Abstract：In order to achieve fast and accurate segmentation of images with complicated background and weak boundaries, the re-initialization method is often adopted in the traditional level set function. However, this method has many problems such as large computation and inaccurate segmentation. Thus, combined with the saliency detection algorithm, a new image segmentation method of variable level set based on the combination of edge information and regional local information is proposed. Firstly, the saliency region of the image is detected by the cellular automata model to obtain initial boundary curve of the image. Then, an improved distance normalized level set evolution (Distance Regularized Level Set Evolution, DRLSE) model is used to combine the local information of the image into the variational energy equation, and the evolution of the curve is guided by the improved energy equation. Compared with the DRLSE, the experimental results show that the average time of the proposed algorithm only needs 2.76% of the former with further improvements in the accuracy of image segmentation.
叶锋,李婉茹,陈家祯,郑子华. 基于显著性区域检测和水平集的图像快速分割算法[J]. 电子与信息学报, 2017, 39(11): 2661-2668.
YE Feng, LI Wanru, CHEN Jiazhen, ZHENG Zihua. Image Fast Segmentation Algorithm Based on Saliency Region Detection and Level Set. JEIT, 2017, 39(11): 2661-2668.
KASS M, WITKIN A, and TERZOPOULOS D. Snakes Active contour models[C]. IEEE International Conference on Computer Vision, London, UK, 1987: 259-268.
[2]
CHAN T F and VESE L A. Active contours without edges[J]. IEEE Transactions on Image Processing, 2001, 10(2): 266-277. doi: 10.1109/83.902291.
[3]
LI Chunming, XU Chenyang, GUI Changfeng, et al. Distance regularized level set evolution and its application to image segmentation[J]. IEEE Transactions on Image Processing, 2010, 19(12): 3243-3254. doi: 10.1109/TIP.2010.2069690.
[4]
ZHANG Kaihua, SONG Huihui, and ZHANG Lei. Active contours driven by local image fitting energy[J]. Pattern Recognition, 2010, 43(4): 1199-1206. doi: 10.1016/j.patcog. 2009.10.010.
[5]
AGARWAL Pankhuri, KUMAR Sandeep, SINGH Rahul, et al. A combination of bias-field corrected fuzzy C-means and level set approach for brain MRI image segmentation[C]. Soft Computing and Machine Intelligence (ISCMI), Hong Kong, China, 2015: 23-24. doi: 10.1109/ISCMI.2015.16.
YU Haiping, HE Fazhi, PAN Yiteng, et al. A fast distance regularized level set method for segmentation based on multi- features[J]. Acta Electronica Sinica, 2017, 45(3): 534-539. doi: 10.3969/j.issn.372-2112.2017.003.004.
[7]
ITTI L, KOCH C, and NIEBUR E. 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.
[8]
GUO Chenlei, MA Qi, and ZHANG Liming. Spatio-temporal saliency detection using phase spectrum of quaternion fourier transform[C]. IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC, USA, 2008: 1-8. doi: 10.1109/ CVPR.2008.4587715.
[9]
BORJI Ali, CHENG Mingming, JIANG Huaizu, et al. Salient object detection: A benchmark[J]. IEEE Transactions on Image Processing, 2015, 24(12): 5706-5722. doi: 10.1109/TIP. 2015.2487833.
[10]
QUO Jingfan, REN Tongwei, and BEI Jia. Salient object detection for RGB-D image via saliency evolution[C]. IEEE International Conference on Multimedia and Expo, Seattle, WA, USA, 2016: 1-6. doi: 10.1109/ICME.2016.7552907.
[11]
NAQVI S S, BROENE W N, and HOLLITT C. Salient object detection via spectral matting[J]. Pattern Recognition, 2016, 51(C): 209-224. doi: 10.1016/j.patcog.2015.09.026.
[12]
PENG Houwen, LI Bing, LIN GHaibin, et al. Salient object detection via structured matrix decomposition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(4): 818-832. doi: 10.1109/TPAMI.2016.2562626.
[13]
WANG Linzhao, WANG Lijun, LU Huchuan, et al. Saliency detection with recurrent fully convolutional Networks[C]. European Conference on Computer Vision, TIWAKI Corporation, Iwaki, Japan, 2016: 825-841. doi: 10.1007/978- 3-319-46493-0_50.
[14]
KAPOOR A, BISWAS K, and HANMANDLU M. An evolutionary learning based fuzzy theoretic approach for salient object detection[J]. Visual Computer, 2017, 33(5): 665-685. doi: 10.1007/s00371-016-1216-1.
[15]
SUN Jingang, LU Huchuan, and LIU Xiuping. Saliency region detection based on Markov absorption probabilities[J]. IEEE Transactions on Image Processing, 2015, 24(5): 1639-1649. doi: 10.1109/TIP.2015.2403241.
[16]
LEE Gayoung, TAI Yuwing, and KIM Junmo. Deep saliency with encoded low level distance map and high level features [C]. IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, USA, 2016: 660-668.
[17]
CHOPARD Bastien and DROZ Michel. Book review: Cellular automata modeling of physical systems[J]. Journal of Statistical Physics, 1999, 97(5/6): 1031-1032. doi: 10.1023/A: 1017270215844.
[18]
QIN Yao, LI Huchuan, XU Yiqun, et al. Saliency detection via sellular automata[C]. IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 2015: 110-119. doi: 10.1109/CVPR.2015.7298606.
[19]
ACHANTA Radhakrishna, SHAJI Appu, SMITH Smith, et al. SLIC superpixels compared to state-of-the-artsuperpixel methods[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2274-2282. doi: 10.1109/ TPAMI.2012.120.
ZHENG Wei, ZHANG Jing, and YANG Hu. The level set active contour model with improved boundary indicator function[J]. Laser Technology, 2016, 40(1): 126-130. doi: 10.7510/jgjs.issn. 1001-3806.2016.01.028.
