KSR-BOF: a new and exemplified method (as KSRs method) for image classification

作     者：Maleki, Mohammad Hassan Hodtani, Ghosheh Abed Hashemi, Seyed Hesam Odin 

作者机构：Sadjad Univ Technol Dept Elect Engn Mashhad Razavi Khorasan Iran Ferdowsi Univ Mashhad Dept Elect Engn Mashhad Razavi Khorasan Iran 

出 版 物：《IET IMAGE PROCESSING》 (IET影像处理)

年 卷 期：2020年第14卷第5期

页      面：853-861页

核心收录：

学科分类：0808[工学-电气工程] 1002[医学-临床医学] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：computer vision feature extraction image classification linear codes image representation image coding pattern recognition computer vision max-pooling sum-pooling average-pooling dictionary atoms coding coefficients pooling methods image classification task KSR method classification accuracy compact representation discriminative final representation two-part KSR bag-of-features locality-constrained linear coding linear distance coding sparse coding scene classification KSR-BOF method K-strongest responses UC Merced land 19-class satellite scene 

摘      要：Image classification is very important in pattern recognition and computer vision, where, for integrating final representation, feature pooling methods of the max-pooling, sum-pooling and average-pooling have been widely used. In this study, the authors propose a new method called K-strongest responses (KSRs) on the dictionary atoms for integrating the coding coefficients to generate the final representation that is compared with the previous pooling methods, produces better performance for the image classification task. On the basis of the KSR method, to improve classification accuracy and generate more compact and discriminative final representation, a new framework consisting of two-part KSR and bag-of-features is proposed. To evaluate the performance of the proposed method and framework, they apply it to locality-constrained linear coding, linear distance coding and sparse coding by using two datasets from benchmarks of scene classification: 19-class satellite scene and UC Merced Land. The results show that the coding coefficients integrated by their method and framework are more discriminative than other methods.