Volume 12, Issue 4 (12-2020)                   itrc 2020, 12(4): 33-45 | Back to browse issues page

XML Print


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

Keyvanpour M, Mehrmolaei S, Ahmadzadeh Hosseini H S. IR-WCO2C: An Enhanced Multi Operators-Based Approach for Content-Aware Image Retargeting . itrc 2020; 12 (4) :33-45
URL: http://ijict.itrc.ac.ir/article-1-470-en.html
1- Department of Computer Engineering, Faculty of Engineering, Alzahra University Tehran, Iran , keyvanpour@alzahra.ac.ir
2- Department of Computer Engineering, Faculty of Engineering, Data Mining Lab Alzahra University Tehran, Iran
3- Department of Computer Engineering, Faculty of Engineering, Alzahra University Tehran, Iran
Abstract:   (568 Views)
In recent years, the image retargeting (IR) problem has been discussed as one of the challenging topics in the field of image processing in different applied domains. In this paper, a multi operators hybrid method is proposed (IR-WCO2C) to improve performance of an IR system, which is performed in three sub-systems. Firstly, the identification precision of important regions is enhanced using a feature extraction technique based on wavelet coefficients (WC) then identified the saliency map of images. In second sub-system, this saliency map is used to improve performance of seam carving process instead of the saliency map identified by conventional methods. Finally, the act of operators selection is improved using metaheuristic techniques to optimize process of operators combination. Findings reveal that our method, IR-WCO2C provided the highest precision (0.74) in the IR process. Also, IR-WCO2C provided an improvement of 20% over the previous methods in different stages of the IR. 
Full-Text [PDF 1149 kb]   (225 Downloads)    
Type of Study: Research | Subject: Information Technology

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

Send email to the article author


Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.