Local Patch Vectors Encoded by Fisher Vectors for Image Classification
AbstractThe objective of this work is image classification, whose purpose is to group images into corresponding semantic categories. Four contributions are made as follows: (i) For computational simplicity and efficiency, we directly adopt raw image patch vectors as local descriptors encoded by Fisher vector (FV) subsequently; (ii) For obtaining representative local features within the FV encoding framework, we compare and analyze three typical sampling strategies: random sampling, saliency-based sampling and dense sampling; (iii) In order to embed both global and local spatial information into local features, we construct an improved spatial geometry structure which shows good performance; (iv) For reducing the storage and CPU costs of high dimensional vectors, we adopt a new feature selection method based on supervised mutual information (MI), which chooses features by an importance sorting algorithm. We report experimental results on dataset STL-10. It shows very promising performance with this simple and efficient framework compared to conventional methods. View Full-Text
Share & Cite This Article
Chen, S.; Liu, H.; Zeng, X.; Qian, S.; Wei, W.; Wu, G.; Duan, B. Local Patch Vectors Encoded by Fisher Vectors for Image Classification. Information 2018, 9, 38.
Chen S, Liu H, Zeng X, Qian S, Wei W, Wu G, Duan B. Local Patch Vectors Encoded by Fisher Vectors for Image Classification. Information. 2018; 9(2):38.Chicago/Turabian Style
Chen, Shuangshuang; Liu, Huiyi; Zeng, Xiaoqin; Qian, Subin; Wei, Wei; Wu, Guomin; Duan, Baobin. 2018. "Local Patch Vectors Encoded by Fisher Vectors for Image Classification." Information 9, no. 2: 38.
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.