Local restriction iteration neighborhood embedding-based face hallucination method

A technology of neighborhood embedding and local constraints, applied in image enhancement, instrumentation, computing, etc., can solve the problem of only considering the manifold of low-resolution image blocks, ignoring the geometric structure information of high-resolution image blocks, lack of reliability of reconstruction results and discriminative issues

Active Publication Date: 2013-07-17
WUHAN UNIV
View PDF2 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

All the methods mentioned above only consider the manifold of low-resolution image blocks, while ignoring the geometric str

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Local restriction iteration neighborhood embedding-based face hallucination method
  • Local restriction iteration neighborhood embedding-based face hallucination method
  • Local restriction iteration neighborhood embedding-based face hallucination method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The technical solution of the present invention can use software technology to realize automatic process operation. The technical solutions of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. see figure 1 , the specific steps of the embodiment of the present invention are as follows:

[0032] Step 1: Initialize the input low-resolution face image, that is, Bicubic up-sampling to obtain the estimated high-resolution face image, and the input low-resolution face image, estimated high-resolution face image, low-resolution face image All low-resolution face sample images in the training set and all high-resolution face sample images in the high-resolution training set are divided into overlapping image patches in the same way;

[0033] The low-resolution training set and the high-resolution training set provide preset training sample pairs. The low-resolution training set contains low-resolution f...

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

No PUM Login to view more

Abstract

The invention relates to a local restriction iteration neighborhood embedding-based face hallucination method. The method comprises the following steps of: establishing high-resolution and low-resolution image block sets to be used as high-resolution and low-resolution image block dictionaries; sampling on inputted image blocks of a low-resolution face image to obtain estimation high-resolution image blocks, seeking K nearest image blocks at the corresponding position in the high-resolution image block dictionary, and expressing the inputted low-resolution image blocks by using the corresponding K low-resolution image blocks to acquire a weight coefficient; reconstructing K neighbor high-resolution image blocks by utilizing the weight coefficient to form new estimation high-resolution image blocks, and performing the operation repeatedly until the most satisfied estimation high-resolution image blocks are obtained; and integrating into a high-resolution image according to the positional relations of the low-resolution image blocks. According to the method, two manifold structures are considered simultaneously on the basis of position apriority and local manifold restriction, and K neighbor points and reconstruction weights are updated continuously in an iteration form on the basis of a result of last reconstruction to achieve a high-quality reconstruction effect which is close to the real condition.

Description

technical field [0001] The invention relates to the field of image super-resolution, in particular to a face illusion method based on local constraint iterative neighborhood embedding. Background technique [0002] In the past 20 years, face recognition technology has developed rapidly. At the same time, due to the limited network bandwidth and server storage limitations of the video surveillance system, the resolution of the captured facial images is low, so that the facial information that can be provided is very limited, which has become one of the most challenging problems in biometrics. Recently, super-resolution techniques have been used to process low-resolution (LR) images, which can generate a sequence of low-resolution images or a single frame of low-resolution images that can provide more faces for the subsequent recognition process. High-Resolution (HR) images of details. [0003] In 2000, Baker and Kanade proposed a kind of face hallucination in literature 1 (...

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
no application Login to view more
IPC IPC(8): G06T5/50
Inventor 胡瑞敏江俊君董小慧韩镇陈军
Owner WUHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap