Human face key point-based prediction system and method in Android platform

Abstract

The invention discloses a human face key point-based prediction system and method in an Android platform. The method comprises the following steps of 1, collecting a human face sample picture set and calibrating human face key points to form a training sample set; 2, obtaining a human face key point initial shape set S<0>; 3, performing training to obtain a global binary characteristic phi 1 during first-time cascading; 4, training linear regression W<1>; 5, obtaining a predicted deformation increment delta S<0> and a human face key point shape set S<1>=S<0>+W<0>.phi 0(I,S<0>) during first-time cascading; and 6, returning the trained global binary characteristic and linear regression device, and obtaining a regression model and final human face key point shapes S<T> until a maximum layer number of cascading is T. According to the system and the method, the algorithm running efficiency can be improved; a relatively small memory is consumed in a mobile platform; and human face key points are accurately located at a high speed, so that human face key parts can be quickly beautified.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a prediction system and method based on key points of human faces under the Android platform. Background technique [0002] The detection and positioning technology of key points of the face refers to the precise positioning of the key areas of the face in the face picture, including eyebrows, eyes, nose, mouth, and facial contours. The use of key point detection technology can provide accurate information for face recognition, and can also accurately locate local areas of the face for beautification. It has been widely used in security, identification and entertainment. [0003] At present, the existing face key point positioning work mainly includes model-based methods and regression-based methods. Model-based methods include Active Shape Model (ASM), Active Appearance Model (AAM), Bay Bayesian Tangent Shape Model (BTSM), etc., regression-based methods include explicit shape reg...

AI Technical Summary

Problems solved by technology

Nowadays, due to the popularization of smart mobile devices, it has become a demand to use facial key point positioning technology to realize functions such as beauty unlocking on mobile platforms, but the existing algorithms have high computational complexity and large memory consumption. Very few on mobile platforms

In addition, there are many middle-aged and elderly people who currently use smart mobile devices, but the vast majority of them do not know how to operate more complex image processing software

Images