Magnolia Jackfruit Maturity Classification System Using Color Space Analysis

Earlier studies on jackfruit maturity suggest that the fruit's physiological features are determinant of its maturity state. Similar to other fruits, the Magnolia jackfruit variety also exhibits rind discoloration from greenish to yellowish and is commonly used to visually assess the fruit's quality prior to its harvest. Using color space analysis, this study focuses on the development of a maturity classification system with the Magnolia jackfruit variety. First, the jackfruit will be captured using the proposed device, wherein the image will undergo preprocessing methods such as image resizing and extraction of ROI. Then, the image will be converted into HSV color space to extract the histograms from hue, saturation, and value channels. These histograms will be further concatenated to generate the final feature vector of the input image. Finally, the SVM will identify the maturity state of the jackfruit based on the final feature vector, labeling the jackfruit whether it is mature or immature. In this study, a total of 240 images were utilized for training the system, yielding an 88.33 % accuracy percentage using the proposed hardware device.