Avaliação de Métodos de Extração de Características para Classificação da Qualidade de Peles de Caprinos

Abstract

An important economic alternative for the semi-arid region of Brazil is the goat and sheep farming. Besides milk and meat, goat/sheep skins are much appreciated in the manufacturing of fine artifacts (e.g. shoes, bags & purses, wallets, and jackets). However, due to the extensive mode of raising/breeding and the informality of slaughtering, sheep/goat farmers deliver to industry skin pieces with different types and levels of defects. Then, at the industry, specialized workers have to classify/discriminate the skin pieces according to their qualities. This handmade work is timeconsuming and extremely dependent on the experience of the employee in charge of the skin-quality discrimination. Even the same employee may produce different classifications if he/she is asked to reclassify the skin lot. Thus, in order to handle these problems, in this paper we report the first results of a computer vision based system aiming at classifying automatically the quality of goat/sheep skin pieces. For this purpose, we compare the performances of statistical and neural network classifiers using several feature extraction techniques, such as Column-Variance, Haar wavelet transform, Non-Negative Matrix Factorization (NMF) and Principal Component Analysis (PCA). The obtained results clearly indicate a better performance for the neural network classifier using the Haar wavelet transform and PCA as feature extractors.

A decision support system for fault detection and definition of the quality of wet blue goat skins

“…The authors used the structure developed by Edmilson Q. S. Filho, José D. A. Santos and Guilherme A. Barreto [6] to acquire images of goat leather. The structure, illustrated in Fig.…”

“…For example, E.Q. Santos Filho, G. Barreto and J. Daniel Santos [6] consider only two types of quality: high, for good quality leather, and low, for bad leather. It is also possible to consider 5 types of quality: level 1, with only 10% defects, level 2, between 10 and 30%, level 3, between 30 and 50%, level 4, plus 50% defects, and leve 5, considered rejected or only 4 levels as excellent, good, regular and bad.…”

“…E.Q. Santos Filho, G. Barreto, and J. Daniel Santos [6] propose a model for classifying skin samples in the wet blue stage. The set of images is divided into 7 types of classes in which the author divided them into Upper Class (classes 1 to 5) and Lower Class (classes 6 and 7).…”