The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Pengecaman gaya berjalan membezakan seseorang individu daripada orang lain mengikut corak semula jadi gaya berjalan manusia. Pengecaman gait ialah teknologi pemprosesan isyarat yang mencabar untuk pengecaman biometrik disebabkan oleh kekaburan kontur dan prosedur pengekstrakan ciri yang kompleks. Dalam kerja ini, kami mencadangkan model baharu - mekanisme perhatian bersama (CJAM) rangkaian saraf konvolusional (CNN) - untuk mengklasifikasikan jujukan berjalan dan menjalankan pengenalpastian orang menggunakan set data gait CASIA-A dan CASIA-B. Model CNN mempunyai keupayaan untuk mengekstrak ciri gaya berjalan, dan mekanisme perhatian terus menumpukan pada kawasan yang paling diskriminatif untuk mencapai pengenalan orang. Kami mempersembahkan transformasi menyeluruh daripada prapemprosesan imej gait kepada pengenalan akhir. Keputusan daripada 12 eksperimen menunjukkan bahawa model perhatian baharu membawa kepada kadar ralat yang lebih rendah daripada yang lain. Model CJAM menambah baik 3D-CNN, CNN-LSTM (memori jangka pendek panjang) dan CNN ringkas masing-masing sebanyak 8.44%, 2.94% dan 1.45%.
Pengtao JIA
Xi'an University of Science and Technology
Qi ZHAO
Xi'an University of Science and Technology
Boze LI
Xi'an University of Science and Technology
Jing ZHANG
Xi'an University of Science and Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Pengtao JIA, Qi ZHAO, Boze LI, Jing ZHANG, "CJAM: Convolutional Neural Network Joint Attention Mechanism in Gait Recognition" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 8, pp. 1239-1249, August 2021, doi: 10.1587/transinf.2020BDP0010.
Abstract: Gait recognition distinguishes one individual from others according to the natural patterns of human gaits. Gait recognition is a challenging signal processing technology for biometric identification due to the ambiguity of contours and the complex feature extraction procedure. In this work, we proposed a new model - the convolutional neural network (CNN) joint attention mechanism (CJAM) - to classify the gait sequences and conduct person identification using the CASIA-A and CASIA-B gait datasets. The CNN model has the ability to extract gait features, and the attention mechanism continuously focuses on the most discriminative area to achieve person identification. We present a comprehensive transformation from gait image preprocessing to final identification. The results from 12 experiments show that the new attention model leads to a lower error rate than others. The CJAM model improved the 3D-CNN, CNN-LSTM (long short-term memory), and the simple CNN by 8.44%, 2.94% and 1.45%, respectively.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020BDP0010/_p
Salinan
@ARTICLE{e104-d_8_1239,
author={Pengtao JIA, Qi ZHAO, Boze LI, Jing ZHANG, },
journal={IEICE TRANSACTIONS on Information},
title={CJAM: Convolutional Neural Network Joint Attention Mechanism in Gait Recognition},
year={2021},
volume={E104-D},
number={8},
pages={1239-1249},
abstract={Gait recognition distinguishes one individual from others according to the natural patterns of human gaits. Gait recognition is a challenging signal processing technology for biometric identification due to the ambiguity of contours and the complex feature extraction procedure. In this work, we proposed a new model - the convolutional neural network (CNN) joint attention mechanism (CJAM) - to classify the gait sequences and conduct person identification using the CASIA-A and CASIA-B gait datasets. The CNN model has the ability to extract gait features, and the attention mechanism continuously focuses on the most discriminative area to achieve person identification. We present a comprehensive transformation from gait image preprocessing to final identification. The results from 12 experiments show that the new attention model leads to a lower error rate than others. The CJAM model improved the 3D-CNN, CNN-LSTM (long short-term memory), and the simple CNN by 8.44%, 2.94% and 1.45%, respectively.},
keywords={},
doi={10.1587/transinf.2020BDP0010},
ISSN={1745-1361},
month={August},}
Salinan
TY - JOUR
TI - CJAM: Convolutional Neural Network Joint Attention Mechanism in Gait Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 1239
EP - 1249
AU - Pengtao JIA
AU - Qi ZHAO
AU - Boze LI
AU - Jing ZHANG
PY - 2021
DO - 10.1587/transinf.2020BDP0010
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2021
AB - Gait recognition distinguishes one individual from others according to the natural patterns of human gaits. Gait recognition is a challenging signal processing technology for biometric identification due to the ambiguity of contours and the complex feature extraction procedure. In this work, we proposed a new model - the convolutional neural network (CNN) joint attention mechanism (CJAM) - to classify the gait sequences and conduct person identification using the CASIA-A and CASIA-B gait datasets. The CNN model has the ability to extract gait features, and the attention mechanism continuously focuses on the most discriminative area to achieve person identification. We present a comprehensive transformation from gait image preprocessing to final identification. The results from 12 experiments show that the new attention model leads to a lower error rate than others. The CJAM model improved the 3D-CNN, CNN-LSTM (long short-term memory), and the simple CNN by 8.44%, 2.94% and 1.45%, respectively.
ER -