Advanced search
Start date
(Reference retrieved automatically from Web of Science through information on FAPESP grant and its corresponding number as mentioned in the publication by the authors.)

Machine learning hyperparameter selection for Contrast Limited Adaptive Histogram Equalization

Full text
Centini Campos, Gabriel Fillipe [1] ; Mastelini, Saulo Martiello [2] ; Aguiar, Gabriel Jonas [2] ; Mantovani, Rafael Gomes [3, 4] ; de Melo, Leonimer Flavio [1] ; Barbon, Jr., Sylvio [2]
Total Authors: 6
[1] Univ Estadual Londrina, Dept Elect Engn, Rodovia Celso Garcia Cid, BR-86057970 Londrina, PR - Brazil
[2] Univ Estadual Londrina, Dept Comp Sci, Rodovia Celso Garcia Cid, BR-86057970 Londrina, PR - Brazil
[3] Univ Sao Paulo, Inst Math & Comp Sci ICMC, Ave Trabalhador Sao Carlense 400, BR-13566590 Sao Carlos, SP - Brazil
[4] Univ Tecnol Fed Parana, Dept Comp Engn, Apucarana, PR - Brazil
Total Affiliations: 4
Document type: Journal article
Web of Science Citations: 1

Contrast enhancement algorithms have been evolved through last decades to meet the requirement of its objectives. Actually, there are two main objectives while enhancing the contrast of an image: (i) improve its appearance for visual interpretation and (ii) facilitate/increase the performance of subsequent tasks (e.g., image analysis, object detection, and image segmentation). Most of the contrast enhancement techniques are based on histogram modifications, which can be performed globally or locally. The Contrast Limited Adaptive Histogram Equalization (CLAHE) is a method which can overcome the limitations of global approaches by performing local contrast enhancement. However, this method relies on two essential hyperparameters: the number of tiles and the clip limit. An improper hyperparameter selection may heavily decrease the image quality toward its degradation. Considering the lack of methods to efficiently determine these hyperparameters, this article presents a learning-based hyperparameter selection method for the CLAHE technique. The proposed supervised method was built and evaluated using contrast distortions from well-known image quality assessment datasets. Also, we introduce a more challenging dataset containing over 6200 images with a large range of contrast and intensity variations. The results show the efficiency of the proposed approach in predicting CLAHE hyperparameters with up to 0.014 RMSE and 0.935 R-2 values. Also, our method overcomes both experimented baselines by enhancing image contrast while keeping its natural aspect. (AU)

FAPESP's process: 12/23114-9 - Use of meta-learning for parameter tuning for classification problems
Grantee:Rafael Gomes Mantovani
Support type: Scholarships in Brazil - Doctorate