Metodologia de inspeção visual utilizando limiar("Threshold") entrópico com aplicações na classificação de placas de madeira / Methodology for visual inspection using entropic threshold with aplications in wooden board classification




The objective of this work was to develop a dedicated computer vision method for the classification of wooden plates used in pencil manufacturing. The process here proposed was idealized looking for a low computational complexity methodology that could be accomplished in VLSI, as for instance using Systolic Computer Architectures made of logic arrays. The pencil cycle of production is described, locating the stage where the proposed classification methodology should be used. There is a sequence of procedures, along the work, that describe the acquisition, extraction of the characteristics and the processing of the images, and finally the classification algorithms. For the extraction of characteristics of the images, it was used an automatic method for the threshold determination, based on Shannons entropy. The information supplied by the threshold determination method allows classifying the plates in different classes. The analysis of the results showed that the method performs well is repetitive and efficient on the classification and its use can be extended to classifying other final products.


classificações de padrões pattern classification limiar entrópico visão computacional computational vision visual inspection inspeção visual entropic threshold

Documentos Relacionados