Title :
A two stage defect recognition method for parquet slab grading
Author :
Kauppinen, Hannu
Author_Institution :
Dept. of Electr. Eng., Oulu Univ., Finland
Abstract :
This paper demonstrates the use of a simple but effective color-based inspection method in parquet slab grading. The approach is to divide the image to small rectangular regions and calculate color percentile features from these areas. Classification is performed in two stages: defect detection and recognition. The recognition results are further used in determining the final grade for the parquet slabs. Comparative results are also presented
Keywords :
automatic optical inspection; flaw detection; image classification; image colour analysis; wood processing; color percentile features; color-based inspection method; defect detection; image classification; image recognition; parquet slab grading; small rectangular regions; two stage defect recognition method; Fires; Histograms; Humans; Inspection; Machine vision; Shape; Size measurement; Slabs; Surface cracks; Testing;
Conference_Titel :
Pattern Recognition, 2000. Proceedings. 15th International Conference on
Conference_Location :
Barcelona
Print_ISBN :
0-7695-0750-6
DOI :
10.1109/ICPR.2000.903039
