Color Image Classification Systems for Poultry Viscera Inspection

A neuro-fuzzy based image classification system that utilizes color-imaging features of poultry viscera in the spectral and spatial domains was developed in this study. Color images of 320 livers and hearts from normal, airsacculitis, cadaver, and septicemia chickens were collected in the poultry process plant. These images in red, green, and blue (RGB) color space were segmented and statistical analysis was performed for feature selection. A neuro-fuzzy system utilizing hybrid paradigms of fuzzy inference system and neural networks was used to enhance the robustness of the classification processes. The accuracy for separation of normal from abnormal livers ranged 87.5 to 92.5%, when two classes of validation data were used. For classification of normal and abnormal chicken hearts, the accuracies were 92.5 to 97.5%. When neuro-fuzzy models were employed to separate chicken livers into normal, airsacculitis, and cadaver, the accuracy was 88.3% for the training data and 83.3% for the validation data. Combining features of chicken liver and heart, a generalized neuro-fuzzy model was designed to classify poultry viscera into four classes (normal, airsacculitis, cadaver, and septicemia). The classification accuracy was 86.3% for training and 82.5% for validation.