A Soybean Image Noise Smoothing Method Using Multi-scale Morphology

A soybean image noise smoothing method using multi-scale morphology is presented in this paper. The method is based on manipulating the intensity of scale-specific features present in the noisy image. Features at various scales are extracted by means of morphological filtering. The proposed scheme has been implemented by using morphological towers to smooth noise in images. The algorithm has been tested on sample images corrupted with various kinds of noise. The results have been compared with those of other standard methods. It is found that the performance of the proposed method is satisfactory and superior to other methods referred in this paper.