Super-resolution method based on artificial neural network

An artificial neural network, super-resolution technology, applied in the field of statistical pattern recognition and image processing, can solve problems such as time-consuming and low efficiency

Inactive Publication Date: 2010-02-03
FUDAN UNIV
View PDF0 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The obvious disadvantage of the super-resolution algorithm using local linear embedding is that it takes a lot of time. For each image block of the test sample, it must first find its k-nearest neighbors in the training set. When the training set is relatively large, the efficiency is very high. low

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
  • Super-resolution method based on artificial neural network
  • Super-resolution method based on artificial neural network
  • Super-resolution method based on artificial neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The present invention is further described below with the application on the ORL face database as an example. The ORL database contains face images of 40 people, 10 for each person, the same as 400. The size of each image is 92×112 pixels. We select 200 of them as the training set, that is, 5 images for each person. The remaining 200 images are used as the test set. Contains two sets of experiments, corresponding to two cases where overlapping pixels are 0 and 1. In the experiment, the low-resolution image is divided into 3×3 image blocks, and the high-resolution image is divided into 6×6 image blocks. The number of neurons in the input layer of the BP neural network is 9, and the number of neurons in the output layer is The number is 36, and the number of neurons in the middle hidden layer is 25. The high and low resolution images in the training set were broken up into 54000 image blocks of 6×6 pixels and 3×3 pixels respectively, and these image blocks were drawn in...

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 belongs to the technical fields of statistical pattern recognition and image processing, in particular to a super-resolution method based on an artificial neural network. In the invention, the artificial neural network is used for expressing the function mapping relation among low-resolution images and high-resolution images. The method of the invention comprises the following concrete steps: creating a training set; establishing a BP neural network for training; bonding high-resolution images which are obtained by training according to the corresponding relation; and then, obtaining super-resolution images. The invention overcomes the disadvantage of time consumption of the original super-resolution algorithm based on manifold learning, and obtains better effect.

Description

technical field [0001] The invention belongs to the technical field of statistical pattern recognition and image processing, and in particular relates to a super-resolution method based on an artificial neural network. Background technique [0002] Super-resolution is one of the important research tasks in the field of image processing. It refers to using one or more low-resolution images to obtain a clear high-resolution image through corresponding algorithms. High resolution means that the image has a high pixel density, which can provide more details, which often play a key role in the application. To obtain high-resolution images, the most direct way is to use high-resolution image sensors, but due to the limitations of the manufacturing process and cost of sensors and optical devices, it is difficult to achieve in many occasions and large-scale deployment. [0003] Therefore, it is of great practical significance to obtain high-resolution images through super-resoluti...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/00G06N3/02G06N3/08
Inventor 刘广明郭跃飞路红张军平
Owner FUDAN 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