Unformatted text preview: deviated, the obtained data does not have affine invariance and needs to be normalized. So we can use the Procrustes method to normalize all the shape sets in the sample set. Finally, we can obtain the similar degree of results by minimizing the measure of the shape difference (Procrustes distance), and then classify the target object. Result Analysis The final average accuracy of the program is 73.25% and the standard accuracy is 0.1055, which are within acceptable limits. At the same time, during multiple program runs, the program runs well and the time cost is low. However, the disadvantage is that there are some problems in the extraction of the edge and the landmarks of the color pictures----there are many unreasonable extracted edges, so the classification result on the color picture is not good....
View Full Document
- Fall '17