摘要
由于猪肉中存在水分,在光照下拍摄得到的图像会产生反光区域,导致图像部分信息丢失。为了更加精准提取图像相关特征参数,需复原反光区域原有信息。利用图像预处理方法、图像修复技术对图像复原。根据反光区域的颜色特征,用一系列图像预处理方法对反光区域进行定位和提取;对比经典图像修复技术在图像反光区域的复原效果,选择样本块图像修复算法作为最佳修补方法;对样本块修复算法进行了改进,采取反光区域依次修复的方法以减少边缘轮廓优先权计算次数,同时采用二次匹配法减少搜索最佳匹配块过程中的扫描数据量,和原算法相比节约了3/4的修复时间。实验结果表明,改进的修复算法能很好地复原图像反光区域信息,并在修复效率上优于原算法。
Because of moisture in pork,there would be reflective area in the image took under illumination,which leads to the loss of image information.In order to improve the accuracy of obtaining related feature parameters of the image,it is necessary to restore the reflective area.Image pre-processing and image inpainting technologies were used to restore the image.According to the color feature of the reflection area,a series of pre-processing methods were used to position and obtain the reflection area.Image restoration results in reflection area by classical image inpainting methods were compared,and the inpainting algorithm based on exemplar patch was taken as the best inpainting method.The inpainting algorithm based on exemplar patch was improved,the method of restoring the reflection area in sequence was used to reduce the calculation times of edge contour priority,in the same time,by using twice matching method,the amount of scanning data was reduced in the process of searching the best matched block,and the repair time was saved about 3 /4 of original algorithm.The experimental results show that the improved inpainting method is able to restore the information from reflection area in the image,and use less time compared with the original algorithm.
出处
《计算机应用》
CSCD
北大核心
2016年第A01期161-164,共4页
journal of Computer Applications
基金
国家科技支撑项目(2014BAD04B05
2012BAD28B02
2013BAD19B09)
国家生猪产业体系北京市创新团队资助项目
关键词
图像修复
样本块修复
眼肌图像
image inpainting
exemplar-based inpainting
rib-eye image
