Search Results 1-20 of 84

  • 1 / 5
  • Development of ROS navigation components using omni-directional images-based lane recognition for IGVC Auto-Nav challenge environment  [in Japanese]

    河野 辰哉

    … This paper describes the development of Robot Operating System (ROS) component for lane recognition and navigation of IGVC Auto - Nav Challenge. … To achieve a robust and stable navigation, we propose new lane and obstacle recognition algorithm based on omnidirectional camera. … The effectiveness of the newly proposed algorithm was confirmed by both offline simulation and actual outdoor experiment. …

    法政大学大学院紀要. 理工学・工学研究科編 (60), 1-6, 2019-03-31

    IR  DOI 

  • Development of a Recognition System for Spraying Areas from Unmanned Aerial Vehicles Using a Machine Learning Approach

    トファエル アハメド , 野口 良造 , Pengbo Gao , Yan Zhang , Linhuan Zhang , Ryozo NOGUCHI , Ahamed TOFAEL

    … The recognition system was divided into offline and online systems. … In the offline recognition system, 74.4% accuracy was obtained for the classifiers in recognizing spray and non-spray areas for croplands. … In the case of orchards, the average classifier recognition accuracy of spray and non-spray areas was 77%. …

    Sensors 19(2), 313, 2019-01

    IR 

  • Vision Based Analysis on Trajectories of Notes Representing Ideas Toward Workshop Summarization  [in Japanese]

    OYAMADA Yuji , MORI Mikihiko , MAENAMI Haruhiko

    … The recognition and tracking results are saved and used for further offline analysis. …

    Proceedings of the Annual Conference of JSAI JSAI2019(0), 2C5E504-2C5E504, 2019

    J-STAGE 

  • Removing Noise from Handwritten Character Images using U-Net  [in Japanese]

    KOMATSU Rina

    <p>オフライン手書き文字認識は、AIによる技術・アルゴリズムにとって未だに残る難しい課題となっている。これは手書きのドキュメントにて、スキャン処理を行う間に、画像内で頻繁にノイズがいくつか生じてしまうためである。スキャンされた画像にあるノイズの存在は、画像を濁らせたりぼやけさせたりし、読みにくくなってしまう。本研究では、3,036種類の日本語を含んだ607,200枚のサンプル画像の分 …

    Proceedings of the Annual Conference of JSAI JSAI2018(0), 4M101-4M101, 2018

    J-STAGE 

  • A Quantitative Quality Measurement for Codebook in Feature Encoding Strategies

    Shinomiya Yuki , Hoshino Yukinobu

    … In image recognition problems, this approach treats an image as a set of partial feature descriptors. … The first experiment investigates the distribution of prior probabilities and compares recognition performances of recent techniques. … The results suggest that recognition performance probably depends on the distribution of prior probabilities. …

    Journal of Advanced Computational Intelligence and Intelligent Informatics 21(7), 1232-1239, 2017

    J-STAGE 

  • Special Issue on Robot Audition Technologies

    Okuno Hiroshi G. , Nakadai Kazuhiro

    … Nakadai and Koiwa present audio-visual automatic speech recognition, and Nakadai, Tezuka, et al. … enhance the human-voice online and offline for a hose-shaped rescue robot with a microphone array.</p><p>In monitoring animal acoustics in natural habitats, Suzuki, Matsubayashi, et al. …

    Journal of Robotics and Mechatronics 29(1), 15-15, 2017

    J-STAGE 

  • Wayang Robot with Gamelan Music Pattern Recognition

    Tomo Tito Pradhono , Schmitz Alexander , Enriquez Guillermo , Hashimoto Shuji , Sugano Shigeki

    … Furthermore, we developed a gamelan music pattern recognition, towards a robot that can perform based on the gamelan music. … In the offline experiment, we extracted energy (time domain), spectral rolloff, 13 Mel-frequency cepstral coefficients (MFCCs), and the harmonic ratio from 5 s long clips, every 0.025 s, with a window length of 1 s, for a total of 2576 features. …

    Journal of Robotics and Mechatronics 29(1), 137-145, 2017

    J-STAGE 

  • A Segmentation Method of Single- and Multiple-Touching Characters in Offline Handwritten Japanese Text Recognition

    NGUYEN Kha Cong , NGUYEN Cuong Tuan , NAKAGAWA Masaki

    … <p>This paper presents a method to segment single- and multiple-touching characters in offline handwritten Japanese text recognition with practical speed. … Distortions due to handwriting and a mix of complex Chinese characters with simple phonetic and alphanumeric characters leave optical handwritten text recognition (OHTR) for Japanese still far from perfection. …

    IEICE Transactions on Information and Systems E100.D(12), 2962-2972, 2017

    J-STAGE 

  • Performance Analysis of Multi-step GA for Real-time 3D Model-Based Recognition for Underwater Vehicle  [in Japanese]

    Lwin Khin Nwe , YONEMORI Kenta , Myint Myo , YANOU Akira , MINAMI Mamoru

    … In this system,(position and orientation) pose between vehicle and target is estimated by means of 3D model-based recognition utilizing Multi-step GA. … This paper analyses the performance of Multi-step GA for 3D recognition for underwater vehicle effectively based on the variations and modification in GA parameters. … The recognition accuracy using Multi-step GA is evaluated by using offline full search. …

    The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) 2016(0), 2A1-18b1, 2016

    J-STAGE 

  • QP Selection Optimization for Intra-Frame Encoding Based on Constant Perceptual Quality

    WANG Chao , MOU Xuanqin , ZHANG Lei

    … The proposed method has acceptable encoding complexity for offline applications. …

