Efficiency of texture image filtering and its prediction
Research output: Contribution to journal › Article › Scientific › peer-review
|Number of pages||8|
|Journal||Signal, Image and Video Processing|
|Publication status||Published - 2016|
|Publication type||A1 Journal article-refereed|
Textures are typical elements of natural scene images widely used in pattern recognition and image classification. Noise, often being present in acquired images, deteriorates texture features (characteristics), and it is desirable both to suppress it and to preserve a texture. This task is quite difficult even for the most advanced filters, and the resulting denoising efficiency can be quite low. Due to this, it is desirable to predict a denoising efficiency before filtering to decide whether it is worth filtering a given image or not. In this paper, we analyze several quantitative criteria (metrics) that can characterize filtering efficiency. Prediction strategy is described and its accuracy is studied. Several modern filtering techniques are analyzed and compared. Based on this, practical recommendations are given.