摘要
已有的稀疏编码模型采用误差的平方和作为信息保持的客观评价标准,但最近的研究表明,人眼视觉系统的主要功能是从视觉区域提取图像和视频中的结构化信息.引入结构相似度来衡量信息保持的程度,通过对改进的目标函数进行优化,获得与初级视皮层中具有局部性、朝向性和带通性的感受野相类似的基函数集.实验结果表明,改进后的稀疏编码模型更符合人眼视觉系统特性.
Current existing sparse coding models employ the mean square of the error between the actual image and the reconstructed image to measure how well the code describes the image. Under the assumption that human visual perception is highly adapted for extracting structural information from a scene or a video, an alternative measure for information preservation assessment, based on the structural similarity, is introduced. After minimizing the cost function, the improved model attains a complete family of localized, oriented, and bandpass receptive fields, similar to those found in the primary visual cortex. The experimental results show that the improved sparse coding model is more consistent in human visual system.
出处
《软件学报》
EI
CSCD
北大核心
2010年第10期2410-2419,共10页
Journal of Software
基金
国家自然科学基金No.60805041
国家重点基础研究发展计划(973)No.2007CB311004
国家高技术研究发展计划(863)No.2007AA01Z132
国家科技支撑计划No.2006BAC08B06~~
关键词
稀疏编码
自然图像
结构相似度
生物视觉系统
计算模型
sparse coding
natural image
structural similarity
biological visual system
computational model