Jackfruit Maturity Classification Using Uniform Local Binary Pattern and Support Vector Machine

According to the Philippine National Standards (PNS), mature jackfruit are defined by their spines being separated far apart and well-developed. Such maturity feature is present in many local cultivars in the Philippines, specifically within the Magnolia jackfruit variety. We developed a maturity classification system based on the Uniform Local Binary Pattern (ULBP) operator as the texture descriptor and the Support Vector Machine (SVM) as the classification model. Initially, the Region of Interest (ROI) was extracted from the captured image to emphasize the jackfruit’s rind. Then, the ULBP operator was used to detect and capture local texture patterns exhibited by the spines. The Hue histogram was also extracted to incorporate the rind’s discoloration. Finally, the extracted features were concatenated to generate the final feature vector. A total of 240 images were utilized to train the system for jackfruit maturity classification. The proposed methodology yielded an accuracy of 93.33% for Magnolia’s immature and mature classes.