基于K-means算法的动画单帧图像颜色PS校正方法

Color PS Correction Method of Animation Single Frame Image Based on K-means Algorithm

针对动画单帧图像颜色偏差影响整个动画序列质量的问题,提出一种基于K-means算法的动画单帧图像颜色PS校正方法.对动画单帧图像颜色PS校正做出分析描述后,在K-means算法的基础上,将图像划分为不同的区域,分析每个区域内的亮度直方图,实现对图像色彩亮度的补偿;根据色彩RGB位数拓展图像,并比较拓展前后两幅图像的色彩,以此得到校准算子;根据校准算子,完成对动画单帧图像的颜色校正.实验结果表明,所提方法可在保证校正效率的同时,取得最低的校准色差和亮度偏差.

The color deviation of animation single frame image affects the quality of the whole animation sequence.Therefore,a color PS correction method of animation single frame image based on K-means algorithm is proposed.After analyzing and describing the color PS correction of the animation single frame image,the image is divided into different regions based on the K-means algorithm,and the brightness histogram in each region is analyzed to realize the compensation of the image color brightness.The image is expanded according to the color RGB digit,and the color of the two images before and after the expansion is compared to get the calibration operator.According to the calibration operator,the color correction of single frame animation image is completed.The experimental results show that the proposed method can obtain the lowest calibration color difference and brightness deviation while ensuring the calibration efficiency.