Computer Vision Algorithms Versus Traditional Methods in Food Technology: The Desired Correlation

Active Contours represent a common Pattern Recognition technique. Classical active contours are based on different methodologies (variational calculus, dynamic programming and greedy algorithm). This paper reviews the most frequently used active contours in a practical application, comparing weights, manually obtained by food technology experts, to volumes, automatically achieved by computer vision results. An experiment has been designed to recognize muscles from Magnetic Resonance (MR) images of Iberian ham at different maturation stages in order to calculate their volume change, using different active contour approaches. The sets of results are compared with the physical data. The main conclusions of the paper are the excellent correlation established between the data obtained with these three non-destructive techniques and the results achieved using the traditional destructive methodologies, as well as the real viability of the active contours to recognize muscles in MR images.

[1]  R. Courant,et al.  Methods of Mathematical Physics , 1962 .

[2]  John W. Berry,et al.  Theory and method , 1997 .

[3]  Jerry L. Prince,et al.  Gradient vector flow: a new external force for snakes , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[4]  Anthony J. Yezzi,et al.  Gradient flows and geometric active contour models , 1995, Proceedings of IEEE International Conference on Computer Vision.

[5]  Petia Radeva,et al.  Guidelines for Choosing Optimal OParameters of Elasticity for Snakes , 1995, CAIP.

[6]  Ramesh C. Jain,et al.  Using Dynamic Programming for Solving Variational Problems in Vision , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Laurent D. Cohen,et al.  On active contour models and balloons , 1991, CVGIP Image Underst..

[8]  Petia Radeva,et al.  Bounds on the Optimal Elasticity Parameters for a Snake , 1995, ICIAP.

[9]  Andrés Caro,et al.  ACTIVE CONTOURS USING WATERSHED SEGMENTATION , 2002 .

[10]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[11]  Mubarak Shah,et al.  A Fast algorithm for active contours and curvature estimation , 1992, CVGIP Image Underst..

[12]  Michael Isard,et al.  Active Contours , 2000, Springer London.

[13]  Andrés Caro,et al.  Potential Fields as an External Force and Algorithmic Improvements in Deformable Models , 2003 .

[14]  L Kish.  Statistical medicine. , 1994, Science.

[15]  Teresa Antequera,et al.  Lipid oxidative changes in the processing of Iberian pig hams , 1992 .