White balance processing method directed towards atypical-feature image

A feature image and processing method technology, which is applied in the field of white balance processing for atypical feature images, can solve the problems of unreal values, grayscale world method distortion, etc. Effect

Inactive Publication Date: 2013-01-16
SHANGHAI UNIV
View PDF5 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the color of the image is not rich, the grayscale world method is often distorted; when the br

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
  • White balance processing method directed towards atypical-feature image
  • White balance processing method directed towards atypical-feature image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0019] This white balance processing method for atypical feature images is mainly aimed at image frames where the white area detection is not obvious and the colors are not sufficiently rich. It is characterized by including the following steps:

[0020] 1) The color video signal is collected by the Cameralink industrial camera in real time, and the video signal transmitted to the FPGA is a 10-bit RGB space video signal.

[0021] 2) Scan a frame of video image, and determine whether there is a white area in the current image according to the preset white point brightness threshold T and the RGB component value in the current image; at the same time, according to the preset RGB channel difference threshold D, and the current image The average value of RGB components determines whether the image is rich in color;

[0022] 3) If it is determined that there is no white area in the current image and the color is not rich, the color space conversion is performed on it, and the average chr...

Embodiment 2

[0026] This embodiment is basically the same as the first embodiment, and the special features are as follows:

[0027] The step 3) using the perfect reflection method to calculate the reference point of Cw_ave as the brightest spot in the current frame image, and using the gray world method to calculate the reference point of Ch_ave as all points of the current frame image.

[0028] Said step 4) Use the adjustment factor K to calculate the improved gains of the three primary colors, and use the gain to correct the original RGB output signal; for images with inconspicuous white areas and less colorful colors, compared to using the perfect reflection method or grayscale alone The world method can achieve a better white balance effect.

Embodiment 3

[0030] The program flow chart of the white balance processing method for atypical feature images is as follows figure 1 Shown. Mainly utilize resources such as FPGA on-chip multiplier, internal memory, and logic unit to realize several major modules such as video signal color space conversion and classic algorithm fusion under the control of the line and field synchronization signals of the video signal. Finally, the color video signal with white balance correction is output.

[0031] Since the RGB channel is 10-bit encoded data, when the RGB signal satisfies the formula (1), it is defined as a white point, and the area formed by the white point is the white area in the perfect reflection method.

[0032] Max{R,G,B} T (1)

[0033] Theoretically, the white point should satisfy T=1023. Considering that there are very few white points in the real world in the strict sense, T represents the RGB channel threshold and is set to 1000.

[0034] For one frame of image, count the sum of all R...

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 white balance processing method directed towards an atypical-feature image. The method comprises the following steps: (1) acquiring the brightest spot RGB (Red, Green and Blue) information of a frame of images as well as an RGB mean through a Camera Link industrial camera; (2) scanning the frame of video images, setting a white spot brightness threshold value and an RGB channel difference threshold, and determining whether current images contain a white area or not and color is rich or not; (3) performing color space conversion on the current images if the current images are determined that the white region is not contained and the color is not rich, and respectively calculating an average chromaticity Cw_ave of a reference point of a perfect reflection method and an average chromaticity Ch_ave of a reference point of a gray world method; and (4) calculating an average chromaticity Cw_ave obtained by the perfect reflection method and an average chromaticity Ch_ave obtained by the gray world method directed towards the current images, and performing white balance correction combined with two classic algorithms on the current frame of images by using the ratio of the Cw_ave and (the Cw_ave plus the Ch_ave) as an adjustment factor K. The method can be realized by using the recourses of an FPGA (Field Programmable Gata Array) internal logic unit, an internal memory, a multiplier and the like.

Description

Technical field [0001] The invention relates to the field of digital image processing, in particular to a white balance processing method for atypical feature images, belonging to the field of electronic information. Background technique [0002] In recent years, computer vision technology has developed rapidly. According to different applications, computer vision processing mainly includes region segmentation, image enhancement, edge detection, feature extraction, target tracking and so on. At present, computer vision processing technology is mainly based on PC operation. With the development of embedded technology, embedded machine vision technology has gradually been widely used in various fields such as scientific research, industrial control, and aerospace. The field programmable device (FPGA) that appeared in the 1990s has convenient and flexible design. The parallel processing structure can greatly shorten the processing time and meet the real-time requirements of man...

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): H04N9/73
Inventor 李翔伟陆小锋何康沈苏旻陆亨立范天翔
Owner SHANGHAI 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