプロセッサによる知的認証ボードの開発
  • 生体情報を用いた個人認証システムの研究とそのプロトタイプの開発
  • 自己学習型知的貨幣識別手法の研究とその実システムへのインプリメンテーションの研究
  • Developement of a individual recognition system using biometrics on the Internet
  • Development of weake up sensing system of human behavior
  • Development of a intelligent recognition board using digital signal processor
  • Research of individual recognition system with biometrics and its development of prototype
  • Research of artificial intelligent currency recognition method by autonomic learning and its implementation to real system.

Social Contribution

  • AI IoTビジネスフォーラム
    Date (from-to) : 2018/08/24
    Role : Appearance
    Category : Lecture
    Sponser, Organizer, Publisher  : YMFG ZONEプランニング
  • 社会人リカレント講座講義(AI技術)
    Date (from-to) : 2018/08/01
    Role : Appearance
    Category : Lecture
    Sponser, Organizer, Publisher  : 株式会社サタケ
  • 平成30年度近畿大学工学部産学連携推進協力講演会 講演
    Date (from-to) : 2018/06/04
    Role : Appearance
    Category : Lecture
  • サンデー毎日に記事掲載
    Date (from-to) : 2018/04/18
    Role : Organizing member
    Event, Program, Title : サンデー毎日

Media Coverage

  • ロボットやAI飲食業界救う？ 自動調理や配膳導入広まる
    Date : 2023/08/19
    Program, newspaper magazine: 北海道新聞
    夕刊 Paper
  • ロボットやAI飲食業界救う！？ 人手不足の切り札に期待＜デジタル発＞
    Date : 2023/08/17
    Program, newspaper magazine: 北海道新聞 電子版
    Internet
  • 食品製造ライン自動化推進プロジェクト
    Date : 2023/08
    Pr
  • 「中国新聞LEADERS倶楽部」通信
    Date : 2023/04/27
    Program, newspaper magazine: 中国新聞
    朝刊 Paper
  • AI自動車部品検査システム導入以来不良品出荷率０％を維持
    Date : 2021/06/29
    Writer: Other than myself
    Program, newspaper magazine: 中国新聞
    Paper
  • AI利用プラスチック検査システム 近大工学部と共同開発、樹脂成形業者に販売
    Date : 2021/06/10
    Writer: Other than myself
    Program, newspaper magazine: 広島経済レポート
    Paper
  • 車部品検査にAI活用 高木デルタ化工 開発進む
    Date : 2021/06/10
    Writer: Other than myself
    Program, newspaper magazine: 中国新聞
    Paper
  • 共同研究事例の紹介 CASE1 特許出願につながった事例
    Date : 2020/10/16
    Publisher, broadcasting station: 近畿大学工学部
    Program, newspaper magazine: NEWS LETTER
    Pr
  • 10分でわかる！近畿大学工学部のYOU TUBE 大学紹介～電子情報工学科編
    Date : 2020/06
    Writer: Myself
    Internet
  • AI応用のパイオニア
    Date : 2019/10
    Writer: Myself
    Program, newspaper magazine: THE WEEKLY PRESSNET
    Paper
  • 大学徹底研究広島県の大学へ行こう近畿大学工学部
    Date : 2019/06/23
    Program, newspaper magazine: 中国新聞
    Paper
  • 「中国新聞LEADERS倶楽部」通信 Vol.7記事掲載
    Date : 2019/05/16
    Program, newspaper magazine: 中国新聞
    Paper
  • 「半端ない」就職力が真骨頂記事掲載
    Date : 2018/11/22
    Publisher, broadcasting station: 近畿大学工学部
    Program, newspaper magazine: THE WEEKLY PRESSNET
    Paper
  • てくたまラジオ近大工学部潜入レポート2018 ラジオ出演
    Date : 2018/11/08
    Publisher, broadcasting station: 近畿大学
    Program, newspaper magazine: 広島FM
    Media report
  • 近畿大学工学部の広報誌に記事掲載
    Date : 2018/07/01
    Program, newspaper magazine: 近畿大学工学部
    Pr
  • 中國新聞にAI先端技術開発記事掲載
    Date : 2018/06/24
    Program, newspaper magazine: 中國新聞
    Paper
  • ニチレイフーズ原料選別システムの記事掲載
    Date : 2018/03/29
    Program, newspaper magazine: 日経産業新聞
    Paper
  • ニチレイフーズ原料選別システムの記事掲載
    Date : 2018/03/06
    Program, newspaper magazine: 中國新聞
    Paper
  • AIによる原料選別システム記事掲載
    Date : 2018/02/27
    Program, newspaper magazine: 冷食タイムス
    Paper
  • ニチレイフーズ原料選別システムの記事掲載
    Date : 2018/02/27
    Program, newspaper magazine: 日刊水産経済新聞
    Paper
  • ニチレイフーズ原料選別システムの記事掲載
    Date : 2018/02/23
    Program, newspaper magazine: 冷凍食品新聞
    Paper
  • ニチレイフーズ原料選別システムの記事掲載
    Date : 2018/02/23
    Program, newspaper magazine: 日本食糧新聞
    Paper
  • ニチレイフーズ原料選別システムの記事掲載
    Date : 2018/02/22
    Program, newspaper magazine: 冷食タイムス
    Paper
  • ニチレイフーズ社内報に記事掲載
    Date : 2018/02
    Program, newspaper magazine: ニチレイフーズ社内報
    Pr
  • H29第二回FD教員研修会GL,発表
    Date : 2017/09/06
  • AIを用いた顔認証システムによる人物特定
    Date : 2017/02/26
    Publisher, broadcasting station: フジテレビ
    Program, newspaper magazine: CX系列「新報道２００１」
    Media report
  • 高速信号処理応用技術学会研究発表会開催
    Date : 2016/08/24
    Publisher, broadcasting station: 高速信号処理応用技術学会
  • RCCラブ・グリーン2018 TVCM出演
    Program, newspaper magazine: RCCラブ・クリーン2018 TVCM
    Media report
  • 畜産コンサルタント2018記事掲載
    Program, newspaper magazine: 畜産コンサルト2018
    Paper

Other link

researchmap


Copyright © MEDIA FUSION Co.,Ltd. All rights reserved.