Edge distance extraction and orientation invariant transform for object recognition

摘要

This research finds the distances between the edge and the centroid as the parameters to do the pattern recognition. The entire edge distances are recorded in a vertical strip. The “vector magnitude invariant transform” technique is used to transfer the distance quantity to an invariant vector magnitude quantity for object identification. The “vector magnitude invariant transform” technique can solve the image rotation problem. Various distance vertical magnitude quantity strips are generated to cope with the image-shifting problem. In this research, one hundred and five comparisons are conducted to find the accuracy-rate of the developed algorithm. Within those one hundred and five comparisons, fifteen comparisons are conducted for self-comparison. The other ninety comparisons are conducted for comparisons between two different object images. The algorithm developed in this research can precisely classify the object image.