Classifying and processing method based on active shape model and K nearest neighbor algorithm for facial forms of human faces

Abstract

The invention relates to a classifying and processing method based on an active shape model and a K nearest neighbor algorithm for facial forms of human faces; the method comprises the following steps of: (1) a sample database in the K nearest neighbor algorithm is established; (2) a user uploads images to be measured to a server through a network multi-media terminal, and the server extracts characteristic points of the human faces from the image to be measured by adopting an ASM (Automated Storage Management) algorithm and determines facial contours by selecting the characteristic points of the faces and lower jaws; (3) the server carries out normalization processing on point sets of the images to be measured according to a sample normalization method and integrates the point sets of the images to be measured and point sets of samples in a coordinate system; (4) the server classifies the images to be measured based on the Hausdorff distance and the K nearest neighbor algorithm to obtain a classifying result; and (5) the server automatically sends the classifying result to a network multi-medium terminal; and the network multi-medium terminal displays the classifying result. Compared with the prior art, the classifying and processing method has the advantages of high recognition rate, fast speed, easy implementation and the like.

Description

technical field [0001] The invention relates to a method for identifying face types of human face photos, in particular to a method for classifying and processing human faces based on an active shape model and a K-nearest neighbor algorithm. Background technique [0002] Face type classification has certain research value and can be applied to different fields, such as face recognition, image retrieval, beauty simulation, etc. In face recognition, when the image database increases, the speed of querying an image decreases linearly, and the face recognition rate also decreases. Therefore, in the case of a huge database, the problems of slow recognition speed and low recognition rate in face recognition urgently need to be solved. Before recognizing the face, the face images in the database can be classified according to the characteristics, and the search range can be narrowed to a small range similar to the characteristics of the image to be recognized, so that the query sp...

AI Technical Summary

Problems solved by technology

[0004] For faces with non-standard faces, the method of classification based on contour curvature lines has low classification accuracy, and in the case of poor image quality, the Sobel operator will not be very effective in extracting contours

However, the classification method based on the morphological surface index and the zygomatic-mandibular width index has a great dependence on the location of the feature points. The feature points used are fixed and the number of feature points is small. The classification method is not robust, and The face shape is only divided into two categories, and the scope of application is limited

By collecting multiple feature points, it is a good face classification method to classify feature point sets, but the method based on ISODATA clustering requires a comprehensive and large number of sample training, the algorithm is complex, and it is not easy to implement, and Gu Hua's method is only for face images. Automatic clustering, without clearly stating which category belongs to which face type

Images