摘要
该文提出一种基于小波变换的血液细胞计数方法。首先对原始图像做RGB空间到HIS空间的变换,提取饱和度图像,然后对饱和度图像的直方图曲线做基于小波变换的多分辨率分析,逐层迭代以确定最佳阈值。最后,对阈值处理图像进行形态学处理和连通区域检测,统计出图像中细胞的个数。仿真实验表明该方法取得了较好效果。
A method for counting blood cell base on wavelet transform is proposed.First,the original image is changed from RGB color space to HIS color space and the saturation image is isolated.Second,the histogram of saturation is analyzed through multi-resolution base on wavelet transformation and the optimum threshold is tracked until the highest resolution.Fi-nally,the mathematical morphology and the connected region detection are processing for counting the number of cells in the image.Simulation results showed that the method achieved better results.
出处
《衡阳师范学院学报》
2015年第3期162-165,共4页
Journal of Hengyang Normal University
基金
湖南省大学生研究性学习和创新项目(CX1202)
湖南省自然科学基金资助项目(12JJ4058)
关键词
血液细胞图像
小波变换
数学形态学
blood cell image
wavelet transformation
mathematical morphology
