Cascaded neural network-based face key point detection method

Abstract

The invention relates to a cascaded neural network-based face key point detection method. The method includes the following steps that: a) a training-used face image set is established, and a key point position requiring detection is marked; b) a first-layer depth neural network is constructed and is used to train a face region estimation model; c) a second-layer depth neural network is constructed and is used to perform face key point preliminary detection; d) local region division is continued to be performed on an inner face region; e) a third-layer depth neural network is constructed for each local region respectively; f) the rotation angle of each local region is estimated; g) correction is performed according to the estimated rotation angles; h) a fourth-layer depth neural network is constructed for the correction data set of each local region; and i) any face image is given, and the above four-layer depth neural network model is adopted to perform key point detection, such that final face key point detection results can be obtained. With the cascaded neural network-based face key point detection method of the invention adopted, face key point detection can be improved, and especially the accuracy and real-time property of dense face key point detection.

Description

technical field [0001] The invention belongs to the technical field of digital image processing and face recognition, and in particular relates to a method for detecting key points of a face based on a cascaded neural network. Background technique [0002] Face key point detection (facial landmark detection), that is, given a face picture, it is necessary to accurately locate the position of a series of key points (such as pupils, eye corners, eyebrow corners, mouth corners, lip edges, etc.). As the most important step before face alignment, face key point detection will greatly affect the overall performance of face recognition / analysis / search systems. [0003] Traditional facial key point detection algorithms can be divided into two categories: the first type treats each key point as an independent part, and each key point trains the detector independently according to its local characteristics; the second type puts all key points in the Train together, focusing on the re...

AI Technical Summary

Problems solved by technology

However, in practical applications, these two types of algorithms have their own great defects: 1) For the first type of algorithm, since each key point is detected separately, the global geometric information of the face is completely ignored, which makes it difficult for Very sensitive to subtle disturbances, not enough for Lubang

At the same time, this type of algorithm uses a lot of redundant information, like using features near the mouth and nose to detect key points of the eyes, which actually wastes a lot of computing resources

Images