Egg weight prediction and egg size classification using image processing and machine learning

Measuring the weight and judging the size of eggs are important in egg grading. This paper presents image processing and machine learning techniques for predicting chicken egg weight and classifying egg size number from a single egg image. A brown chicken egg is candled and its image is taken as an input to the algorithm. The egg image region is segmented from the background. Thirteen features are computed from geometric parameters acquired from the egg region. The weight of the egg is predicted and the size number is classified using the 13 features. The experiment shows that using the linear regression technique to predict the weight yielded the correlation coefficient of 0.9915, and the experiment using the Support Vector Machine (SVM) technique for classifying the size number yielded 87.58% accuracy.