彩色图像素描生成算法优化及研究

Optimization and research of color sketch generation of image algorithm

针对空域和频域图像素描生成算法存在素描效果不突出和耗费时间长的缺点,将离散小波变换引入彩色图像素描生成算法,提出一种具有时域和频域特性的彩色图像素描生成算法.首先,灰度化处理彩色图像,通过离散小波正变换提取图像的低频系数和高频系数,保留高频系数通过离散小波逆变换提取图像边缘信息图像;其次,在倒置求反边缘图像的基础上,锐化和平滑处理边缘图像获取彩色图像的素描效果.为了验证图像素描生成算法的优劣,选择度量F评价图像素描生成算法的效果.研究结果表明,与空域和频域算法相比,改进的算法的素描轮廓效果和图像边缘更加清晰和连续.

In order to overcome the shortcomings of spatial and frequency domain sketch generation of image algorithms,the paper introduce the Discrete wavelet transform intp the color sketch generation of image algorithm.This paper presents an algorithm for color sketch generation of image based on time domain and frequency domain.Firstly,the color image is processed by grayscale,and the low-frequency coefficients and high-frequency coefficients are extracted by the discrete wavelet forward transform,while the high-frequency coefficients are retained and the image edge information is extracted by the inverse discrete wavelet transform On the basis of inverting the edge image,sharpening and smoothing the edge image to obtain the sketch effect of color image.In order to verify the quality of the sketch generation of image algorithm,we choose the metric F to evaluate the effect of the sketch generation of image algorithm.The research results show that the improved algorithm is more clear and continuous than the spatial domain and frequency domain algorithms.