Location Extraction and Discrimination of Similar Texture Using Gabor Filter for Donut Recognition

This paper describes a machine vision system for recognition of bakery donut produce using Gabor filter that is capable of first locating and then analyzing regions of subtle texture differences. In the case when there is similar texture pattern, color analysis can then be used. Compared to conventional methods and applications, what newly presented are: Automatic location of small distinctive areas that characterizes the donut produce Identification of texture feature based on the spatial and orientation relationshp between coarse-to-fine frequency components of the image.