Abstract

The objective of this study was to investigate the usefulness of pork loin color image features in predicting pork two-tone color grade according to objective L* value. Nine image color features (specifically, the means for two-tone ratios of R, G, B, L*, a*, b*, H, S and I) were extracted from 3 different color spaces (RGB (Red, Green and Blue), CIE LAB (L*: luminance; a*: green to red; b*: blue to yellow) and HIS (Hue, saturation and Intensity)). Color features were extracted from a laboratory-based high-quality camera imaging system. Objective color (CIE L*, a* and b*) was measured using a Minolta Colorimeter, calibrated using both white and black tiles. Boneless, 2.54-cm thick sirloin chops (enhanced, n = 541; non-enhanced, n = 232) were collected. K-means clustering technique was used for grouping pork into two color grades based on Minolta L* value. The image color features were used as predictors for multivariate classification of the samples using machine learning method (Support Vector Machine, SVM). For establishing the model, each data set was separated into training (70%) and testing (30%) sets. Ten-fold cross validation was used to set up the model and test for the best model parameters. The results showed that, for both enhanced and non-enhanced chops, the SVM machine method predicted 100% correct for both grades. Therefore, color image features can be used to correctly classify pork chops by SVM model according to the Minolta L* value.

Keywords:

Color grade, image processing, k-mean, pork sirloin, SVM,

References