Automatic salient object segmentation using saliency map and color segmentation

Abstract

A new method for automatic salient object segmentation is presented. Salient object segmentation is an important research area in the field of object recognition, image retrieval, image editing, scene reconstruction, and 2D/3D conversion. In this work, salient object segmentation is performed using saliency map and color segmentation. Edge, color and intensity feature are extracted from mean shift segmentation (MSS) image, and saliency map is created using these features. First average saliency per segment image is calculated using the color information from MSS image and generated saliency map. Then, second average saliency per segment image is calculated by applying same procedure for the first image to the thresholding, labeling, and hole-filling applied image. Thresholding, labeling and hole-filling are applied to the mean image of the generated two images to get the final salient object segmentation. The effectiveness of proposed method is proved by showing 80%, 89% and 80% of precision, recall and F-measure values from the generated salient object segmentation image and ground truth image.

Keywords

salient object / visual attention / saliency map / color segmentation

References

[1] JungC-h, KimC-gick. A unified spectral-domain approach for saliency detection and its application to automatic object segmentation [J]. IEEE Transactions on Image Processing, 2012, 21(3): 1272-1283

[2] HanS-h, HongY-p, LeeS-hun. Applying differential techniques for 2D/3D video conversion to the objects grouped by depth information [J]. Journal of The Korea Academia-Industrial Cooperation Society, 2012, 13(3): 1302-1309

[3] LiH-l, NganN. Saliency model-based face segmentation and tracking in head-and-shoulder video sequences [J]. Journal of Visual Communication and Image Representation, 2008, 19(5): 320-333

[4] AvrahamT, LindenbaumM. Esaliency (extended saliency): Meaningful attention using stochastic image modeling [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(4): 693-708

[5] GuoC-l, ZhangL-ming. A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression [J]. IEEE Transactions on Image Processing, 2010, 19(1): 185-198

[6] IttiL, KochC, NieburE. A model of saliency-based visual attention for rapid scene analysis [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259

[7] MaY-f, ZhangH-j. Contrast-based image attention analysis by using fuzzy growing [C]. ACM International Conference on Multimedia, 2003New YorkACM374-381

[8] OuerhaniN, BurA, HügliH. Linear vs. nonlinear Feature Combination for Saliency Computation: A comparison with human Vision [J]. Lecture Notes in Computer Science, 2006, 4174: 314-323

[9] HarelJ, KochC, PeronaP. Graph-Based Visual Saliency [J]. Advances in Neural Information Processing Systems, 2007, 19: 545-552

[10] HouX-d, ZhangL-qing. Saliency detection: A spectral residual approach [C]. IEEE Conference on Computer Vision and Pattern Recognition, 2007MinneapolisIEEE Press1-8

[11] HuY-q, XieX, MaW-y, ChiaL-t, RajanD. Salient region detection using weighted feature maps based on the human visual attention model [J]. Lecture Notes in Computer Science, 2005, 3332: 993-1000

[12] AchantaR, HemamiS, EstradaF, SüsstrunkS. Frequency-tuned salient region detection [C]. IEEE Conference on Computer Vision and Pattern Recognition, 2009MiamiIEEE Press1597-1604

[13] LiangZ-j, WangM-j, ZhouX-cong. Salient object detection based on regions [J]. Multimedia Tools and Applications, 2012

[14] ChengM-m, ZhangG-x, Mitra NiloyJ, HuangX-l, HuS-min. Global contrast based salient region detection [C]. IEEE Conference on Computer Vision and Pattern Recognition, 2011409-416

[15] MarchesottiL, CifarelliC. Gabriela csurka, a framework for visual saliency detection with applications to image thumbnailing [C]. IEEE International Conference on Compter Vision, 2009KyotoIEEE Press2232-2239

[16] LiuZ, ShiR, ShenL-q, XueY-z, NganK N, ZhangZ-yang. Unsupervised salienct object segmentation based on kernel density estimation and two-phase graph cut [J]. IEEE Transactions on Multimedia, 2012, 14(4): 1275-1289

[17] LiuT, SunJ, ZhengN-n, TangX-o, ShumH-yeung. Learning to detect a salient object [C]. IEEE Conference on Computer Vision and Pattern Recognition, 2007MinneapolisIEEE Press1-8

[18] HanS-h, HongY-p, LeeS-hun. Saliency map creation method robust to the contour of objects [J]. The Korea Society of Digital Policy & Management, 2012, 10(3): 173-178

[19] AchantaR, EstradaF, WilsP, SüsstrunkS. Salient Region Detection and Segmentation [C]. Proceedings of 6th International Conference in Computer Vision System, Santorini, 2008GreeceICVS66-75