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/10119/15480

Title: Informative Sequential Selection of Variable-Sized Patches for Image Retrieval
Authors: Shen, Zhihao
Lee, Hosun
Jeong, Sungmoon
Chong, Nak Young
Keywords: Sequential feature selection
Image retrieval
Field of view
Information theory
Issue Date: 2017-09-19
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Magazine name: 2017 56th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE)
Start page: 1169
End page: 1172
DOI: 10.23919/SICE.2017.8105625
Abstract: To quickly and efficiently analyze a large-scale environment by the camera with limited field-of-view, intelligent systems should sequentially select the optimal field-of-view to observe an important and informative patch of area. Especially in the image retrieval task, small observations should be sequentially selected to increase the performance of image retrieval and the updated performance can be used to select the next best view again in a cyclic process. In this paper, we have investigated the role of selected image patches, which can be either overlapped or non-overlapped with previous observations, in this cyclic process. To evaluate the different patch selection strategies, the adaptive observation selection method is also described as follows: (1) robots select adaptive observations sequentially based on its prior knowledge from the training dataset. (2) After each selection, the prior knowledge will be updated by discarding the target-irrelevant data for the next observation selection. During this process, we have shown that an informative patch, even though a part of selected patch is already observed at previous steps, can enhance the retrieval accuracy and it has better performance than an independent observation method.
Rights: This is the author's version of the work. Copyright (C) 2017 IEEE. 2017 56th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE), 2017, 1169-1172. 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/10119/15480
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
23573.pdf734KbAdobe PDFView/Open

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


Contact : Library Information Section, Japan Advanced Institute of Science and Technology