A face super-resolution processing method and system with multi-scale space constraints
A space-constrained, super-resolution technology, applied in image data processing, image analysis, image enhancement, etc., can solve the problems affecting the accuracy of local relationship description, the distance measurement criterion is no longer accurate, and the effect is unsatisfactory. Improve visual experience, good recovery effect, obvious effect
Active Publication Date: 2022-03-15
FUJIAN NORMAL UNIV
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Therefore, although in the process of reconstructing low-quality images in general environments, good results can be obtained, but in the face of severe noise images represented by surveillance, the damage of high-frequency details has led to this kind of high-frequency details as the main consideration. The distance measurement criterion is no longer accurate, which seriously affects the accuracy of the local relationship description. Therefore, the subspace information of the image itself is easily damaged, and 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
[0053] Such as figure 1 or 2, the present invention uses images of lower quality to provide mid-low frequency information, and utilizes low-quality images of this quality level to provide local relationship guidance composed of mid-low frequency information for the restoration of conventional low-quality images, and is robust to low-quality The low-frequency information in the image enhances the accurate expression and robustness of the image block. In the face super-resolution algorithm based on the traditional manifold assumption of local embedding, the present invention introduces the mid-low frequency sample constraint relationship across the scale space, expresses multiple local relationships for image blocks to be processed through the mid-low frequency sample constraint relationship, and utilizes multiple local The local relations with complementary relations are constraints, which enhance the consistency and noise robustness of image patch representations, and improve ...
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 with multi-scale space constraints. Method steps: S1: build a multi-scale training library; S2: build a multi-scale input according to the input image to be tested; S3: use the same block The low-resolution face image to be processed and the image in the training library are divided into image blocks with overlapping parts; S4: preprocessing the multi-scale training library to obtain the local relationship corresponding to each data point; S5: for each scale The input under the conditions is to find the anchor neighbors; S6: Determine the neighbor index set of the low-resolution face image block to be processed through the anchor neighbors and the pre-processed local relationship; S7: Determine the neighbor sample set; S8: According to the existing neighbor set and Multi-scale input to find the best neighbor coefficient; S9: Reconstruction of local image block results based on the existing neighbor set and the best neighbor coefficient; S10: Stitching high-resolution face image blocks. The invention can significantly improve the visual experience of restored images, and is suitable for restoring human face images in a low-quality monitoring environment.
Description
technical field [0001] The present invention relates to the technical field of image processing and image restoration, in particular to a face super-resolution processing method and system with multi-scale space 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. However, d...
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): G06T3/40G06T3/00G06T5/50
CPCG06T3/4007G06T3/4038G06T3/4076G06T5/50G06T2207/20216G06T2207/30201G06T2207/20081G06T2207/20021G06T3/02
Inventor 陈亮吴庆祥林贵敏杨正吴怡郑云
Owner FUJIAN NORMAL UNIV