Купить СНПЧ А7 Архангельск, оперативня доставка

crosscheckdeposited

Classificador Textural para Identificação de Plantas

DOI: http://dx.doi.org/10.13083/1414-3984.v18n06a07

http://www.seer.ufv.br/seer/index.php/reveng/index 

downloadpdf

José A. R. de Souza1 & Débora A. Moreira2

 

Resumo: No presente trabalho, objetivou-se desenvolver um classificador textural em Matlab, para identificação de quatro espécies de plantas. A textura foi definida por meio de um conjunto de medidas estatísticas, descrevendo as variações espaciais de intensidade de pixels ou cor da parte aérea das plantas. As medidas foram calculadas utilizando-se matrizes de ocorrência. Os resultados indicaram que a classificação textural para identificação de plantas é uma das mais simples possíveis, sendo os resultados das classificações extremamente relacionados com as texturas analisadas.

Palavras-chave: classificação de imagens, textura, matriz de co-ocorrência

 

Abstract: The objective of this work was to develop a texture classifier in Matlab to identify four plant species. The texture was defined by means of a set of statistical measures describing the spatial variations of pixel intensity or color of the shoots. Such measures were calculated using matrices of co-occurrence. The results showed that the textural classification for plant identification is simple, because the classification results highly related to the analyzed textures.

Key words: classification of images, texture, matrix of co-occurrence

 

1 Prof. IFET – GO, Rodovia Geraldo da Silva Nascimento, km 2,5, Urutaí-GO, email: jarstec@yahoo.com.br
2 Profª. UEMG – Ubá-MG, Rua: Olegário Maciel, 1427- Bairro Industrial – Ubá – MG, email: deboraastoni@yahoo.com.br

 

Literatura Citada

AKSOY, S. Textural features for image database retrieval. Dissertação (Mestrado) — University of Washington, Seattle, WA.1998.

AYALA, W.; DOMINGO, J. Spatial size distributions: Applications to shape and texture analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, Spain, v.23, n.12, p.1430–1442, 2001. doi

BISHOP, Y.; FIENBERG, S.; HOLLAND, P. Discrete multivariate analysis: theory and practice. Cambridge, Estados Unidos: MIT, 1975. 575p.

CARD, D. H. Using know map category marginal frequencies to improve estimates of thematic map accuracy. Photogrammetric Engineering and Remote Sensing, v.43, n.3, p.431-439, 1982.

CONGALTON, R. G; GREEN, K. A practical look at source of confusion in error matrix generation. Photogrammetric Engineering and Remote Sensing, v. 59, n. 5, p. 641-644, 1993.

CONNERS R. W.; HARLOW C. A. A. Theoretical Comparison of Texture Alogrithms, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.2, n.3, p.204-222, 1980. doi

DUDA, R; HART, P. Pattern Classification and Scene Analysis. New York: John & Sons, 1973. 482p.

FERREIRA, M. A. L; FIGUEIREDO, A. M. Chroma Key a partir de imagens de TV Utilizando análise de Textura. Pontifícia Universidade Católica do Rio de Janeiro, Departamento de Informática 6p. 2006. Disponível em: <http://www.tecgraf.puc-rio.br/~mgattass/fcg/trb06/T2-Aurelio%20&%20Mauricio/paper1.doc>. Acessado em 18 out de 2006.

HARALICK, R. M.; SHANMUGAM, K.; DINSTEIN, I. Textural features for image classification. IEEE Transactions on Systems, Man and Cybernetics, v.3, n.6, p.610–621, 1973. doi

IIVARINEN, J.; VISA, A. An adaptive texture and shape based defect classification. In: In Proc. International Conf. on Pattern Recognition. [S.l.; s.n.], 1998. p. 117–123.

LI, S.Z. Markov Random Field, Modeling in Computer Vision, Springer-Verlag, ISBN 0-387-70145-1, 1995 LIEW, S. C. et al. Texture analysis of SAR images. In: International Geoscience and Remote Sensing Symposium. [S.l.; s.n.], 1995. p.1412–1414.

MARCEAU, D. J. et al. Evaluation of the grey-level coocurrence matrix method for land-cover classification using SPOT imagery. IEEE Transactions on Computers, Waterloo, Canada, p.513–519, 1990.

MUDIGONDA, N. R.; RANGAYYAN, R. M.; DESAUTELS, J. E. L. Gradient and texture analysis for the classification of mammographic masses. IEEE Transactions on Medical Imaging, v.19, n.10, p.1032–1043, 2000. doi

PEREIRA, A. K.; OLIVEIRA, E. A.; LEITE, H. V.; CABRAL, A. C. V. Correlação entre o Diagnóstico Morfológico Pré e Pós-natal das Nefrouropatias Fetais. Revista Brasileira de Ginecologia e Obstetrícia v.22, n.6, p.365-371, 2000. doi

PIERCE, L. et al. Texture features for classification with ERS/JERS composites. IEEE Transactions on Computers, p.348–350, 1998.

ROSENFIELD, G. H.; FITZPATRICK, K. A coefficient of agreement as a measure of thematic classification accuracy. Photogrammetric Engineering & Remote Sensing, v.52, n.2, 1986. p.233-227.

SCHOWENGERDT, R. A. Techniques for Image Processing an Classification in Remote Sensing. Arizona: Academic Press, 2000. 520 p.

SHABAN, M. A.; DIKSHIT, O. Textural classification of high resolution digital satellite imagery. IEEE Transactions on Computers, p. 2590-2592, 1998.

SOLBERG, A. H. S.; JAIN, A. K. A study of the invariance properties of textural features in SAR images. IEEE Transactions on Computers, p.670–672, 1995.

STORY, M. Accuracy assessment: user’s perspective. Photogammetric Engineering and Remote Sensing, v.52, n.3, 1986. p.397-399.

TURCEYAN, M and A. K. JAIN. Handbook of Pattern Recognition and Computer Vision, chapter Texture Analysis, p. 235–276. World Scientific Publishing Company, 1993.