Visual saliency endeavors to decide the measure of consideration guided towards different locales in a picture in the human pictorial and intellectual systems. It is thusly a focal issue in knowledge explore, neural science, and PC vision. PC vision examiners spin around influencing computational models for either recreating the human visual idea to process or suspecting visual saliency happens as expected. Visual saliency has been consolidated in a gathering of PC vision and picture getting ready endeavors to improve their execution.In this paper aims to correctly popping up the complete salient object(s). Salient object detection aims to correctly highlight the most salient object(s) in an image. Then we formulate saliency map computation as an regression problem,utilizes the supervised learning approach to map the regional feature vectors to detect the saliency scores. The regional feature vector includes contrast and background details. Random forest regressors with multilevel segmentation algorithms can be used to detect the salient object regions with improved accuracy rate. Experimental results provide improved clustered accuracy for real time datasets and are fit for accomplishing cutting edge execution on all open benchmark datasets.

Salient object detection, Saliency map construction, Regional Feature vectors, Benchmark datasets

[1] D. Walther and C. Koch, “Modeling attention to salient proto-objects,” Neural Networks, vol. 19, no. 9, pp. 1395–1407, 2006.
[2] L. Itti, “Automatic foveation for video compression using a neurobiological model of visual attention,” IEEE TIP, 2004.
[3] L. Marchesotti, C. Cifarelli, and G. Csurka, “A framework for visual saliency detection with applications to image thumbnailing,” in ICCV, 2009, pp. 2232–2239.
[4] S. Goferman, A. Tal, and L. Zelnik-Manor, “Puzzle-like collage,” Comput. Graph. Forum, vol. 29, no. 2, pp. 459–468, 2010.
[5] J. Wang, L. Quan, J. Sun, X. Tang, and H.-Y. Shum, “Picture collage,” in CVPR (1), 2006, pp. 347–354.
[6] Dr.S.Thilagamani, V.Manochitra ,”An Intelligent Region-Based Method for Detecting Objects from Natural Images”, International Journal of Pure and Applied Mathematics , issue Feb. 2018 , pp 473-478.
[7] Dr.S.Thilagamani, N.Shanthi ,”A Survey on image segmentation through clustering ” , International Journal of Research and Reviews in Information Sciences, issue 2011, vol. 1, pp . 14-17.
[8] Dr.S.Thilagamani, N.Shanthi ,”A novel recursive clustering algorithm for image oversegmentation” , in European Journal of Scientific Research , issue 2011, vol. 52, pp. 430-436.
[9] Dr.S.Thilagamani , N.Shanthi ” Literature Survey on enhancing cluster quality” , in International Journal on Computer Science and Engineering , vol. 2, pp. 2010 , 1999.
[10] Dr.S.Thilagamani , N.Shanthi ” Object Recognition based on image segmentation and clustering” , in 2011.
[11] Dr.S.Thilagamani , N.Shanthi ”Gaussian and gabor filter approach for object segmentation” , in Journal on Computing and Information Science in Engineering , issue 2014 , vol. 14, pp. 021006.
[12] Dr.S.Thilagamani , N.Shanthi ” Innovative methodology for segmenting the object from a static frame” , in International Journal of Engineering on Innovative Technology , vol. 2, pp. 52-56, 2013.
[13] Dr.S.Thilagamani, S.Ramesh ponnusamy ,”A Comparative study on Diverse fuzzy logic Techniques in segmenting the color images ” , i-manager’s journal on Image processing, vol. 2, pp. 6-13, 2015.
[14] Dr.S.Thilagamani, N.Kavya”A review: Analysis of the of algorithm and techniques in image segmentation” International Journal, vol. 9 , 2018.