Method and device for image bit-depth expansion based on combination frame

An extension method and bit depth technology, applied in the field of image bit depth extension method and device based on hybrid framework, can solve the problems of loss of high-frequency details in non-flat areas, weak bit reconstruction ability, difficult low bit depth image restoration, etc., to achieve Suppresses the band effect and improves the subjective visual quality

Active Publication Date: 2017-12-15
PEKING UNIV SHENZHEN GRADUATE SCHOOL
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current bit-depth extension methods are mostly traditional non-learning methods, which use fixed strategies to fill in the missing bit information, but the ability to reconstruct the real value of the missing bit is weak, and at the same time, ...

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
  • Method and device for image bit-depth expansion based on combination frame
  • Method and device for image bit-depth expansion based on combination frame
  • Method and device for image bit-depth expansion based on combination frame

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] Below in conjunction with accompanying drawing, further describe the present invention through embodiment, but do not limit the scope of the present invention in any way.

[0041] The present invention provides an image bit depth extension method based on a hybrid framework, which can better remove the unnatural effect of the flat area of ​​the image by fusing the traditional stripping effect algorithm and the learning algorithm based on the deep network, and at the same time restore all the images more realistically. Numerical information for missing bits.

[0042] figure 1 Shown is the flow of the method of the present invention, including the extraction process of the flat area of ​​the image, the bit depth expansion process of the flat area based on local adaptive pixel value adjustment, and the bit depth expansion process of the non-flat area based on the convolutional neural network, specifically including the following steps :

[0043] The first step: the extra...

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 discloses a method and device for image bit-depth expansion based on a combination frame. The traditional de-banding effect algorithm and the learning algorithm based on a deep network are fused to remove the unnatural effect of an image flat region and more realistically recover the value information of deleted bits; and the method comprises extraction of the image flat region, the flat region bit-depth expansion based on local adaptive pixel value regulation and the non-flat region bit depth expansion based on the convolutional neural network. The method based on learning is employed to solve the vivid bit deletion recovery problem through training of an efficient deep network; and moreover, the method effectively inhibits the unnatural effects such as banding effect, the ringing effect, flat noise and the like of a flat region aiming at usage of a simple and robust local adaptive pixel value regulation method at the flat region so as to improve the subjective visual sense quality of the flat region.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to image bit depth extension and enhancement processing technology, in particular to an image bit depth extension method and device based on a hybrid framework, which combines adaptive pixel value adjustment and convolutional neural network based reconstruction technique. Background technique [0002] Image bit-depth expansion (Bit-Depth Expansion) refers to the recovery of high-bit-depth images from low-bit-depth images. The bit depth of an image (Bit-Depth) is the number of binary bits in the value of each pixel in the image. For example, the value range of a pixel in an 8-bits image is 0 to 255 (28). The higher the bit depth of the image, the more delicate the brightness changes can be reflected. The bit depth that the human eye can perceive is between 12 and 14 bits, so we often feel that the image seen through the 8bits display is different from the picture seen by the...

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): G06T7/50
CPCG06T7/50G06T2207/10028G06T2207/20081G06T2207/20084H04N1/58H04N1/6072G06N3/08G06N3/045G06T7/11G06T5/001G06T5/008G06T2207/20012
Inventor 赵洋王荣刚高文王振宇王文敏
Owner PEKING UNIV SHENZHEN GRADUATE SCHOOL
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