SYSTEM AND METHOD FOR CLASSIFYING IMAGES BASED ON THEIR LOCAL TEXTURAL CHARACTERISTICS

Abstract

The present invention relates to an image classification system and method, in which the system comprises electronic equipment including: a camera; and an analysis unit connected to the camera, comprising: a binarization module; a feature extraction module including a selection and interpretation submodule, one or more processing submodules, and a construction submodule; and a classification module. These components enable the identification and analysis of the texture features of objects displayed in digital images for subsequent classification. The method employs observation windows of variable dimensions that allow for modification of the image analysis time, as well as the accuracy of the classification.

Images