Abstract：Aiming at the difficult problem of unsupervised or automatic foreground extraction, an automatic foreground extraction method based on genetic mechanism and difference of Gaussian, named GFO, was proposed. Firstly, Gaussian variation was used to extract the relative important regions in the image, which were defined as candidate seed foregrounds. Secondly, based on the edge information of the original image and the candidate seed foregrounds, the contour of foreground object contour was generated according to connectivity and convex sphere principle, called star convex contour. Thirdly, the adaptive function was constructed, the seed foreground was selected, and the genetic mechanism of selection, crossover and mutation was used to obtain the accurate and valid final foreground. The experimental results on the Achanta database and multiple videos show that the performance of the GFO method is superior to the existing automatic foreground extraction based on difference of Gaussian (FMDOG) method, and have achieved a good extraction effect in recognition accuracy, recall rate and Fβ index.
[1] ZHANG J, FENG S W, LI D, et al. Image retrieval using the extended salient region[J]. Information Sciences, 2017, 399(C):154-182. [2] 王丹丹,徐越,宋怀波,等.融合K-means与Ncut算法的无遮挡双重叠苹果目标分割与重建[J]. 农业工程学报,2015,31(10):227-234.(WANG D D, XU Y, SONG H B, et al. Fusion of K-means and Ncut algorithm to realize segmentation and reconstruction of two overlapped apples without blocking by branches and leaves[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(10):227-234.) [3] 王海英,郭志芬.一种复杂图像目标的分割与识别[J]. 北京理工大学学报,2000,20(2):224-228. (WANG H Y, GUO Z F. An approach to complex target segmentation and recognition[J]. Journal of Beijing Institute of Technology, 2000, 20(2):224-228.) [4] 张惊雷,张云飞.基于改进分水岭算法的运动目标行为理解[J]. 计算机工程与设计,2015,36(7):1840-1844. (ZHANG J L, ZHANG Y F. Behavior understanding of moving objects based on improved watershed algorithm[J]. Computer Engineering and Design, 2015, 36(7):1880-1844.) [5] PRICE B L, MORSE B S, COHEN S. Simultaneous foreground, background, and alpha estimation for image matting[C]//Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2010:2157-2164. [6] CHEN Y T, SHENG J W. Learning-based hierarchical graph for unsupervised matting and foreground estimation[J]. IEEE Transactions on Image Processing, 2014, 23(12):4941-4953. [7] HASSAN M A, MALIK A S, NICOLAS W, et al. Foreground extraction for real-time crowd analytics in surveillance system[C]//Proceedings of the 18th International Symposium on Consumer Electronics. Piscataway, NJ:IEEE, 2014:1-2. [8] WANG M, SHEN L, YUAN Y. Automatic foreground extraction of clothing images based on GrabCut in massive images[C]//Proceedings of the 2012 Information Science and Technology. Piscataway, NJ:IEEE, 2012:238-242. [9] LEI B, XU L Q. Real-time outdoor video surveillance with robust foreground extraction and object tracking via multi-state transition management[J]. Pattern Recognition Letters, 2006, 27(15):1816-1825. [10] ROSENFELD A, WEINSHALL D. Extracting foreground masks towards object recognition[C]//Proceedings of the 2011 International Conference on Computer Vision. Piscataway, NJ:IEEE, 2011:1371-1378. [11] LEVIN A, LISCHINSKI D, WEISS Y A. Closed-form solution to natural image matting[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(2):228-242. [12] SHEKHAR R, CHAUDHURI S. Content-based image retrieval in presence of foreground disturbances[J]. IEE Proceedings-Vision, Image and Signal Processing, 2006, 153(5):625-638. [13] ZOU W, KPALMA K, RONSIN J. Automatic foreground extraction via joint CRF and online learning[J]. Electronics Letters, 2013, 49(18):1140-1142. [14] YUAN Y B, LIU Y, DAI G H, et al. Automatic foreground extraction based on difference of Gaussian[J]. The Scientific World Journal, 2014, 2014:29074. [15] ACHANTA R, HEMAMI S, ESTRADA F, et al. Frequency-tuned salient region detection[C]//Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2009:1597-1604. [16] FUKUCHI K, MIYAZATO K, KIMURA A, et al. Saliency-based video segmentation with graph cuts and sequentially updated priors[C]//Proceedings of the 2009 International Conference on Multimedia and Expo. Piscataway, NJ:IEEE, 2009:638-641.
2017, Vol. 37 
