關於我們 聯絡我們
電子報下載


 
Image restoration method and image processing apparatus using the same
 
專利名稱 Image restoration method and image processing apparatus using the same
專利證書號 US 9,478,016 B2
專利權人 國立台北科技大學
專利國家 台灣, 美國 ,
發明人 黃士嘉、葉建輝、陳柏豪
應用領域 資訊, 電機, 機械
需求項目 專利授權
 
專利商品特色:
The invention discloses an image restoration method and an imager processing apparatus using the same. The method includes the following steps: receiving a haze image comprising a plurality of pixels; detecting whether a color cast phenomenon occurs on the haze image; if yes, calculating a plurality of Laplacian distribution values respectively corresponding to the color channels; determining a maximum distribution value and a minimum distribution value among the Laplacian distribution values, and generating a self-adaptive parameter by comparing the maximum distribution value and the minimum distribution value; adjusting the transmission map by the self-adaptive parameter so as to generate a adjusted transmission map; calculating a plurality of color parameters respectively corresponding to the color channels according to the Laplacian distribution values; and restoring the haze image by using the color parameters and the adjusted transmission map so as to obtain a restored image.

專利商品技術說明:
1. An image restoration method, wherein the image restoration method is based on an optical model formed by a transmission map, and the method comprises:
receiving a haze image comprising a plurality of pixels, wherein each of the pixels has a plurality of color components corresponding to a plurality of color channels;
detecting whether a color cast phenomenon occurs on the haze image;
if yes, calculating a plurality of Laplacian distribution values respectively corresponding to the color channels;
determining a maximum distribution value and a minimum distribution value among the Laplacian distribution values, and generating a self-adaptive parameter by comparing the maximum distribution value and the minimum distribution value;
adjusting the transmission map by the self-adaptive parameter so as to generate an adjusted transmission map;
calculating a plurality of color parameters respectively corresponding to the color channels according to the Laplacian distribution values; and
restoring the haze image by using the color parameters and the adjusted transmission map so as to obtain a restored image,
wherein the self-adaptive parameter is generated via dividing the maximum distribution value by the minimum distribution value, and the adjusted transmission map is generated via taking the self-adaptive parameter as an exponent of the transmission map being a radix.
2. The method as claimed in claim 1, wherein the optical model is expressed as:

I(x)=J(x)t(x)+A(1?t(x)),
wherein I(x) represents the haze image, J(x) represents a haze-free image, A represents the global atmospheric light, x represents pixel location of the pixels, and t(x) represents the transmission map,
wherein the transmission map t(x) is expressed as:

t(x)=e ?βd(x),
wherein β represents a scattering coefficient of the atmosphere and d(x) represents scene depth information.
3. The method as claimed in claim 1, wherein the step of calculating the Laplacian distribution values respectively corresponding to the color channels comprises:
determining a calculating region of the haze image, wherein the calculating region comprises a plurality of representing pixels;
determining a maximum color component of each of the representing pixels among the color components of each of the representing pixels;
respectively comparing the maximum color component with each of the color components of each of the representing pixels to obtain a plurality of color differences of each of the representing pixels, wherein the color differences are respectively corresponding to the color channels; and
calculating the Laplacian distribution values respectively corresponding to the color channels base on the color differences.
4. The method as claimed in claim 3, wherein the calculating region is a region having the highest intensity in the haze image.
5. The method as claimed in claim 3, wherein the formula for comparing the maximum color component with each of the color components of each of the representing pixels to obtain the color differences of each of the representing pixels is expressed as:

Δc(L)=|I M(L)?I c(L)|,
wherein c is an index of the color channels and cε{r,g,b}, Δc(L) represents the color differences respectively corresponding to the color channels, L represents any one of the representing pixels within the calculating region, IM (L) represents the maximum color component, and Ic(L) represents the color components,
wherein the formula for calculating the Laplacian distribution values base on the color differences is expressed as:
P ? ( Δ c ? ( L ) | S ) = 1 a ? ? L ? S ? exp ? {  Δ c ? ( L ) - μ  σ } ,
wherein P(Δc(L)|S) represents the Laplacian distribution values respectively corresponding to the color channels, p represents an ideal value of Δc(L), σ represents an optimum parameter, and α represents the number of the representing pixels in the calculating region S.
6. The method as claimed in claim 1, wherein the step of calculating the color parameters respectively corresponding to the color channels according to the Laplacian distribution values comprises:
respectively comparing the maximum distribution value with each of the Laplacian distribution values corresponding to the color channels so as to obtain a plurality of chromatic adaptable parameters for each of the color channels; and
generating the color parameters respectively corresponding to the color channels base on the chromatic adaptable parameters.
7. The method as claimed in claim 6, wherein the formula for generating the color parameters base on the chromatic adaptable parameters is expressed as:
α c = v c max c ? I c ,
wherein c is an index of the color channels and cε{r,g,b}, αcrepresents the color parameters, vc represents the chromatic adaptable parameters respectively corresponding to the color channels,
max c ? I c
?represents the maximum color component of each of the color channels in the haze image.
(因欄位字數限制,未將所有權項列出)

聯繫方式
聯絡人:專利技轉組 電 話:(02)8772-0360
與我連絡 地 址:10608 台北市忠孝東路三段1號 行政大樓5樓
 
 
   




國立臺北科技大學專利技轉組 10608 台北市忠孝東路三段1號 行政大樓5樓 TEL:(02)8772-0360
        2008-2017 © NTUT All Rights Reserved  著作權聲明
本系統採用專利行銷平台