STUDY THE PROPERTIES OF REGULAR GEOMETRICAL SHAPES IN THE DIGITAL IMAGES

Abstract

The present research has conducted so as to search for the new properties for a group of regular geometrical shapes of pictures, and to classify this group into categories depending on four features including energy, contrast, correlation and homogeneity all of which can be obtained from a co-occurrence matrix. These four features have also been studied into details and then were vastly discussed and presented so as to show their effects respectively on the features characterizing the regular geometrical shapes. Besides, the algorithm applied has proved that these features can be extracted as new features for the regular geometrical shapes.However, the experimental results of the proposed algorithm have proved that both energy and homogeneity features have given high recognition properties compared with the remaining other properties.