Digital image analysis as a tool to quantify gaping and morphology in smoked salmon slices

Gaping in salmon fillets refers to the appearance of slits in the muscle. This is unsightly and leads to downgrading and hence economical loss, particularly for salmon smoke houses. Present day manual and semi automatic methods for quantifying gaping are labour intensive and subjective. This study presents an automated and objective image analysis method for quantifying gaping in smoked salmon slices. The slices are first photographed in a photobox and then analysed by the fully automated image analysis method. The method has four main steps: (1) pre-processing, (2) segmentation of slices from the background, (3) labelling of each slice, (4) identification of gaps within the slices (holes), (5) identification of gaps on the perifery (notches) and (6) quantification of gaps and notches. The results obtained by the automatic image analysis are visually convincing and there is a strong correlation with manual quantification of gaps (r = 0.83, p-value < 0.05). The automatic image analysis method can easily be extended to also include morphological parameters as shape, red and white muscle area, myocommata and myotome area. Interestingly, the automatic image analysis demonstrated that gaps are strongly associated with white, and not red, muscle tissue.

[1]  Gunilla Borgefors,et al.  Distance transformations in digital images , 1986, Comput. Vis. Graph. Image Process..

[2]  E Misimi,et al.  Computer vision-based sorting of Atlantic salmon (Salmo salar) fillets according to their color level. , 2007, Journal of food science.

[3]  R. L. Olsen,et al.  Protein expression and enzymatic activities in normal and soft textured Atlantic salmon (Salmo salar) muscle , 2011 .

[4]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[5]  Fredrik Manne,et al.  Rapid estimation of fat content in salmon fillets by colour image analysis , 2007 .

[6]  T. Skåra,et al.  Effects of cold smoking procedures and raw material characteristics on product yield and quality parameters of cold smoked Atlantic salmon (Salmo salar L.) fillets , 2004 .

[7]  Michael J. Crawley,et al.  The R book , 2022 .

[8]  Casimir A. Kulikowski,et al.  A Graph-Based Approach for Image Segmentation , 2008, ISVC.

[9]  S. Stella,et al.  Shelf‐life of vacuum packed Alaskan, Scottish and Norwegian cold‐smoked salmon available on the Italian market , 2009 .

[10]  B. Lunestad,et al.  Quality of cold smoked salmon collected in one French hypermarket during a period of 1 year , 2004 .

[11]  B. Roth,et al.  Stunning, pre slaughter and filleting conditions of Atlantic salmon and subsequent effect on flesh quality on fresh and smoked fillets , 2009 .

[12]  G. Parisi,et al.  Fish welfare and quality as affected by pre-slaughter and slaughter management , 2004, Aquaculture International.

[13]  Marit Aursand,et al.  Use of NMR in fish processing optimization: a review of recent progress , 2012, Magnetic resonance in chemistry : MRC.

[14]  M. Balaban,et al.  Quantification of gaping, bruising, and blood spots in salmon fillets using image analysis. , 2011, Journal of food science.

[15]  Antti Kause,et al.  Automated image analysis as a tool to quantify the colour and composition of rainbow trout (Oncorhynchus mykiss W.) cutlets , 2006 .

[16]  I. Johnston,et al.  A novel tensile test method to assess texture and gaping in salmon fillets. , 2010, Journal of food science.

[17]  Kari Ruohonen,et al.  Texture, gaping and colour of fresh and frozen Atlantic salmon flesh as affected by pre-slaughter iso-eugenol or CO2 anaesthesia , 2004 .

[18]  P. Schmid.  Segmentation of digitized dermatoscopic images by two-dimensional color clustering , 1999, IEEE Transactions on Medical Imaging.

[19]  K. Ruohonen,et al.  Muscle fibre growth and quality in fish , 2006 .

[20]  Thomassen,et al.  Fillet gaping in farmed Atlantic salmon (Salmo Salar) , 1994 .

[21]  Anthony Hoogs,et al.  Object Boundary Detection in Images using a Semantic Ontology , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[22]  Franco Pedreschi,et al.  Color of Salmon Fillets By Computer Vision and Sensory Panel , 2010 .

[23]  J. Lavety,et al.  The connective tissues of fish. , 2007 .

[24]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[25]  Graham W. Horgan,et al.  Image analysis for the biological sciences , 1997 .

[26]  Grigory V. Merkin,et al.  Effect of pre-slaughter procedures on stress responses and some quality parameters in sea-farmed rainbow trout (Oncorhynchus mykiss) , 2010 .

[27]  L. Frøyland,et al.  Interactions between ice storage time, collagen composition, gaping and textural properties in farmed salmon muscle harvested at different times of the year , 2004 .

[28]  R. S. Rasmussen.  Quality of farmed salmonids with emphasis on proximate composition, yield and sensory characteristics , 2001 .