基于卷积神经网络的图像分割算法研究  

Research on image segmentation algorithm based on convolution neural network

作　　者：查志华[1] 邓红涛[1] 田敏[1] Zha Zhihua;Deng Hongtao;Tian Min(College of Information Science and Technology,Shihezi University,Shihezi 832003,China)

机构地区：[1]石河子大学信息科学与技术学院

出　　处：《无线互联科技》2019年第13期23-24,共2页Wireless Internet Technology

摘　　要：随着科技的快速发展,在人们的日常生活中,图像信息所占的比重越来越大,带动了图像处理领域的发展,其中,图像分割属于理解图像内容的一个重要条件,因而在该领域备受关注和重视。未来,与某些领域相结合的图像分割技术,尤其是基于卷积神经网络的图像分割算法,将会为图像分割开辟全新的方向。文章介绍了图像分割算法的现状,并提出基于卷积神经网络图像分割算法的改进策略,以改进卷积神经网络的准确性,优化卷积网络图像分割算法。With the rapid development of science and technology, the proportion of image information in people's daily life is increasing, which leads to the development of image processing. Image segmentation is an important condition for understanding image content, so it has attracted much attention and attention in this field. In the future, the image segmentation technology combined with the end of some fields, especially the image segmentation algorithm based on convolution neural network, opens up a new direction for image segmentation. This paper introduces the present situation of image segmentation algorithm, and puts forward an improved strategy based on convolution neural network image segmentation algorithm in order to improve the accuracy and optimization of convolution neural network.

关 键 词：卷积神经网络 图像分割 分割算法 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]