Abstract In recent years, there has been an increased scope for assistive software and technologies, which help the visually impaired to perceive and recognize natural scene images. In this article, we propose a novel saliency cuts approach using local adaptive thresholding to obtain four regions from a given saliency map. The saliency cuts approach is an effective tool for salient object detection. First, we produce four regions for image segmentation using a saliency map as an input image and applying an automatic threshold operation. Second, the four regions are used to initialize an iterative version of the Grab Cut algorithm and to produce a robust and high-quality binary mask with a full resolution. Lastly, based on the binary mask and extracted salient object, outer boundaries and internal edges are detected by Canny edge detection method. Extensive experiments demonstrate that the proposed method correctly detects and extracts the main contents of the image sequences for delivering visually salient information to the visually impaired people compared to the results of existing salient object segmentation algorithms.

References

[1] Achanta R., Shaji A., Smith K., Lucchi A., Fua P., and Süsstrunk S., “SLIC Superpixels Compared to State-of-the-Art Superpixel Methods,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 11, pp. 2274-2282, 2012.

[2] AlSaeed D., Bouridane A., and El-Zaart A., “A Novel Fast Otsu Digital Image Segmentation Method,” The International Arab Journal of Information Technology, vol. 13, no. 4, pp. 427- 433, 2016.

[3] Aytekin Ç., Ozan E., Kiranyaz S., and Gabbouj M., “Visual Saliency By Extended Quantum Cuts,” in Proceedings of IEEE International Conference on Image Processing, Quebec City, pp. 1692-1696, 2015.

[4] Benny D. and Soumya K., “New Local Adaptive Thresholding and Dynamic Self Organizing Feature Map Techniques for Handwritten Character Recognizer,” in Proceedings of International Conference on Power and Computing Technologies, Nagercoil, pp. 1-4, 2015.

[5] Bradley D. and Roth G., “Adaptive Thresholding Using the Integral Image,” Journal of Graphics Tools, vol. 12, no. 2, pp. 13-21, 2007.

[6] Chen J. and Takagi N., “A Pattern Recognition Method for Automating Tactile Graphics Translation from Hand Drawn Maps,” in Proceedings of IEEE International Conference on Systems, Man, and Cybernetics, Manchester, pp. 4173-4178, 2013.

[7] Cheng M., Mitra N., Huang X., Torr P., and Hu S., “Global Contrast Based Salient Region Detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, no. 3, pp. 569-582, 2015.

[8] Comaniciu D. and Meer P., “Mean Shift: A Robust Approach toward Feature Space Analysis,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 5, pp. 603-619, 2002.

[9] Felzenszwalb P. and Huttenlocher D., “Efficient Graph-Based Image Segmentation,” International Journal of Computer Vision, vol. 59, no. 2, pp. 167-181, 2004.

[10] Fu Y., Cheng J., Li Z., and Lu H., “Saliency Cuts: an Automatic Approach to Object Segmentation,” in Proceedings of 19th International Conference on Pattern Recognition, Tampa, pp. 1-4, 2018.

[11] Jungil J., Hongchan Y., Hyelim L., and Jinsoo C., “Graphic Haptic Electronic Board-Based Education Assistive Technology System for Blind People,” in Proceedings of IEEE International Conference on Consumer Electronics, Las Vegas, pp. 364-365, 2015.

[12] Lee G., Tai Y., and Kim J., “Deep Saliency with Encoded Low Level Distance Map and High Level Features,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, pp. 660-668, 2016.

[13] Li S., Ju R., Ren T., and Wu G., “Saliency Cuts Based on Adaptive Triple Thresholding,” in Proceedings of IEEE International Conference on Image Processing, Quebec City, pp. 4609- 4613, 2015.

[14] Liu N. and Han J., “Dhsnet: Deep Hierarchical Saliency Network for Salient Object Detection,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, pp. 678-686, 2016.

[15] Manipoonchelvi P. and Karuppiah M., “Saliency Detection for Content Aware Computer Vision Applications,” The International Arab Journal of Information Technology, vol. 14, no. 4, pp. 528- 533, 2017.

[16] Mehrani P. and Veksler O., “Saliency Segmentation Based on Learning and Graph Cut Refinement,” in Proceedings of British Machine Vision Conference, Aberystwyth, pp. 1-12, 2010.

[17] Mukhiddinov M., Salient Region Extraction based on Global Contrast Enhancement and Saliency Cut for Image Information Recognition 720 The International Arab Journal of Information Technology, Vol. 17, No. 5, September 2020 of the Visually Impaired, Thesis Master’s, Gachon University, 2017.

[18] Rother C., Kolmogorov V., and Blake A., “Grabcut: Interactive Foreground Extraction Using Iterated Graph Cuts,” ACM Transactions on Graphics, vol. 23, no. 8, pp. 309-314, 2004.

[19] Sauvola J. and Pietikinen M., “Adaptive Document Image Binarization,” Pattern Recognition, vol. 33, no. 2, pp. 225-236, 2000.

[20] Singh O., Sinam T., James O., and Taiyenjam R., “Local Contrast and Mean Thresholding in Image Binarization,” International Journal of Computer Applications, vol. 51, no. 6, pp. 4-10, 2012.

[21] Takagi N. and Chen J., “Character String Extraction From Scene Images By Eliminating Noncharacter Elements,” in Proceedings of IEEE International Conference on Systems, Man, and Cybernetics, San Diego, pp. 3685-3690, 2014.

[22] Zhou Q., Chen J., Ren S., Zhou Y., Chen J., and Liu W., “On Contrast Combinations for Visual Saliency Detection,” in Proceedings of IEEE International Conference Image Processing, Melbourne, Australia, pp. 2665-2669, 2013. Mukhriddin Mukhiddinov received the B.S. degree in Informatics and Information Technologies from Tashkent University of Information Technologies (TUIT), Uzbekistan in 2015 and the M.S. degree in IT Convergence Engineering from Gachon University, Korea in 2017. In 2020, he received the Ph.D. degree in Computer Engineering from TUIT, Uzbekistan. He is currently assistant professor in the Department of Hardware and Software Control Systems in Telecommunication, TUIT, Uzbekistan. His research interest includes object extraction, image processing, and pattern recognition. Rag-Gyo Jeong received the B.S., M.S., and Ph.D. degrees, all in Electrical Engineering, from Inha University, Incheon, Korea, in 1991, 1999, and 2005, respectively. He joined KRRI (Korea Railroad Research Institute), Uiwang, South Korea, as a Senior Researcher in 1995. Currently, he is a Principal Researcher and team leader of On-demand Transit Research Team in the New Transportation Systems Research Center at KRRI. From 1990 to 1994, he was a Staff Engineer at Hanjin Heavy Industries Co., Ltd. His research interests include autonomous train control system, electric-powered transportation systems, PRT (Personal Rapid Transit), system engineering. Jinsoo Cho received his B.S. in Electronic Engineering from Inha University in 1994, M.S. in Electrical Engineering from Columbia University in 1998, and Ph.D. in Electrical and Computer Engineering from the Georgia Institute of Technology in 2003. From 2004 to 2006, he was a senior research engineer in the D-TV development team of System LSI Division, Samsung Electronics Co., Ltd in Korea. He is currently an associate professor in the Department of Computer Engineering, College of IT, Gachon University, Korea. His current research interests include image/video processing, computer vision, and assistive technology for the visually impaired.