TY - GEN
T1 - Pornographic image classification based on top down color-saliency based BoW representation
AU - Tian, Chunna
AU - Zhang, Xiangnan
AU - Gao, Xinbo
AU - Wei, Wei
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/12/11
Y1 - 2014/12/11
N2 - Since color is an important visual clue of the pornographic image, this study presents a new framework for pornographic image classification based on the fusion of color and shape information for the bag of words representation. This framework contains three fusion patterns: The early fusion, late fusion and top down color-saliency based fusion, which are compared intensively. Based on the comparison, the top down color-saliency fusion based pornographic image classification method is proposed by using the statistical class prior of each color word to weight the shape word. In the late fusion and color-saliency based fusion, color name is adopt to represent the color information. To verify the effectiveness of spatial constrain on the words, we also compared the shape features quantized by vector quantization and locality-constrained linear coding. The experimental results show that our model combines the shape and color information properly and it is superior over the popular methods to distinguish the normal and pornographic-like images from the pornographic ones.
AB - Since color is an important visual clue of the pornographic image, this study presents a new framework for pornographic image classification based on the fusion of color and shape information for the bag of words representation. This framework contains three fusion patterns: The early fusion, late fusion and top down color-saliency based fusion, which are compared intensively. Based on the comparison, the top down color-saliency fusion based pornographic image classification method is proposed by using the statistical class prior of each color word to weight the shape word. In the late fusion and color-saliency based fusion, color name is adopt to represent the color information. To verify the effectiveness of spatial constrain on the words, we also compared the shape features quantized by vector quantization and locality-constrained linear coding. The experimental results show that our model combines the shape and color information properly and it is superior over the popular methods to distinguish the normal and pornographic-like images from the pornographic ones.
KW - Bag of words
KW - Color-saliency
KW - Pornographic image classification
KW - Top down attention
UR - http://www.scopus.com/inward/record.url?scp=84920735530&partnerID=8YFLogxK
U2 - 10.1109/SPAC.2014.6982698
DO - 10.1109/SPAC.2014.6982698
M3 - 会议稿件
AN - SCOPUS:84920735530
T3 - Proceedings 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics, SPAC 2014
SP - 273
EP - 278
BT - Proceedings 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics, SPAC 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics, SPAC 2014
Y2 - 18 October 2014 through 19 October 2014
ER -