1. Scene Labeling using Kernel Codebook Encoding
- Author
-
Hasan Fehmi Ateş, Sercan Sünetci, Bölüm Yok, Ates, Hasan F. -- 0000-0002-6842-1528, and [Ates, Hasan F. -- Sunetci, Sercan] Isik Univ, Elekt Elekt Muhendisligi Bolumu, Istanbul, Turkey
- Subjects
Pixel ,business.industry ,Feature vector ,Codebook ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Scale-invariant feature transform ,Pattern recognition ,Image processing ,superpixel ,02 engineering and technology ,Image segmentation ,03 medical and health sciences ,0302 clinical medicine ,Kernel (image processing) ,Histogram ,0202 electrical engineering, electronic engineering, information engineering ,image parsing ,020201 artificial intelligence & image processing ,Computer vision ,Artificial intelligence ,feature encoding ,business ,030217 neurology & neurosurgery ,Mathematics - Abstract
25th Signal Processing and Communications Applications Conference (SIU) -- MAY 15-18, 2017 -- Antalya, TURKEY WOS: 000413813100213 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. Turk Telekom, Arcelik A S, Aselsan, ARGENIT, HAVELSAN, NETAS, Adresgezgini, IEEE Turkey Sect, AVCR Informat Technologies, Cisco, i2i Syst, Integrated Syst & Syst Design, ENOVAS, FiGES Engn, MS Spektral, Istanbul Teknik Univ
- Published
- 2017