| Přispěvatelé: |
Bölüm Yok, Ates, H.F., Elektrik-Elektronik Mühendisligi Bölümü, Işik Üniversitesi, Istanbul, Turkey -- Sunetci, S., Elektrik-Elektronik Mühendisligi Bölümü, Işik Üniversitesi, Istanbul, Turkey |
| Popis: |
25th Signal Processing and Communications Applications Conference, SIU 2017 -- 15 May 2017 through 18 May 2017 -- -- 128703 Superpixel based methods have recently shown success in scene segmentation and labeling. In scene labeling, a superpixel algorithm is used first to segment the image into visually consistent small regions; then several feature descriptors are computed and classification is performed for each superpixel. In this paper, Kernel Codebook Encoding (KCB) of superpixel features is proposed. In KCB feature vectors are mapped to multiple codewords in a soft manner, instead of the usual hard quantization. The weights assigned to the codewords are determined by a kernel distance function. KCB method is used for encoding of SIFT features in SuperParsing image parsing algorithm. The developed approach is tested on the SIFT Flow dataset consisting of 2,688 images and 33 classes, and achieves 2.7% increase in parsing accuracy over SuperParsing. © 2017 IEEE. |