    IEICE Transactions on Information and Systems E99.D(2), 443-453, 2016

    J-STAGE 

  • Bus ride estimation using Cellular Radio Characteristics  [in Japanese]

    Hanano Hiroshi , Izumikawa Haruki , Okada Hiroshi , Ishikawa Yuichi , Ono Chihiro

    … 筆者らは,スマートフォン上におけるクーポン配信と,プッシュメディアとしての移動体デジタルサイネージを組み合わせたO2O(Online-to-Offline)サービスを検討している.具体的には,ユーザに対し,バス・電車等に設置した移動体デジタルサイネージ上にクーポンの存在を告知してスマートフォン上のクーポン取得へと誘導し,広告配信元店舗へ送客するサービスである.この際,どの程度のユーザが広告の表示された交通機関を使 …

    IEICE technical report. Information networks 114(401), 19-23, 2015-01-22

  • Optimized wavelet-domain filtering under noisy and reverberant conditions

    R. Gomez , T. Kawahara , K. Nakadai

    … The paper addresses a robust wavelet-based speech enhancement for automatic speech recognition in reverberant and noisy conditions. … In the offline mode, the optimal wavelet family is selected separately for the speech, late reflections, and background noise based on the AM likelihood. … For speech recognition, the most suitable wavelet is identified from the pre-stored wavelets, and wavelet-domain filtering is conducted to the noisy and reverberant speech signal. …

    APSIPA Transactions on Signal and Information Processing 4(e3), 1-12, 2015

    IR 

  • Combination of LSTM and CNN for recognizing mathematical symbols

    HAI Nguyen Dai , ANH Le Duc , NAKAGAWA Masaki

    … In this paper we present a combination of CNN and LSTM, which are both sophisticated neural networks and good classifiers for offline and online handwriting mathematical character recognition, respectively. … The best combination ensemble has a recognition rate which is higher than the rate achieved by the best individual classifier on the Mathbrush database. …

    電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 114(306), 287-292, 2014-11-17

  • A Method for Embedding Context to Sound-based Life Log

    Watanabe Hiroki , Terada Tsutomu , Tsukamoto Masahiko

    … In this paper, we propose an activity and context recognition method where the user carries a neck-worn receiver comprising a microphone, and small speakers on his/her wrists that generate ultrasounds. … We combine the gesture recognition by using ultrasound and conventional MFCC-based environmental-context recognition to recognize complex contexts from the recorded sound. …

    Journal of information processing 22(4), 651-659, 2014-10-15

    IPSJ  IR  J-STAGE 

  • Neural Networks for Rotated Character Recognition  [in Japanese]

    Yoshihisa Shinozawa

    … して産業技術総合研究所提供の文字画像データベースETL9B,3,036字種を認識対象として,ニューラルネットワークを構築した結果,文字種の多い場合においても,回転文字の学習が可能であること,文字を回転させて認識を行い,認識結果を統合することによって,認識率の向上が図れたことを示す.The recognition of rotated character patterns is thought to be one of the more difficult problems in the field of pattern recognition. …

    IPSJ Journal 55(10), 2300-2308, 2014-10-15

    IPSJ 

  • A Method for Embedding Context to Sound-based Life Log

    Hiroki Watanabe , Tsutomu Terada , Masahiko Tsukamoto

    … In this paper, we propose an activity and context recognition method where the user carries a neck-worn receiver comprising a microphone, and small speakers on his/her wrists that generate ultrasounds. … We combine the gesture recognition by using ultrasound and conventional MFCC-based environmental-context recognition to recognize complex contexts from the recorded sound. …

    情報処理学会論文誌 55(8), 2014-08-15

    IPSJ 

  • Flatness Intelligent Control Based on T-S Cloud Inference Neural Network

    Zhang Xiuling , Zhao Liang , Zang Jiayin , Fan Hongmin , Cheng Long

    … Based on the new network, flatness recognition model and flatness predictive model are established. … Initial parameters of the controller are firstly determined through offline training based on measured data, and then they are optimized online automatically. …

    ISIJ International 54(11), 2608-2617, 2014

    J-STAGE 

  • 2A1-H04 Negative Obstacle Detection and Drivability Judgement for Mobility User Support(Demonstration experiments of personal mobility robots in Mobility Robot Special Zone of Tsukuba-city)  [in Japanese]

    HORIUCHI Eiichi

    … Risks on road surfaces are defined by subjective judgement from users that a surface is drivable or not so that risk detection can meet risk recognition of users. … After the risks are modeled by offline learning by SVM of those judgements as well as range images, they are predicted online. …

    The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) 2014(0), _2A1-H04_1-_2A1-H04_4, 2014

    J-STAGE 

  • Handwritten Character Segmentation from Images with Overlapping Characters  [in Japanese]

    Nishi Daichi , Yokomichi Masahiro

    … In the handwritten character recognition from image, it is necessary to extract each character from the string. … The latter is based on a image feature used in character recognition. …

    Memoirs of the Faculty of Engineering, Miyazaki University (42), 257-262, 2013-08-30

    IR 

  • Segmentation-free MRF Recognition Method in Combination with P2DBMN-MQDF for Online Handwritten Cursive Word

    ZHU Bilan , Shivram Arti , Setlur Srirangaraj , Govindaraju Venu , Nakagawa Masaki

    … This paper describes an online handwritten English cursive word recognition method using a segmentation-free Markov random field (MRF)model in combination with an offline recognition method which uses pseudo 2D bi-moment normalization (P2DBMN)and modified quadratic discriminant function (MQDF). … Each character is modeled as a MRF and word MRFs are constructed by concatenating character MRFs according to a trie lexicon of words during recognition. …

    Technical report of IEICE. PRMU 112(495), 213-218, 2013-03-14

  • 1 / 5
Page Top