1 December 1996 Automated system for detection and classification of leather defects
Author Affiliations +
Optical Engineering, 35(12), (1996). doi:10.1117/1.601111
A leather inspection system based on visual textural properties of the material surface is presented. Defects are isolated from the complex and nonhomogeneous background, analyzing their oriented structure. The patterns to be analyzed are represented in an appropriate parameter space using a neural network, in this way, a parameter vector is associated to each different textured region in the original image. Finally a filter process, based on knowledge about the parameter vectors representing the leather without defects, detects and classifies any abnormality. The resulting system is flexible and does not depend on dimensions, structure, and color of defects.
Antonella Branca, Maria Tafuri, Giovanni Attolico, Arcangelo Distante, "Automated system for detection and classification of leather defects," Optical Engineering 35(12), (1 December 1996). http://dx.doi.org/10.1117/1.601111


Neural networks

Classification systems

Image classification

Optical engineering

Coherence (optics)

Defect detection


Mask cost for sub 100 nm technologies stopping a...
Proceedings of SPIE (July 02 2003)
Cost analysis of 4x and 6x 9 in. reticles for...
Proceedings of SPIE (December 30 1999)
X-shooter near-IR spectrograph arm realisation
Proceedings of SPIE (July 09 2008)

Back to Top