Face recognition method and equipment

Abstract

The embodiment of the invention discloses a face recognition method and equipment , and the method comprises the steps: obtaining a first face image and a second face image, enabling the first face image to be a current face image obtained by a camera, and enabling the second face image to be a stored reference face image; judging whether the mode of the first face image is the same as the mode ofthe second face image or not; if the mode of the first face image is different from the mode of the second face image, respectively mapping the first face image and the second face image to a cross-modal space to obtain a first sparse face feature of the first face image in the cross-modal space and a second sparse face feature of the second face image in the cross-modal space; and performing face recognition on the first face image according to the first sparse face feature and the second sparse face feature. According to the embodiment of the invention, the cross-modal face recognition speed can be improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a face recognition method and device. Background technique [0002] Due to the non-contact nature of face recognition, a biometric-based recognition technology, it has broad development and application prospects in the vehicle field. Vehicle face recognition refers to the technology of using the internal camera of the vehicle for identity confirmation or identity search. The traditional face recognition technology acquires face images in the visible light mode. Since there are often poorly illuminated scenes such as garages and nights in vehicle scenes, face images in visible light mode are used in vehicle scenes to identify people. The recognition rate of identity recognition is low, so in most cases in the car scene, a near-infrared camera that is not affected by ambient light is used. [0003] The near-infrared camera emits infrared light invisible to the naked e...

AI Technical Summary

Problems solved by technology

However, in practical applications, since the deep learning of convolutional neural networks requires a large amount of training data, it is difficult to select triplets of difficult samples, so it is prone to over-fitting of the network and reduces the recognition rate of identity recognition.

At the same time, the calculation of the convolutional neural network requires the acceleration of a graphics processing unit (GPU). On a device without a GPU, the calculation speed of the algorithm based on the neural network is slow and cannot meet the real-time requirements.

Images