Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Restore method of blurred text and image in video tape

A video tape and blur technology, applied in the field of blurred image restoration processing, can solve the problems of small license plate number image, poor image, insufficient original image resolution, etc.

Inactive Publication Date: 2004-07-28
TSINGHUA UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In some banks, video recorders are used to record the live images of the business halls. Sometimes it happens that the deposits in the bank are fraudulently claimed, and the images recorded by the video recorders are poor. The detection work needs to clarify the portraits in the pictures. deal with
In the car toll booth, the license plate number recorded by the video recorder is also unreadable because the image is too small
[0004] For the restoration of blurred text and blurred portraits in video tapes, the general method is to send the images of blurred texts and blurred portraits in video tapes directly to the computer through the video image acquisition card and use Wiener filtering or other methods for restoration. Raw images aren't high enough resolution to work

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
  • Restore method of blurred text and image in video tape
  • Restore method of blurred text and image in video tape
  • Restore method of blurred text and image in video tape

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] Embodiment 1 is a method for restoring a blurred portrait. The image of the blurred portrait is taken from a bank's video tape. Specific steps include;

[0026] 1) Connect with video recorder and image monitor, and also connect with video printer at the same time, broadcast the video tape containing the image to be processed with video recorder, observe the image on the image monitor from the image monitor, and determine the video tape to be processed Image position, after finding the videotape image position to be processed, the image (that is, the video printer photo) that needs to be restored is output by the video printer; wherein, the connection of the video printer and video recorder is as follows figure 1 as shown, figure 1 The function of the monitor in the computer is to observe the image played by the video recorder, so as to determine the video tape image to be restored.

[0027] 2) Use a scanner to input video tape photos containing images to be processed ...

Embodiment 2

[0043] Embodiment 2 is a method for restoring blurred text on a video tape. The image of the blurred text is taken from a video tape at a motor vehicle toll station. Concrete steps are with step 1) to step 3) of embodiment 1.

[0044] Figure 7 It is the unclear original image recorded by the video recorder output by the video printer of this embodiment, and any number in the license plate number cannot be recognized from the figure. Figure 8 It is a defocused blurred digitized image input by the scanner, and the resolution of the scanner is 1200 lines at this time. Figure 9It is a restoration method using Wiener filtering for Figure 8 The result of restoration, where the point diffusion radius R is 22, and the reciprocal r of the image signal-to-noise ratio is 0.005. From Figure 9 It can be clearly seen that there is a "7" in the license plate number, thus achieving the purpose of partial restoration.

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 present invention relates to the method for blurred image restoration in the digital image processing, which is characterized by that said method includes four portions of the method using video printer to deliver videotape imag to be processed, method using scanner to transfer the videotape image delivered by video printer into computer to form amplified out-of-focus blurred image, method using wiene filter to restore out-of-focus blurred image and method using computer human image combination to ofrm clear human image. By adopting said invention the original fuzzy characters and blurred image which can not be identified can be identified completely or partially, and its effect improvement is obvious.

Description

technical field [0001] The invention belongs to the technical field of computer image processing, in particular to a blurred image restoration processing method. Background technique [0002] As we all know, the restoration of blurred images, especially the restoration of videotape blurred images, is a major problem in image processing, and has many application backgrounds. [0003] Taking a picture of a moving car, it is difficult to see the license plate number of the car from the obtained photo, which has caused great difficulties in investigating and punishing traffic violations and traffic perpetrators. At a tourist attraction, a tourist accidentally took a picture of a sudden crime scene while taking pictures. Due to defocus, the criminal's appearance in the photo was unrecognizable, so it was necessary to restore the blurred image. In the detection of public security criminal cases, it is more necessary to restore blurred characters and blurred portraits in video tap...

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 Patents(China)
IPC IPC(8): G06T5/00
Inventor 苏光大
Owner TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com