RICE QUALITY ANALYSIS USING DIGITAL IMAGE PROCESSING

Abstract: Our nation relies on grains for agricultural revenue, with rice being a primary crop. The quality of milled rice determines its commercial viability, impacted by contaminants like stones and weed seeds. While grain testing is partly automated, human labor remains essential. Ensuring food grain quality affects supply chain profits, especially varietal purity, though the process is time-consuming. Advanced techniques like GLCM and CNN aid in quality assessment and contaminant detection, streamlining the labor-intensive process for farmers.

Keywords: GLCM, support vector machine, image processing, Convolutional Neural Networks, quality assessment.