JAIST Repository >
School of Information Science >
Conference Papers >
Conference Papers >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/12344

Title: Informative Census Transform for Very Low-Resolution Image Representation
Authors: Jeong, Sungmoon
Lee, Hosun
Chong, Nak Young
Keywords: upsupervised feature representation
informative census transform
submodular optimization
greedy algorithm
very low resolution images
Issue Date: 2014-08
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Magazine name: IEEE International Symposium on Robotand Human Interactive Communication
Start page: 435
End page: 440
DOI: 10.1109/ROMAN.2014.6926291
Abstract: Our paper newly presents unsupervised feature representation method for very low-resolution (VLR) images called informative census transform (ICT) based on statistical analysis of CT binary features and submodular optimization. A new cost function is designed to measure the informativeness of each binary feature: (1) an individual informativeness of features to represent unlabeled image dataset and (2) relative informativeness between binary features to represent different binary features. Therefore, we considered informativeness of binary feature according to two relationship (1) between feature space and image space, and (2) between different features within same feature space. Moreover, two constraints are designed by considering sub-modular characteristics to guarantee theoretical performance and fast optimization via simple greedy algorithm. Experimental results show that the proposed ICTfeatures with two constraints outperforms the traditional CT features in terms of recognition performance and computational cost at VLR problem.
Rights: This is the author's version of the work. Copyright (C) 2014 IEEE. IEEE International Symposium on Robotand Human Interactive Communication, 2014, 435-440. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
URI: http://hdl.handle.net/10119/12344
Material Type: author
Appears in Collections:b11-1. 会議発表論文・発表資料 (Conference Papers)

Files in This Item:

File Description SizeFormat
20321.pdf420KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.

 


Contact : Library Information Section, JAIST (ir-sys[at]ml.jaist.ac.jp)