Busca avançada
Ano de início
Entree
(Referência obtida automaticamente do Web of Science, por meio da informação sobre o financiamento pela FAPESP e o número do processo correspondente, incluída na publicação pelos autores.)

Machine learning hyperparameter selection for Contrast Limited Adaptive Histogram Equalization

Texto completo
Autor(es):
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]
Número total de Autores: 6
Afiliação do(s) autor(es):
[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
Número total de Afiliações: 4
Tipo de documento: Artigo Científico
Fonte: EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING; MAY 6 2019.
Citações Web of Science: 1
Resumo

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)

Processo FAPESP: 12/23114-9 - Uso de meta-aprendizado para ajuste de parâmetros em problemas de classificação
Beneficiário:Rafael Gomes Mantovani
Linha de fomento: Bolsas no Brasil - Doutorado