Method for updating gender classifier in image analysis and the gender classifier

Abstract

The invention discloses a method for updating a gender sorter in image analysis and comprises the following steps of: extracting the characters of a face image to be checked and obtaining the characteristic vector of the face image to be checked; identifying the gender corresponding to the characteristic vector through the gender sorter and determining that the gender identification result is satisfied with the characteristic vector required by the preset confidence coefficient; adding the characteristic vector with the gender identification result satisfying the preset confidence coefficient into a training sample set of the gender sorter, thus obtaining the updated training sample set; and obtaining an updated gender sorter by using the updated training sample set for training the gender sorter. The method for updating the gender sorter in image analysis raises the self-training capability of the gender sorter and raises the correctness and suitability of gender identification. The invention also discloses a gender sorter.

Description

technical field [0001] The invention relates to image analysis technology, in particular to a method for updating a gender classifier in image analysis and the gender classifier. Background technique [0002] Gender recognition based on face images has broad application prospects in computer vision, human-computer interaction, video surveillance, and video retrieval. Gender recognition is a kind of binary classification recognition. Commonly used classification methods can be used for gender recognition, that is, gender classifiers with different classification strategies can be used for gender recognition. [0003] In the gender classifier, a correspondence relationship between various face feature vectors and genders is established, and the input is the face feature vector, and the gender corresponding to the face feature vector can be output according to the established correspondence. It can also be considered that the gender classifier has the functions of face detecti...

AI Technical Summary

Problems solved by technology

However, the previous training usually uses the existing training samples, and the obtained classifier has better classification results for the samples in the training set. Since the samples participating in the training usually only occupy a small part of the sample space, with the possible occurrence of The samples to be identified are becoming more and more complex, and the pre-trained classifiers often have problems such as a decrease in the recognition rate in practical applications, and satisfactory gender identification results cannot be obtained

Images