Multilayer Perceptron classifier combination for identification of materials on noisy soil science multispectral images

Author(s)

Brevel, Fabricio A. ; Ponti, Moacir P., Jr. ; Mascarenhas, Nelson D. A.

• Document type: Journal article
• Source: 2009 XXII BRAZILIAN SYMPOSIUM ON COMPUTER GRAPHICS AND IMAGE PROCESSING (SIBGRAPI 2009); v. N/A, p. 2-pg., 2007-01-01.

Abstract

Classifier combination experiments using the Multilayer Perceptron (MY) were carried out using noisy soil science multispectral images, which were obtained using a Tomograph scanner. Using few units in the MLP hidden layer, images were classified using a single classifier. Later we used classifier combining techniques as Bagging, Decision Templates (DT) and Dempster-Shafer (DS), in order to improve the performance of the single classifiers and also stabilize If the performance of the Multilayer Perceptron. The classification results were evaluated using Cross-Validation. The results showed stabilization of Multilayer Perceptron and improved results were achieved with fewer units in the MLP hidden layer. (AU)

• FAPESP's process: 02/07153-2 - Algorithms for tomographic reconstruction: optimization, restoration, quantification and clinical application
• Grantee: Sergio Shiguemi Furuie
• Support Opportunities: Research Projects - Thematic Grants