Volume 5, Issue 2 (9-2016)                   SCJ 2016, 5(2): 34-47 | Back to browse issues page

XML Persian Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Regions Proposal Selection in Objects Detection and Recogntion Systems. SCJ. 2016; 5 (2) :34-47
URL: http://scj.kashanu.ac.ir/article-1-353-en.html
Abstract:   (1159 Views)

According to the studies carried out in recent years, determination of the regional proposal is one of the crucial steps in detection and recognition of the objects included in an image. In fact, determination of this region has been like a bottleneck, gaining a significant computational energy. As a result, selection of suitable and fast approaches, under these circumstance, may enhance the performance of the recognition system. In this paper, a review was provided on the recent studies carried out in this field of research and few of the famous and friendly approaches conventionally used in the strong recognition systems were introduced and applied on the dataset of PASCAL VOC, ImageNet and COCO. The results obtained indicated that the multiclass combinatorial grouping (MCG) method with the region-convoulational neural network (R-CNN) can provide the best results with the efficiency of 57%, 54% and 41% on the dataset of PASCAL VOC 2007, ImageNet 2013 and COCO 2014  respectively.

Full-Text [PDF 1255 kb]   (392 Downloads)    
Type of Study: Research | Subject: Special
Received: 2016/07/10 | Accepted: 2017/04/16 | Published: 2017/10/29

Add your comments about this article : Your username or Email:
CAPTCHA code

© 2018 All Rights Reserved | Soft Computing Journal

Designed & Developed by : Yektaweb