Entropy-Based Approach to Analyze and Classify Mineral Aggregates

Autor(es)

de Gouveia, Lilian Tais ^[1] ; Costa, Luciano da Fontoura ^[1] ; Senger, Luciano Jose ^[2] ; Albertini, Marcelo Keese ^[3] ; de Mello, Rodrigo Fernandes ^[3]

Afiliação do(s) autor(es)

^[1] Univ Sao Paulo, Inst Fis Sao Carlos, BR-13560970 Sao Carlos, SP - Brazil

^[2] Univ Estadual Ponta Grossa, Dept Informat, BR-84030900 Ponta Grossa, PR - Brazil

^[3] Univ Sao Paulo, Inst Ciencias Matemat & Computacao, Dept Ciencias Computacao, BR-13560970 Sao Carlos, SP - Brazil

• Tipo de documento: Artigo Científico
• Fonte: JOURNAL OF COMPUTING IN CIVIL ENGINEERING; v. 25, n. 1, p. 75-84, JAN-FEB 2011.
• Citações Web of Science: 2

Resumo

This paper presents an automatic method to detect and classify weathered aggregates by assessing changes of colors and textures. The method allows the extraction of aggregate features from images and the automatic classification of them based on surface characteristics. The concept of entropy is used to extract features from digital images. An analysis of the use of this concept is presented and two classification approaches, based on neural networks architectures, are proposed. The classification performance of the proposed approaches is compared to the results obtained by other algorithms (commonly considered for classification purposes). The obtained results confirm that the presented method strongly supports the detection of weathered aggregates. (AU)

• Processo FAPESP: 07/01128-0 - Predicao do comportamento estrutural e mecanico de misturas de concreto asfaltico utilizando tecnicas de processamento digital de imagens
• Beneficiário: Lilian Tais de Gouveia
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado