Face feature extraction method, electronic device, and computer-readable storage medium
CN116152889BActive Publication Date: 2026-07-10MASHANG CONSUMER FINANCE CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- MASHANG CONSUMER FINANCE CO LTD
- Filing Date
- 2022-12-28
- Publication Date
- 2026-07-10
AI Technical Summary
Technical Problem
In existing technologies, facial recognition devices perform periodic facial feature extraction operations on each frame of an image, resulting in low efficiency, especially when processing images without faces, which affects the user experience.
Method used
By obtaining the previous frame of the target image as a reference image, the pixel difference at the same position and the similarity of the predetermined region are calculated. Facial feature extraction is performed only when the target image changes, reducing invalid processing.
Benefits of technology
It improves the efficiency of facial feature extraction, reduces invalid processing time, and enhances the user experience.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116152889B_ABST
Abstract
The present disclosure provides a face feature extraction method, an electronic device and a computer readable medium. The method comprises: obtaining a reference image and a target image; calculating a difference value of pixel values of two pixel points of each pixel pair in a first preset number of pixel pairs; if the number of difference values greater than or equal to a first preset threshold value in the difference values of pixel values reaches a first threshold value, obtaining a verification result by using at least one of the following verification methods: judging a difference in the number of pixels reaching a pixel threshold value in a target image block of the reference image and a target image block of the target image, and judging a similarity of each group of sub-image blocks in a plurality of sub-image blocks of the reference image and a plurality of sub-image blocks of the target image; and if the verification result indicates that the target image has changed relative to the reference image, performing face feature extraction on the target image. According to the embodiments of the present disclosure, the efficiency of face feature extraction can be improved.
Need to check novelty before this filing date? Find Prior Art