TY - JOUR
T1 - A pooled Object Bank descriptor for image scene classification
AU - Zang, Mujun
AU - Wen, Dunwei
AU - Liu, Tong
AU - Zou, Hailin
AU - Liu, Chanjuan
N1 - Publisher Copyright:
© 2017
PY - 2018/3/15
Y1 - 2018/3/15
N2 - Object Bank (OB) is a high-level image representation encoding semantic and spacial information, and has superior performance in scene classification tasks. However, the dimensionality of OB feature is high, which demands massive computation. Existing dimensionality reduction methods for OB are incapable of achieving both high classification accuracy and substantial dimensionality reduction simultaneously. In order to solve this problem, we propose a threshold value filter pooling method to avoid noise accumulation in histogram-pooling and represent more useful information than max-pooling. We also propose a Matthew effect normalization method to highlight the useful information, and thus boost the performance of OB-based image scene classification. Finally, we apply these two methods in a dimensionality reduction framework to simplify OB representation and construct more proper descriptors, and thus achieve both dimensionality reduction and classification accuracy increase. We evaluated our framework on three real-world datasets, namely, event dataset UIUC-Sports, natural scene dataset LabelMe, and mixture dataset 15-Scenes. The classification results demonstrate that our framework not only obtains accuracies similar to or higher than the original OB representation, but also reduces the dimensionality significantly. The computational complexity analysis shows that it can reduce the time complexity of classification. Therefore, our framework can improve OB-based image scene classification through both computational complexity reduction and accuracy increase.
AB - Object Bank (OB) is a high-level image representation encoding semantic and spacial information, and has superior performance in scene classification tasks. However, the dimensionality of OB feature is high, which demands massive computation. Existing dimensionality reduction methods for OB are incapable of achieving both high classification accuracy and substantial dimensionality reduction simultaneously. In order to solve this problem, we propose a threshold value filter pooling method to avoid noise accumulation in histogram-pooling and represent more useful information than max-pooling. We also propose a Matthew effect normalization method to highlight the useful information, and thus boost the performance of OB-based image scene classification. Finally, we apply these two methods in a dimensionality reduction framework to simplify OB representation and construct more proper descriptors, and thus achieve both dimensionality reduction and classification accuracy increase. We evaluated our framework on three real-world datasets, namely, event dataset UIUC-Sports, natural scene dataset LabelMe, and mixture dataset 15-Scenes. The classification results demonstrate that our framework not only obtains accuracies similar to or higher than the original OB representation, but also reduces the dimensionality significantly. The computational complexity analysis shows that it can reduce the time complexity of classification. Therefore, our framework can improve OB-based image scene classification through both computational complexity reduction and accuracy increase.
KW - Dimensionality reduction
KW - Image classification
KW - Image feature
KW - Object Bank
KW - Pooling
UR - http://www.scopus.com/inward/record.url?scp=85033583521&partnerID=8YFLogxK
U2 - 10.1016/j.eswa.2017.10.057
DO - 10.1016/j.eswa.2017.10.057
M3 - Journal Article
AN - SCOPUS:85033583521
SN - 0957-4174
VL - 94
SP - 250
EP - 264
JO - Expert Systems with Applications
JF - Expert Systems with Applications
ER -