Grading/ Sorting Of Lemons By Applying Pattern Recognition Techniques On Color Images
Each fruit changes its color in its life span; including stages not ripe, semi ripped, completely ripped or at the end
rotten. Hence, we can grade/sort the fruits by processing its color images and then applying pattern recognition techniques on
those images. In general, various parameters for grading of a fruit are its’ size, ripeness, sweetness, longetivity,
diseased/rotten. This paper discusses the research work for automated grading of lemons using multiple pattern recognition
techniques applied on color images of lemons. This research is carried out on 150 Lemon fruits of 5 different breeds,
collected from varied geographical locations in Vidarbha Region of Maharashtra. System designed can automatically
classify a lemon given its color image of 640 × 480 pixel resolution taken inside a special box designed with 430 lux
intensity light inside it, by a digital camera. The various pattern recognition techniques used are Nearest Prototype
Classification, Edited Nearest Neighbor and Linear Regression.
Keywords- Pattern Recognition, Color Image Processing, and Automated Fruit sorting.