GLCM and K-Means based Chicken Gender Classification

Machine learning plays an influential role in the agricultural sector. Intelligent machines can perform automatic management tasks in various fields. In recent years, the poultry farm management field also utilizes this concept. In poultry farms, the machine learning algorithms are employed for different purposes such as weather monitoring and control, gender classification, disease detection in the earlier stage because human resources requirement in extensive poultry farm management is one of the struggling tasks for farmers. To maintain the perfect mating ratio between cocks and hens, gender identification is one of the important things. In a way, gender (cock and hen) features are not similar and may vary from one breed to another. Poultry farming experts manually identify chicken gender based on features like feather color, shapes, comb appearance, beak shape, body-color, and height, to maintain the ratio of cock and hen. In this research work, the K-means clustering algorithm for grouping, Gray Level Co-occurrence Matrix algorithm (GLCM), is used to extract the feature from cock and hen images, and extracted features are to train and test using the Support Vector Machine (SVM) classifier. One thousand chicken images are used for training and testing the classifier. 80% of images are used for training, and 20% are used to test the classifier. This work achieved 95.8% of accuracy in classifying the gender.