Rank-based transformation algorithm for image contrast adjustment
Year: 2025
Type: article
Abstract: Performing proper image contrast adjustment without information loss is an art. The default settings are often inappropriate for the image in question rendering a contrast adjustment depending on trial and error. We propose a simple method, rank-based transformation (RBT), for image contrast adjustment that requires no prior knowledge. This makes RBT an ideal first tool to apply for underexposed images. The RBT algorithm normalizes and equalizes all the intensity differences of the image over the full intensity range of the image data type, and thus assigning equal weight to all gradients. Even the state-of-the-art AI tool Cellpose visually benefits from RBT preprocessing. Our comparison of histogram normalization methods demonstrates the ability of RBT to bring out image features.
Authors: Cheng-Hui Chen, Torbjörn E.M. Nordling
Institution: National Cheng Kung University
Language: English
Topic: Image Enhancement Techniques
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $2,470
Awards: G3856973164, Development of Reliable Video-Based Monitoring of Vital Signs, In Depth Study of Serocomplex and Antigenic Clustering of Flavivirus through a Universal Vlp Platform, A Web Service Utilising Artificial Intelligence for Evaluation of Computational Reproducibility in Life Science, G6988584423, Forecasting of Covid-19 Based on Synthetic Individual Data
OpenAlex ID: W4416425409