一种增强手绘草图清晰度的高性能方法（英文）

A high-performance approach for enhancingthe clarityof hand-drawn sketch images

手绘草图作为更接近于自然的人机交互方式,是图像检索研究领域一个重要的研究方向.针对手绘草图在获取过程中所呈现的噪声、模糊及清晰度不高等问题,提出一种增强手绘草图清晰度的高性能方法,简称为HPACSI.包括手绘草图的预处理过程和提取过程.前者采用噪声检测和噪声滤除解决扫描手绘草图降质问题;后者采用基于阈值的图像分割方法提取手绘草图解决手绘草图清晰度不高问题.采用20个类别的600幅手绘扫描图像进行仿真验证,根据实际问题采用无参考图像质量评价指标对手绘草图的质量进行客观评价,并与现有的图像分割方法进行效果对比,结果表明,本文提出的HPACSI可以有效且高效地提高手绘草图的清晰度.

As a direct,convenient,natural and efficient human-machine interactive way,hand-drawn sketch is an important research direction in the field of image retrieval.A high-performance approach for improving the clarity of hand-drawn sketch images(HPACSI for short)has been proposed,to address the problems of noise,blurring and lack of clarity presented in the hand-drawn sketches.The proposed approach mainly includes two processes:the hand-drawn sketch pre-processing and the hand-drawn sketch extraction.The former adopts two processes of noise detection and noise filtering to solve the problem of hand-drawn sketch images corrupted by noise and blurring;the latter uses the threshold-based image segmentation method to extract hand-drawn sketches to solve the problem of low resolution of hand-drawn sketches.600 scanned,hand-drawn scanned images in 20 classes are processed by using the HPACSI,non-reference image quality evaluation method can be used to objective evaluate the proposed HPACSI,and the existing image segmentation methods for comparison results show that the proposed HPACSI can effectively and efficiently improve the clarity of hand-drawn sketch images.