期刊
IET IMAGE PROCESSING
卷 14, 期 1, 页码 183-191出版社
WILEY
DOI: 10.1049/iet-ipr.2018.6622
关键词
learning (artificial intelligence); affine transforms; image segmentation; convolutional neural nets; realistic image priors; training set; fully convolutional networks; FCN; image segmentation; deep prior method; high-level semantic patterns; high-level semantic information; intrinsic prior shape; specific image; improved level set method; corrected prior shape; segmented images; deep learning; convolutional neural network; portrait data set
类别
资金
- National Key Research and Development Program of China [2017YFC1601800]
- National Natural Science Foundation of China [61673046, 61603025]
- Science and Technology Major Project of Guizhou Province (Guizhou Branch) [[2018]3002]
- Fundamental Research Funds for the Central Universities [XK1802-4]
Deep convolutional neural network can effectively extract hidden patterns in images and learn realistic image priors from the training set. And fully convolutional networks (FCNs) have achieved state-of-the-art performance in the image segmentation. However, these methods have the disadvantages of noise, boundary roughness and no prior shape. Therefore, this study proposes a level set with the deep prior method for the image segmentation based on the priors learned by FCNs. The FCNs can learn high-level semantic patterns from the training set. Also, the output of the FCNs represents the high-level semantic information as a probability map and the global affine transformation can obtain the optimal affine transformation of the intrinsic prior shape. Moreover, the improved level set method integrates the information of the original image, the probability map and the corrected prior shape to achieve the image segmentation. Compared with the traditional level set method of simple scenes, the proposed method solves the disadvantage of FCNs by using the high-level semantic information to segment images of complex scenes. Finally, Portrait data set are used to verify the effectiveness of the proposed method. The experimental results show that the proposed method can obtain more accurate segmentation results than the traditional FCNs.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据