A computer-based system for dyeing leather patch edges

The visual appearance of seamless dyed edges of luxury leather goods represents a key issue in terms of quality grading since a high-quality leather has to be characterised by homogeneously coloured and shaped edges with uniform ink thickness. Despite a huge literature produced by scientific and technical community to automate many leather manufacturing processes, since leather patches are often characterised by a free-form shape, any attempt of automating leather edges dyeing produced unsatisfactory and inaccurate results. In order to overcome the drawbacks of the existing approaches, the main objective of the present work is to provide a computer-based system for automatically dyeing leather patches edges. The described system includes: 1) a machine vision (MV) hardware equipment, consisting of both illumination and a high resolution acquisition device, devoted to patches edge detection; 2) a pantograph whose dyeing tool is moved along leather edges; 3) a series of computer-based methods for the automatic extraction of the leather patches outlines. Extensive testing performed using the developed machine demonstrated its effectiveness in delivering fast, automatic and high quality edge finishing in a reliable and repeatable way.

[1]  Bojan Nemec,et al.  Shoe Grinding Cell using Virtual Mechanism Approach , 2008, ICINCO-RA.

[2]  Hemerson Pistori,et al.  Defect detection in raw hide and wet blue leather , 2006, CompIMAGE.

[3]  Paul R. Cohen,et al.  Camera Calibration with Distortion Models and Accuracy Evaluation , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Tai-Hsi Wu,et al.  Nesting of two-dimensional parts in multiple plates using hybrid algorithm , 2003 .

[5]  Der-Baau Perng,et al.  Establishing a Demerit Count Reference Standard for the Classification and Grading of Leather Hides , 2001 .

[6]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Andrew Zisserman,et al.  Multiple View Geometry in Computer Vision (2nd ed) , 2003 .

[8]  K. Hoang,et al.  Image processing techniques for leather hide ranking in the footwear industry , 1996 .

[9]  José Fernando Oliveira,et al.  A 2-exchange heuristic for nesting problems , 2002, Eur. J. Oper. Res..

[10]  S. Sitharama Iyengar,et al.  Finding obstacle-avoiding shortest paths using implicit connection graphs , 1996, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[11]  G. A. Watson,et al.  A class of methods for fitting a curve or surface to data by minimizing the sum of squares of orthogonal distances , 2003 .

[12]  Wei Wen,et al.  Achieving automation in leather surface inspection , 1997 .

[13]  Giovanni Attolico,et al.  Automated system for detection and classification of leather defects , 1996 .

[14]  Alberto Tellaeche,et al.  Robotics for the Benefit of Footwear Industry , 2012, ICIRA.

[15]  Janne Heikkilä,et al.  A four-step camera calibration procedure with implicit image correction , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[16]  Andrew Zisserman,et al.  Multiple View Geometry , 1999 .

[17]  David H. Douglas,et al.  ALGORITHMS FOR THE REDUCTION OF THE NUMBER OF POINTS REQUIRED TO REPRESENT A DIGITIZED LINE OR ITS CARICATURE , 1973 .

[18]  T. Clarke,et al.  The Development of Camera Calibration Methods and Models , 1998 .

[19]  Wen Wang,et al.  Automatic Visual Inspection for Leather Manufacture , 2006 .

[20]  Marcello Pellicciari,et al.  Real-time 3D features reconstruction through monocular vision , 2010 .

[21]  Kathryn A. Dowsland,et al.  The irregular cutting-stock problem - a new procedure for deriving the no-fit polygon , 2001, Comput. Oper. Res..