Object recognition based on image sequences by using inter-feature-line consistencies

by: CHEN Jiun-Hung, CHEN Chu-Song

Pattern Recognition, Vol. 37, No. 9. (2004), pp. 1913-1923.

View FullText article

http://cat.inist.fr/?aModele=afficheN&…

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

edgarbc

Find related articles with these CiteULike tags

object-recognition, representation

Abstract

An image sequence-based framework for appearance-based object recognition is proposed in this paper. Compared with the methods of using a single view for object recognition, inter-frame consistencies can be exploited in asequence-based method, so that a better recognition performance can be achieved. We use the nearest feature line (NFL) method (IEEE Trans. Neural Networks 10 (1999) 439) to model each object. The NFL method is extended in this paper by further integrating motion-continuity information between features lines in a probabilistic framework. The associated recognition task is formulated as maximizing an a posteriori probability measure. The recognition problem is then further transformed to a shortest-path searching problem, and a dynamic-programming technique is used to solve it.

@article{citeulike:2891102, abstract = {An image sequence-based framework for appearance-based object recognition is proposed in this paper. Compared with the methods of using a single view for object recognition, inter-frame consistencies can be exploited in asequence-based method, so that a better recognition performance can be achieved. We use the nearest feature line (NFL) method (IEEE Trans. Neural Networks 10 (1999) 439) to model each object. The NFL method is extended in this paper by further integrating motion-continuity information between features lines in a probabilistic framework. The associated recognition task is formulated as maximizing an a posteriori probability measure. The recognition problem is then further transformed to a shortest-path searching problem, and a dynamic-programming technique is used to solve it.}, author = {Jiun-Hung, C. H. E. N. and Chu-Song, C. H. E. N. }, citeulike-article-id = {2891102}, journal = {Pattern Recognition}, keywords = {object-recognition, representation}, number = {9}, pages = {1913--1923}, posted-at = {2008-06-13 11:46:41}, priority = {3}, title = {Object recognition based on image sequences by using inter-feature-line consistencies}, url = {http://cat.inist.fr/?aModele=afficheN\&\#38;cpsidt=15924408}, volume = {37}, year = {2004} }

RIS record

TY - JOUR ID - citeulike:2891102 L3 - citeulike-article-id:2891102 TI - Object recognition based on image sequences by using inter-feature-line consistencies JF - Pattern Recognition VL - 37 IS - 9 SP - 1913 EP - 1923 N2 - An image sequence-based framework for appearance-based object recognition is proposed in this paper. Compared with the methods of using a single view for object recognition, inter-frame consistencies can be exploited in asequence-based method, so that a better recognition performance can be achieved. We use the nearest feature line (NFL) method (IEEE Trans. Neural Networks 10 (1999) 439) to model each object. The NFL method is extended in this paper by further integrating motion-continuity information between features lines in a probabilistic framework. The associated recognition task is formulated as maximizing an a posteriori probability measure. The recognition problem is then further transformed to a shortest-path searching problem, and a dynamic-programming technique is used to solve it. KW - object-recognition KW - representation AU - Jiun-Hung, CHEN AU - Chu-Song, CHEN PY - 2004/// UR - http://cat.inist.fr/?aModele=afficheN&cpsidt=15924408 ER -

RIS BibTeX