Agricultural product grading is helpful in assessing the quality of a product and classifying it into categories. Presently, the grade analysis procedures involve the manual analysis of grains which is highly subjective and is influenced by human factors and the working environment. Thus, determining the quality of grains is a big challenge. In this paper, we have proposed a system that determines the quality of grains using image processing techniques. A variety of approaches were utilized to automate the screening process through machine vision approaches. Initially, the grain samples run on the conveyor belt, and then random images of grains are captured by the camera. The image processing algorithm is applied to the grain samples through MATLAB. Quality analysis of rice grains is determined by morphological features of rice grains. Various standards and procedures are then used to determine grades for the sample under test. The process of grading helps farmers to get the value for their produce, particularly rice, depending upon the results of quality inspections. Deep learning and machine learning models involving image processing has been tried in this paper to observe the computational accuracy