Abstract




 
   

IJE TRANSACTIONS B: Applications Vol. 31, No. 5 (May 2018) 684-692    Article in Press

PDF URL: http://www.ije.ir/Vol31/No5/B/1-2755.pdf  
downloaded Downloaded: 168   viewed Viewed: 462

  IMPROVED CONTENT AWARE IMAGE RETARGETING USING STRIP PARTITIONING
 
A. Alavi Gharahbagh and F. Yaghmaee
 
( Received: November 19, 2016 – Accepted in Revised Form: February 08, 2018 )
 
 

Abstract    Based on rapid upsurge in the demand and usage of electronic media devices such as tablets, smart phones, laptops, personal computers, etc. and its different display specifications including the size and shapes, image retargeting became one of the key components of communication technology and internet. The existing techniques in image resizing cannot save the most valuable information of images on display devices with different resolutions. Seam carving is a standard technique for content-aware resizing of images and videos with negligible distortion. However, seam carving resize high-resolution videos and high quality images with high computational complexity; this limits its real-time applications. In this paper, we present a novel approach to reduce seam carving process time. In the proposed technique, the image was split into three equal parts: upper-middle-lower (or right-middle-left) using horizontal or vertical strips. The middle strip was analyzed by original seam carving technique. For other strips (upper-lower), the seam was obtained employing Dijkstra fixed start point technique. In our proposed technique, unlimited Dijkstra depth search was replaced with a limited depth search. It enhances the computational efficiency of Dijkstra technique for the upper and lower strips. The experimental results showed much better computational efficiency than the current enhanced seam carving techniques. These results indicate that computational complexity is superior, while still maintaining the output quality of the original seam carving method.

 

Keywords    Seam Carving, Image Resizing, Image Retargeting, Dijkstra Method, Strip Partitioning

 

چکیده    با توجه به گسترش سریع تقاضا برای رسانه‌های دیجیتال و تجهیزاتی مانند تبلت و گوشی های هوشمند، نیاز مبرم به روشهای که بتوانند ابعاد تصویر را به سرعت با اندازه صفحه نمایشگر تجهیزات مختلف تطبیق دهد به شدت احساس میشود. روش های موجود در تغییر ابعاد تصاویر عمدتا قادر به حفظ اطلاعات دارای محتوای بالاي بصري نبوده و از روش های هندسی برای تغییر ابعاد استفاده میکنند. سيم كاروينگ به عنوان یک روش مبتنی بر محتوا در تغییر ابعاد تصویر و ویدئو گسترش نسبتاً زیادی در سال‌های اخیریافته است. یکی از چالشهای نسبتا بالا در این روش، محاسبات مورد نیاز است كه کاربرد آن را در روشهاي آنلاين محدود می‌کند. با توجه به این موارد در این مقاله یک روش جدید برای کم کردن حجم محاسبات روش سيم كاروينگ پیشنهاد شده که در آن با شکسته شدن تصویر به سه نوار و اعمال الگوریتم اصلی به نوار میانی و تعميم نتیجه آن به نوارهای بالا و پایین تصویر، حجم محاسبات کاهش بسیار مشهود یافته بدون آنکه کیفیت نسبت به روش اصلی کاهش چنداني پيدا كند. علاوه بر این کار برای کم شدن حجم محاسبات عمق جستجو در نوار های بالا و پایین نیز محدود شده است. در نهایت نتایج پیاده سازی كاهش زمان اجرای بسیار قابل توجه و به صورت همزمان حفظ کیفیت خروجی را به صورت قابل قبولی نشان میدهد. نتایج تغییر پارامترهای موجود در الگوریتم نیز بر خروجی به تفکیک آورده شده تا کاربر بتواند بر اساس نظر خود پارامترهای مناسب را انتخاب کند.

References   

1.     Avidan, S. and Shamir, A., "Seam carving for content-aware image resizing", in ACM Transactions on graphics (TOG), ACM. Vol. 26, No. Issue, (2007), 10.

