DocumentCode :
249677
Title :
Aggregating contour fragments for shape classification
Author :
Song Bai ; Xinggang Wang ; Xiang Bai
fYear :
2014
fDate :
27-30 Oct. 2014
Firstpage :
5252
Lastpage :
5256
Abstract :
In this paper, we address the problem of building a compact representation for shape. We first decompose shape into meaningful contour fragments, and each fragment is described by a certain descriptor, e.g., Shape Context. Then inspired by the coding scheme Vector of Locally Aggregated Descriptors widely used in image representation, we try to aggregate the contour fragments into a very compact vector of limited dimension to stand for a shape, and we name the new designed shape descriptor as Vector of Aggregated Contour Fragments (VACF). We apply VACF to shape classification task on the well-known MPEG-7 shape benchmark, and the experimental results show that the accuracy of our proposed method outperforms other state-of-the-art algorithms with much smaller memory usage.
Keywords :
image classification; image representation; image representation; shape classification; shape context; vector of aggregated contour fragments; Accuracy; Computer vision; Context; Principal component analysis; Shape; Training; Vectors; Compact Representation; Contour Fragments; Shape Classification; VACF;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2014 IEEE International Conference on
Conference_Location :
Paris
Type :
conf
DOI :
10.1109/ICIP.2014.7026063
Filename :
7026063
Link To Document :
بازگشت