白丝美女被狂躁免费视频网站,500av导航大全精品,yw.193.cnc爆乳尤物未满,97se亚洲综合色区,аⅴ天堂中文在线网官网

Living body recognition method, storage medium, and computer device

專利號
US11176393B2
公開日期
2021-11-16
申請人
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED（CN Shenzhen）
發(fā)明人
Shuang Wu; Shouhong Ding; Yicong Liang; Yao Liu; Jilin Li
IPC分類
G06K9/62; G06K9/00; G06T7/194
技術(shù)領(lǐng)域
facial,image,liveness,confidence,model,training,live,target,feature,face
地域： Shenzhen

摘要

A face liveness recognition method includes: obtaining a target image containing a facial image; extracting facial feature data of the facial image in the target image; performing face liveness recognition according to the facial feature data to obtain a first confidence level using a first recognition model, the first confidence level denoting a first probability of recognizing a live face; extracting background feature data from an extended facial image, the extended facial image being obtained by extending a region that covers the facial image; performing face liveness recognition according to the background feature data to obtain a second confidence level using a second recognition model, the second confidence level denoting a second probability of recognizing a live face; and according to the first confidence level and the second confidence level, obtaining a recognition result indicating that the target image is a live facial image.

說明書

The facial region is a position of a face in the target image. Specifically, the server may recognize a facial region in the target image through a facial detection algorithm. The facial detection algorithm may be customized as required, and may be, for example, an OpenCV facial detection algorithm, a built-in facial detection algorithm in an IOS or Android system, or a Youtu facial detection algorithm. The facial detection algorithm may return a result indicating whether the target image includes a face, and a specific facial region, for example, identify the position of a face with a rectangular box. After determining the facial region in the target image, the server may intercept the target image along the facial region to obtain a facial image. In this embodiment, the facial image may include only an image of a facial region of a human face.

FIG. 4 shows a schematic diagram of multi-scale region division according to an embodiment. Refer to the left section of FIG. 4, which shows a target image acquired by a camera of a terminal. A region 411 is a facial region, and an image intercepted along the region 411 is a facial image. Refer to the right section of FIG. 4, which is a target image acquired by a facial acquisition camera in an access control system. A region 421 is a facial region, and an image intercepted along the region 421 is a facial image.

權(quán)利要求

1
微信群二維碼
意見反饋