2.     Shamir, A. and Avidan, S., "Seam carving for media retargeting", Communications of the ACM,  Vol. 52, No. 1, (2009), 77-85.

3.     Wu, L., Cao, L. and Chen, C.W., "Fast and improved seam carving with strip partition and neighboring probability constraints", in Circuits and Systems (ISCAS), 2013 IEEE International Symposium on, IEEE. Vol., No. Issue, (2013), 2812-2815.

4.     He, Z., Gao, M., Yu, H., Ye, X., Zhang, L. and Ma, G., "A new improved seam carving content aware image resizing method", in Industrial Electronics and Applications (ICIEA), 2013 8th IEEE Conference on, IEEE. Vol., No. Issue, (2013), 738-741.

5.     Kim, J.-S., Jeong, S.-G., Joo, Y. and Kim, C.-S., "Content-aware image and video resizing based on frequency domain analysis", IEEE Transactions on Consumer Electronics,  Vol. 57, No. 2, (2011).

6.     Kumar, M., Conger, D.D., Miller, R.L., Luo, J. and Radha, H., "A distortion-sensitive seam carving algorithm for content-aware image resizing", Journal of Signal Processing Systems,  Vol. 65, No. 2, (2011), 159.

7.     Ajorian, A., Samavi, S. and Mohrekesh, M., "Accelerating image resizing by multiple seam removal and path update", in Electrical Engineering (ICEE), 2013 21st Iranian Conference on, IEEE. Vol., No. Issue, (2013), 1-6.

8.     Shen, J., Wang, D. and Li, X., "Depth-aware image seam carving", IEEE transactions on cybernetics,  Vol. 43, No. 5, (2013), 1453-1461.

9.     Dahan, M.J., Chen, N., Shamir, A. and Cohen-Or, D., "Combining color and depth for enhanced image segmentation and retargeting", The Visual Computer,  Vol. 28, No. 12, (2012), 1181-1193.

10.   Dekkers, E. and Kobbelt, L., "Geometry seam carving", Computer-Aided Design,  Vol. 46, No., (2014), 120-128.

11.   Luo, S., Zhang, J., Zhang, Q. and Yuan, X., "Multi-operator image retargeting with automatic integration of direct and indirect seam carving", image and vision computing,  Vol. 30, No. 9, (2012), 655-667.

12.   Lin, S.-S., Yeh, I.-C., Lin, C.-H. and Lee, T.-Y., "Patch-based image warping for content-aware retargeting", IEEE transactions on multimedia,  Vol. 15, No. 2, (2013), 359-368.

13.   Zhang, L., Song, H., Ou, Z., Fu, Y. and Zhang, X.L., "Image retargeting with multifocus fisheye transformation", The Visual Computer,  Vol. 29, No. 5, (2013), 407-420.

14.   Lee, J. and Kim, D., "Fast seam carving using partial update and divide and conquer method", in Signal Processing and Information Technology (ISSPIT), 2009 IEEE International Symposium on, IEEE. Vol., No. Issue, (2009), 107-112.

15.   Du, H., Liu, Z., Xue, Y. and Shi, R., "Fast seam carving based on direction map",  Vol., No., (2011).

16.   Cao, L., Wu, L. and Wang, J., "Fast seam carving with strip constraints", in Proceedings of the 4th International Conference on Internet Multimedia Computing and Service, ACM. Vol., No. Issue, (2012), 148-152.

17.   Wang, D., Li, G., Jia, W. and Luo, X., "Saliency-driven scaling optimization for image retargeting", The Visual Computer,  Vol. 27, No. 9, (2011), 853-860.

18.   Chang, H.-C. and Yang, C.-K., "Fast content-aware video length reduction", Signal, Image and Video Processing,  Vol. 8, No. 7, (2014), 1383-1397.


Download PDF 



International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir