Innovative Automated Landmark Detection for Food Processing: The Backwarping Approach

The shape of an object can be described by a finite number of points called landmarks. Nowadays, there are no systems available for the automated landmarks detection. However, the implementation of such method would be of elevated interest in the food industrial processing. The evaluation of cattle carcass and fish quality requires the time-consuming and manual positioning of landmarks, with still too subjective results. The aim of this work is the application of an innovative algorithm, called backwarping, for the automated positioning of landmarks onto the beef carcass and sea bass profiles. This algorithm combines the automated extraction of the outlines with the thin-plate spline interpolation algorithm. The proposed approach is applied to two very different cases in order to stress the high performing versatility of the procedure. We firstly carried out a calibration phase where the landmarks were manually placed. Then we applied the automated procedure for comparison. The errors in the automated landmarks positioning has been always lower than 3 % and the percentage standard error of prediction was always lower than 1.5 %. The approach for both study cases showed its feasibility in being easily extended to the processing of a diversified variety of food products, such as poultry, bakery or “pasta.” Moreover, due to its versatility, the technique could be also applied within the zoological and biomedical fields, given the obtained high levels of accuracy in the automated landmark positioning.

[1]  Amandeep Kaur,et al.  Automatic cephalometric landmark detection using Zernike moments and template matching , 2015, Signal Image Video Process..

[2]  E. Setiadi,et al.  Effect of saddleback syndrome and vertebral deformity on the body shape and size in hatchery‐reared juvenile red spotted grouper, Epinephelus akaara (Perciformes: Serranidae): a geometric morphometric approach , 2006 .

[3]  Hui Yang,et al.  Prediction of shelled shrimp weight by machine vision , 2008, Journal of Zhejiang University SCIENCE B.

[4]  Fred L. Bookstein,et al.  Principal Warps: Thin-Plate Splines and the Decomposition of Deformations , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  P. G. Lee,et al.  A review of automated control systems for aquaculture and design criteria for their implementation , 1995 .

[6]  Dominique Adriaens,et al.  Deformities in larval gilthead sea bream (Sparus aurata): A qualitative and quantitative analysis using geometric morphometrics , 2007 .

[7]  Norval J. C. Strachan,et al.  Automated measurement of species and length of fish by computer vision , 2006 .

[8]  C Borggaard,et al.  In-line image analysis in the slaughter industry, illustrated by Beef Carcass Classification. , 1996, Meat science.

[9]  J D Tatum,et al.  Video image analysis as a potential grading system for Uruguayan beef carcasses. , 2009, Journal of animal science.

[10]  Anil K. Jain,et al.  Component-Based Representation in Automated Face Recognition , 2013, IEEE Transactions on Information Forensics and Security.

[11]  K. Mardia,et al.  Statistical Shape Analysis , 1998 .

[12]  F. Antonucci,et al.  External shape analyses in Atherina boyeri (Risso, 1810) from different environments , 2012 .

[13]  Francesca Antonucci,et al.  Automated sorting for size, sex and skeletal anomalies of cultured seabass using external shape analysis , 2013 .

[14]  Murat O. Balaban,et al.  Machine Vision Applications to Aquatic Foods: A Review , 2011 .

[15]  B. Heck.  Automated chicken processing: machine vision and water-jet cutting for optimized performance , 2006, IEEE Control Systems.

[16]  S. Shackelford,et al.  On-line prediction of yield grade, longissimus muscle area, preliminary yield grade, adjusted preliminary yield grade, and marbling score using the MARC beef carcass image analysis system. , 2003, Journal of animal science.

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

[18]  M. Kentouri,et al.  Geometric quantification of lordosis effects on body shape in European sea bass, Dicentrarchus labrax (Linnaeus, 1758) , 2006 .

[19]  G. W. Froning,et al.  Mechanical Deboning of Poultry and Fish , 1981 .

[20]  Corrado Costa,et al.  Stocking density and its influence on shape of Senegalese sole adults , 2008, Aquaculture International.

[21]  Ferruh Erdogdu,et al.  Potential use of 3-dimensional scanners for food process modeling , 2009 .

[22]  Martin Kocour,et al.  Heritability estimates for processing and quality traits in common carp (Cyprinus carpio L.) using a molecular pedigree , 2007 .

[23]  Marc Vandeputte,et al.  Genetic parameters of in-vivo prediction of carcass , head and fillet yields by internal ultrasound and 2 D external imagery in large rainbow trout ( Oncorhynchus mykiss ) ☆ , 2013 .

[24]  Federico Pallottino,et al.  RGB Color Calibration for Quantitative Image Analysis: The “3D Thin-Plate Spline” Warping Approach , 2012, Sensors.

[25]  C. P. Schofield,et al.  The use of various live animal measurements to predict carcass and meat quality in two divergent lamb breeds. , 2008, Meat science.

[26]  Corrado Costa,et al.  Skeletal Deformities and Juvenile Quality , 2011 .

[27]  Shiri Gordon,et al.  Automatic landmark detection in uterine cervix images for indexing in a content-retrieval system , 2006, 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2006..

[28]  Hans J. Johnson,et al.  Development of a novel constellation based landmark detection algorithm , 2013, Medical Imaging.

[29]  Thijs Defraeye,et al.  A Geometrical Model Generator for Quasi-Axisymmetric Biological Products , 2013, Food and Bioprocess Technology.

[30]  Bozidar Potocnik,et al.  Automated landmark points detection by using a mixture of approaches: the vole-teeth case , 2015, Signal Image Video Process..

[31]  Lutgarde M. C. Buydens,et al.  Improvement of PLS model transferability by robust wavelength selection , 1998 .

[32]  D. Kendall.  MORPHOMETRIC TOOLS FOR LANDMARK DATA: GEOMETRY AND BIOLOGY , 1994 .

[33]  Da-Wen Sun,et al.  Shape Analysis of Agricultural Products: A Review of Recent Research Advances and Potential Application to Computer Vision , 2011 .

[34]  John Reidar Mathiassen.  Machine Vision for Defect Detection in Fisheries and Fish Processing Applications , 2009 .

[35]  M. Pavlidis,et al.  Sparidae: Biology and aquaculture of gilthead sea bream and other species. , 2011 .

[36]  S. W. Searcy,et al.  FEATURE EXTRACTION FOR A MACHINE-VISION-BASED SHRIMP DEHEADER , 1991 .

[37]  H. K. Mebatsion,et al.  Modelling fruit (micro)structures, why and how? , 2008 .

[38]  F. Rohlf,et al.  Extensions of the Procrustes Method for the Optimal Superimposition of Landmarks , 1990 .

[39]  Griffiths G. Atungulu,et al.  Three-Dimensional Geometric Modeling of Processing Tomatoes , 2011 .

[40]  Karri Muinonen,et al.  Three-dimensional Stochastic Shape Modelling for Potato Tubers , 2006, Potato Research.

[41]  Jérôme Bugeon,et al.  Reprint of: Genetic parameters of in-vivo prediction of carcass, head and fillet yields by internal ultrasound and 2D external imagery in large rainbow trout (Oncorhynchus mykiss) , 2013 .

[42]  Sarah Elton,et al.  Sample size and sampling error in geometric morphometric studies of size and shape , 2007, Zoomorphology.

[43]  Francesca Antonucci,et al.  Genetic and environmental influences on shape variation in the European sea bass (Dicentrarchus labrax) , 2010 .