• V.Thamilarasi
• DR.R.Roselin

Woods are the gifted and basic resource to human beings. Wood is anisotropic and heterogeneous in nature. Every aspect of wood is important as different wood has different characteristics and features, these might affect the nature of uses in different environments like conservation, construction, wood fabrication, forensic investigation, archaeology and etc. The wood consumers need absolute wood recognition and measure the quality of wood, still automatic wood analyzer has not been achieved. There are not enough researches in this area due to lack of availability of benchmark database in wood. Identifying quality of wood and detection of wood abnormalities like knots, lumber, cracks, holes, blue surface, etc., is very difficult and time consuming process. This paper presents the different computer aided techniques which is used for wood recognition through detection of wood abnormalities like knots, holes. Image processing techniques have been applied on images which are taken from web resources. This paper examines only two defects knots and holes in the wood samples. Images are enhanced by using image preprocessing techniques and the defect portions are segmented using morphological operators. Haralick texture features are extracted over Gray Level Cooccurrence matrix (GLCM) and classified by machine vision classifiers of Weka tool. The results attained high rate (90%) of defect detection in wood and also proves techniques used in this paper are appropriate for identification of knots and holes.

Image processing, Wood abnormalities, Segmentation, Feature Extraction, and Classification

"IMAGE PROCESSING TECHNIQUES IN WOOD ABNORMALITIES IDENTIFICATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 3, page no.324-332, March-2019, Available :http://www.jetir.org/papers/JETIRAD06054.pdf

"IMAGE PROCESSING TECHNIQUES IN WOOD ABNORMALITIES IDENTIFICATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 3, page no. pp324-332, March-2019, Available at : http://www.jetir.org/papers/JETIRAD06054.pdf