Paper Info
Title
Texture Complexity Based Redundant Regions Ranking for Object Proposal.
Abstract
Object proposal has been successfully applied in recent visual object detection approaches and shown improved computational efficiency. The purpose of object proposal is to use as few as regions to cover as many as objects. In this paper, we propose a strategy named Texture Complexity based Redundant Regions Ranking (TCR) for object proposal. Our approach first produces rich but redundant regions using a color segmentation approach, i.e. Selective Search. It then uses Texture Complexity (TC) based on complete contour number and Local Binary Pattern (LBP) entropy to measure the objectness score of each region. By ranking based on the TC, it is expected that as many as true object regions are preserved, while the number of the regions is significantly reduced. Experimental results on the PASCAL VOC 2007 dataset show that the proposed TCR significantly improves the baseline approach by increasing AUC (area under recall curve) from 0.39 to 0.48. It also outperforms the state-of-the-art with AUC and uses fewer detection proposals to achieve comparable recall rates.
Year
DOI
Venue
2016
10.1109/CVPRW.2016.139
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Field
DocType
Volume
Object detection,Computer vision,Pattern recognition,Ranking,Computer science,Segmentation,Local binary patterns,Artificial intelligence,Recall
Conference
2016
Issue
ISSN
Citations 
1
2160-7508
1
PageRank 
References 
Authors
0.35
17
6
Name
Order
Citations
PageRank
Wei Ke17112.11
Tianliang Zhang242.41
Jie Chen31476.37
Fang Wan4213.44
Qixiang Ye591364.51
Zhenjun Han617616.40