Color transfer between images

• Main Author: Liang, Ruyin
• Other Authors: He Ying
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2021
• Subjects: Engineering::Computer science and engineering
• Online Access: https://hdl.handle.net/10356/153337
• Institution: Nanyang Technological University

Color transfer is one of the digital image processing tasks. It changes the dominant color of a source image to match the color characteristics of the reference image, while the scene and the objects of the source image remain unchanged. This report evaluated two color transfer algorithms: the statistical approach and the iterative 1D mapping approach. Their implementations were presented in this report. The two algorithms' performance was measured in terms of color distribution, information loss, and image fidelity. The method using mean and standard deviation yields acceptable results is simple to implement and has an inexpensive computational cost. The iterative 1D mapping approach produces good results in terms of color matching but fails to preserve scene details.