ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Automated Human Recognition by Gait using Neural Network
Cited 77 time in scopus Download 1 time Share share facebook twitter linkedin kakaostory
저자
유장희, 황두성, 문기영, Mark S. Nixon
발행일
200811
출처
International Workshops on Image Processing Theory, Tools and Applications (IPTA) 2008, pp.1-6
DOI
https://dx.doi.org/10.1109/IPTA.2008.4743792
협약과제
08MS2800, 프라이버시 보호형 바이오인식 시스템 개발, 문기영
초록
We describe a new method for recognizing humans by their gait using back-propagation neural network. Here, the gait motion is described as rhythmic and periodic motion, and a 2D stick figure is extracted from gait silhouette by motion information with topological analysis guided by anatomical knowledge. A sequential set of 2D stick figures is used to represent the gait signature that is primitive data for the feature extraction based on motion parameters. Then, a back-propagation neural network algorithm is used to recognize humans by their gait patterns. In experiments, higher gait recognition performances have been achieved. © 2008 IEEE.
KSP 제안 키워드
Back Propagation(BP), Feature extractioN, Gait motion, Gait recognition, Human Recognition, Motion information, Motion parameters, Neural network algorithm, Periodic motion, Stick figure, back-propagation neural network