摘要
传统图像分割方法主要依赖图像光谱、纹理等底层特征,容易受到图像中遮挡和阴影等的干扰。为此,提出一种基于卷积受限玻尔兹曼机的CV(Chan-Vest)图像分割模型,采用生成式模型——卷积受限玻尔兹曼机对目标形状建模并生成目标形状,以此为先验信息对CV模型能量函数增加目标全局形状特征约束,指导图像分割。在训练数据有限、目标形态各异、目标尺度变化较大的遥感影像数据集Satellite-2000和Vaihigen的目标分割中取得了理想的结果。
Traditional image segmentation methods mainly rely on the low-level features,such as image spectrum and texture,and are easily disturbed by occlusion and shadow.To address these problems,a CV(Chan-Vest)image segmentation model combining the convolutional restricted Boltzmann machine is proposed.The target shape a priori information is modeled and generated using the convolutional restricted Boltzmann machine.Then the energy function of the CV model is constrained by the added apriori shape term to guide image segmentation.Better segmentation results are obtained in remote sensing datasets Satellite-2000and Vaihigen,whose training data are limited while target shapes and sizes are different.
作者
李晓慧
汪西莉
Li Xiaohui;Wang Xili(School of Computer Science,Shaanxi Normal University,Xi′an,Shaanxi 710119,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2020年第4期193-204,共12页
Laser & Optoelectronics Progress
基金
国家自然科学基金(41471280)。
关键词
图像处理
图像分割
形状先验
卷积受限玻尔兹曼机
深度学习
CV模型
image processing
image segmentation
shape apriori
convolutional restricted Boltzmann machine
deep learning
CV model
