Method for the Recovery of Images in Databases of Rice Grains from Visual Content

Abstract

This paper presents a method for detecting and identifying defects in polished rice grains from their scanned image using an expert system. The sample used is designed to contain specimens with the most common defects. Digital image processing techniques were used to identify different types of visible defects in rice grains that affect the quality of the sample. The proposed method has advantages over manual identification such as reduced analysis times, repeatability of results, eliminates subjectivity in identification, records and stores information, uses easily accessible equipment and has a relatively low cost.