Region texture analysis based Laplacian pyramid color transfer ICA method

Yuan Luo; Ping Chen; Hongqiang Lu; Pingping Yun; Yingqi Liu

doi:10.1117/12.3032729

22 November 2024 Region texture analysis based Laplacian pyramid color transfer ICA method

Yuan Luo, Ping Chen, Hongqiang Lu, Pingping Yun, Yingqi Liu

Proceedings Volume 13238, Advanced Optical Imaging Technologies VII; 132380J (2024) https://doi.org/10.1117/12.3032729
Event: SPIE/COS Photonics Asia, 2024, Nantong, Jiangsu, China

Conference Poster

Abstract

Independent Component Analysis(ICA) applied in the field of image processing is a noval transformation domain method that utilizes sparse coding on the basis of analyzing the characteristics of the human visual system. It has multidirectionality, feature extraction, and edge modeling characteristics. Color transfer is currently the best way to integrate natural color in images. On the basis of effectively integrating ICA method and color transfer algorithm, a region texture color transfer-ICA natural color fusion algorithm is proposed by organically combining the matching parameters and transfer parameters of color transfer. Dynamic online method training ICA domain decomposition kernel function and synthesis kernel function; generating grayscale fusion images according to regional energy fusion rules; using grayscale image color transfer algorithm based on regional Gray Level Co-occurrence Matrix(GLCM) texture to extract texture features of reference images, achieving optimal matching with regional texture features of grayscale fusion images, and linearly assigning first-order and second-order color information to grayscale images to generate source color image; the Laplacian pyramid decomposes the color space channels of the source color image and color reference image into multiple resolutions for color transfer, enhancing the natural color fusion image’s representation of significant scene information such as local textures. Human visual perception and objective evaluation indicates that the fusion image highlights band features and enhances detailed information with natural and comfortable colors, further improving scene perception.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yuan Luo, Ping Chen, Hongqiang Lu, Pingping Yun, and Yingqi Liu "Region texture analysis based Laplacian pyramid color transfer ICA method", Proc. SPIE 13238, Advanced Optical Imaging Technologies VII, 132380J (22 November 2024); https://doi.org/10.1117/12.3032729

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available