Fully Convolutional Neural Network Combined with K-means Clustering Algorithm for Image Segmentation

被引:3
作者
He, Bing [1 ]
Qiao, FengXiang [1 ]
Chen, Weijun [1 ]
Wen, Ying [2 ]
机构
[1] Shanghai Inspect & Maintenance Power Co, Shanghai, Peoples R China
[2] East China Normal Univ, Dept Comp Sci & Technol, Shanghai, Peoples R China
来源
TENTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2018) | 2018年 / 10806卷
关键词
Image Segmentation; Fully Convolutional Networks; Edge detection; K-mean clustering;
D O I
10.1117/12.2502814
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
Image segmentation is an important part of many computer vision tasks such as image recognition and image understanding. Traditional image segmentation algorithms are susceptible to the influence of complex backgrounds such as illumination, shading and occlusion, thus the application of convolution neural network to image segmentation becomes a hot spot of current research. But in the process of image convolution, as the convolution goes further, the image will lose some edge information, resulting in the blurring of the final partition edge. To overcome this problem, we propose an image segmentation algorithm combining the fully convolution neural network and K-means clustering algorithm. By conducting pixel matching between the coarse segmentation result obtained by using the convolution neural network and the segmentation results obtained by using K-means, the algorithm enhances the classification of pixels on the edge to improve segmentation accuracy. The proposed algorithm adopts two-stage training method to train and optimize the model. The experimental results on VOC2012 set validate the effectiveness of the proposed method.
引用
收藏
页数:7
相关论文
共 14 条
[1]  
[Anonymous], 2013, IEEE T PATTERN ANAL, DOI DOI 10.1109/TPAMI.2012.59
[2]  
[Anonymous], 2 INT C LEARN REPR
[3]  
[Anonymous], 2014, ICML
[4]  
[Anonymous], 2014, NIPS
[5]  
[Anonymous], 2014, P IEEE C COMP VIS PA
[6]  
[Anonymous], 2014, P INT C LEARN REPR
[7]  
[Anonymous], 2010, INT J COMPUT VISION, DOI DOI 10.1007/s11263-009-0275-4
[8]   Restoring An Image Taken Through a Window Covered with Dirt or Rain [J].
Eigen, David ;
Krishnan, Dilip ;
Fergus, Rob .
2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2013, :633-640
[9]  
Johnson R.A., 2001, APPL MULTIVARIATE ST, V5th
[10]   ImageNet Classification with Deep Convolutional Neural Networks [J].
Krizhevsky, Alex ;
Sutskever, Ilya ;
Hinton, Geoffrey E. .
COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90