Hangzhou Hikvision Digital Technology Co., Ltd.

Chuan Shen

Weichang Kang

Xianlin Zhao

Congyi Hua

Shengguo Wang

Zhihao Ren

Fan Wei

Shaojie Ding

Method, an electronic device and a storage medium for living body detection based on face recognition are disclosed. The method comprises: obtaining to-be-detected infrared image and visible light image; performing edge detection and texture feature extraction on the infrared image, and feature extraction on the visible light image through a convolutional neural network; and determining whether the infrared and visible light images pass living body detection based on results of the edge detection and texture feature extraction on the to-be-detected infrared image, and a result of feature extraction on the to-be-detected visible light image through the convolutional neural network. The method, an electronic device and a storage medium for living body detection based on face recognition combine the advantages of three technologies of edge detection, texture feature extraction and convolution neural network, effectively perform living body detection, and improve the determination accuracy.

Living body detection method based on facial recognition, and electronic device and storage medium

Embodiments of the present application provide an image storage method and apparatus, and an electronic device and a storage medium. In the method, pixel data obtained by scanning with a first partial region of a scanning region is acquired as first pixel data, and the first pixel data is stored in a storage space; the first pixel data is corrected by using a preset correction algorithm to obtain second pixel data, and the second pixel data is stored in the storage space; if it is determined that the remaining space of the storage space meets the preset condition, the pixel data obtained by scanning with the remaining region of the scanning region is acquired as the third pixel data, and the third pixel data is stored in the storage space; wherein, the scanning mode of the remaining region is a preset second scanning mode; and the third pixel data is corrected by using the preset correction algorithm to obtain fourth pixel data, and the fourth pixel data is stored in the storage space. In the present application, due to the number of pixels obtained by scanning in the preset second scanning mode is less than the number of pixels obtained by scanning in the preset first scanning mode, the size of the image before correction is reduced, and thereby the success rate of image storage is improved.

Image storage method and apparatus, and electronic device and storage medium

A method, an apparatus and an electronic device for face liveness detection based on a neural network model are provided. The method includes: a target visible light image and a target infrared image of a target object to be detected are obtained (S); a first face image is extracted from the target visible light image, and a second face image is extracted from the target infrared image (S); a target image array of the target object is generated based on multiple monochromatic components of the first face image and a monochromatic component of the second face image (S); and feeding the target image array into a pre-trained neural network model for detection, to obtain a face liveness detection result of the target object (S).

Face liveness detection based on neural network model

Provided are a method and apparatus for preventing an illegal attack, and an electronic device. According to one embodiment, the method comprises: when a user feature of a user is identified successfully, determining whether a living body detection result for the user feature indicates failure; if the living body detection result for the user feature indicates failure, locking a feature ID when the feature ID of the user feature is not locked and a locking condition of the feature ID is satisfied currently; and if the living body detection result for the user feature indicates success, unlocking the feature ID when the feature ID of the user feature is locked and an unlocking condition of the locked feature ID is satisfied currently.

Growing community of inventors

Hangzhou, China

Chuan Shen