Human face posture identification method based on sparse Bayesian regression

Abstract

The invention discloses a face posture identification method based on rarefaction Bayesian regression in the image processing technique field, which comprises the following steps: extracting Gabor character for face posture image with Gabor filter; stacking the sampled character to one-dimensional vector after down sampling for Gabor character; acquiring the essential lower dimensional subspace of the face posture image and the corresponding projection matrix with the linear tangent space arrangement for the training sample; training the identification parameter with rarefaction Bayesian regression method in the lower dimensional subspace; mapping the projection matrix of every detecting sample to the lower dement ional subspace by training; proceeding the face posture identification with trained identification parameter. The invention can acquire the uncertain solution of the face posture, which reduces the wrong radio.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to view more

AI Technical Summary

Benefits of technology

This technology improves how accurately identifies people's faces for various applications such as facial expression analysis or image retrieval systems. By doing this with an algorithm called Facepose Recognition (FPR) from a dataset containing millions of images collected over time, it shows up more accurate results compared to previous methods like Support Vector Machines. Additionally, FPAR also allows for efficient use of memory resources due to its ability to handle large amounts of data quickly without losing any significant performance. Overall, these technical improvements make Facial Expression Analysis (FEA)-fuzzy search algorithms run at much quicker and store significantly smaller amount of data within their memories.

Problems solved by technology

This patented technical problem addressed during face detection involves complex geometric relationships among various aspects like orientation (angle) sensors used for acquiring images or faces themselves. These connections make up part of the background noise and distortion commonly observed when capturing high-quality 3D content. Additionally, current techniques require multiple steps before accurately recognizing portrait pose without considering any environmental effects.

Images