A face super-resolution processing method and system based on double-manifold constraints
A technology of super-resolution and processing methods, which is applied in the directions of instruments, calculations, character and pattern recognition, etc., and can solve problems such as unsatisfactory effects, pixel destruction and aliasing, and easy damage to image subspace information.
Inactive Publication Date: 2019-01-04
WUHAN UNIV
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, when the image quality is very low, the pixels will be severely damaged and aliased, and the subspace information of the image itself will be easily damaged. The image restored by traditional methods is not satisfactory.
Method used
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
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0058] In order to facilitate those of ordinary skill in the art to understand and implement the present invention, the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the implementation examples described here are only used to illustrate and explain the present invention, and are not intended to limit this invention.
[0059] The present invention uses the manifold space of the image block in the library as the second-layer manifold, uses the manifold space of the image block to be processed as the first manifold, and provides the consistency of multiple expressions of the image block to be processed through the spatial association of the manifold space To enhance the accurate representation and robustness of image patches with consistency constraints. The present invention introduces a double-layer manifold assumption into the face super-resolution algorithm based on the t...
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 PUM
Login to View More Abstract
The invention discloses a face super-resolution processing method and system based on double-manifold constraints. By constructing a training library, the low-resolution face image to be processed and the image in the training library are divided into images with overlapping parts. block; for each image block of the low-resolution face image to be processed, find its first-layer neighbors in the low-resolution training block set at the corresponding position; find the second-layer neighbors of the image block to be processed; calculate the first-layer neighbors of the image block to be processed and the weight coefficient in the low-resolution library between the image block to be processed and the first-layer neighbor; the weight coefficient in the low-resolution library between the image block to be processed and the first-layer neighbor; The weight coefficients between; the weights are projected onto the high-resolution space to obtain the high-resolution image blocks of the low-resolution image to be processed; finally, the high-resolution face image blocks are stitched together. The invention can significantly improve the visual experience of restored images, and is especially suitable for restoring human face images in low-quality monitoring environments.
Description
technical field [0001] The invention belongs to the technical field of image processing and image restoration, and in particular relates to a face super-resolution processing method and system based on double-manifold constraints. Background technique [0002] Face super-resolution technology is to learn the corresponding relationship between high and low resolution through the auxiliary training library, and then achieve the purpose of estimating high-resolution face images from existing low-resolution face images. Face super-resolution is now widely used in many fields, one of the most representative fields is face image enhancement in surveillance video. With the widespread popularization of surveillance systems, surveillance video is playing an increasingly important role in the process of criminal evidence collection and criminal investigation. Face images, as one of the direct evidence, occupy an important position in case analysis and court evidence collection. Howe...
Claims
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 Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62
CPCG06F18/214
Inventor 胡瑞敏陈亮周楚韩镇陈军渠慎明李青杨庆雄卢正马芸魏雪丽丁新
Owner WUHAN UNIV