Local region matching-based face search method

Abstract

The invention discloses a local region matching-based face search method. The method includes the following steps that: 1) faces of each image in a face image set A are aligned with a face of a standard format, and areas of various organs are divided; 2) bottom-level feature vectors of each organ are extracted from and are clustered; 3) any two classifications are selected from clustering results of each organ and are adopted as positive and negative samples, and a support vector machine classifier is trained; training is performed in a paired combination manner, such that a classifier set of the organs can be obtained, and the results of discrimination of the bottom-level feature vectors which is performed by each classifier in the classifier set are united so as to form new feature vectors, namely, middle-level feature vectors of the organs; 4) the ratio of the distance of each key point on each face contour to left and right eyes to the distance between the two eyes is calculated and is adopted as the middle-level feature vector of the corresponding face contour; the above middle-level feature vectors are combined such that Vr can be obtained; and 5) a middle-level feature vector Vq is generated for a face image q to be searched; and the Vq is matched with the Vr in the A, and query results are returned. With the local region matching-based face search method of the invention adopted, a search effect of similar faces can be improved.

Description

technical field [0001] The invention relates to a face search method, in particular to a face search method based on local area matching, and belongs to the technical field of image recognition. Background technique [0002] At present, face recognition detection technology has been widely used in various fields and has become a current research hotspot. Its system" patent literature. [0003] Similar face search (face search), that is, given a face to be searched (query face), it is necessary to find results similar to it from an image database containing hundreds of thousands or more faces, and return results according to its appearance. A sequence of images sorted by similarity. With the explosive growth of Internet pictures and the increasing popularity of security monitoring equipment, a large amount of face image data is generated every day, and these face data need to be effectively organized, indexed, searched and analyzed. In this context, similar face search tec...

AI Technical Summary

Problems solved by technology

However, because different users have different definitions of face "similarity", the search results based on the similarity of the whole face are often unsatisfactory to users (for example, some users tend to search for faces with similar eyes, Other users tend to search for faces with similar facial contours)

At the same time, the similarity of the whole face is easily disturbed by local changes, especially very sensitive to partial occlusions (such as wearing sunglasses)

In this case, the similarity of the whole face is often seriously affected by these interfering regions, so that the face that should be very similar is pulled down by these "bad" local regions to reduce the overall similarity, so it cannot be detected. find return

Images