Face image library construction method

Abstract

The invention provides a face image library construction method. According to the method, at least two different face images can be stored for the same object identified in a library, and the face image library can be used as a target face image library, a video image face image extraction library and a video image face image summary library. The above method can be extended to the construction ofimage libraries of fingerprints, irises, palm prints, gaits, human heads, human bodies, car faces, whole cars, motor vehicles, non-motor vehicles, tires, unmanned aerial vehicles, aircraft, ships, engineering machinery, tools, firearms, ammunition, cutters, bows, arrows, watches, mobile phones, texts, graphics, nameplates, trademarks, clothes, trousers, belts, shoes, hats, jewelry, bags, flowers,leaves, fruits, seeds and insects, and can also be extended to the construction of the image libraries of dog and cat faces. According to the method, the missing report rate of identification when the face image library is used as the target library can be reduced, and the effective rate of images when the face image library is used as the extraction library or the summary library can be improved.

Description

technical field [0001] The invention relates to a method for constructing a face image library, and also relates to a method for constructing a recognizable object image library. Background technique [0002]The English name of face recognition is Human Face Recognition. Face recognition in a broad sense actually includes a series of related technologies for building a face recognition system, including face image acquisition, face positioning, face recognition preprocessing, identity confirmation, and identity search, etc. A technology or system for face identification or identification. Face recognition is a popular research field of computer technology. It belongs to biometric identification technology, which is to distinguish the biological characteristics of the organism (generally refers to the person) itself. The biometric features studied by biometric identification technology include face, fingerprint, palm print, iris, retina, voice (voice), body shape, personal ...

AI Technical Summary

Problems solved by technology

The biggest shortcoming of the two-dimensional face image library construction method is that it is relatively fragile in the face of posture, different lighting conditions, expression changes, and facial makeup, etc., and the accuracy of recognition is greatly limited, and these are faces in the natural state. will show up anytime

For the face image acquisition under non-cooperative conditions, the occlusion problem is a very serious problem, especially in the monitoring environment, often the monitored objects will wear glasses, hats and other accessories, so that the collected face images may be Incomplete, which affects the subsequent feature extraction and recognition, and even leads to the failure of the face recognition algorithm

But for massive data, the training process of these methods is difficult, and may even crash

As the size of the face database grows, the performance of the face algorithm will decline