Machine Learning for Auto Segregation of Fruits Classification Based Logistic Support Vector Regression

Abstract

In agriculture, automation is an important attribute for improving and enhancing the quality, expansion and efficiency of the products produced. The quality of the rating has been reduced as the product classification has improved. Sorting is one of the most important challenges in the industry, so need a reliable segregation system that allows us to package our products easily and automatically. Features used in this process include pre-processing, entry, division, extraction, classification, and detection. Existing approaches is not accurately finding the fruit result and take more time take to finding the segregation part. To overcome the issue in this work proposed the method Logistic Support Vector Regression (LSVR) is efficient classified the fruits images. Initially start the process include the image dataset, and first step is preprocessing. In this stage, remove unwanted areas of images, to check the imbalanced values and eliminating the image defects. Next step segmenting the images form the stage of preproceeing filtered images, it helps to splitting the images. Extracting the features based on the images weightages and evaluating for classification. Then using the training and testing images for classification, it includes segregating or identifying color, texture, shape, and defects. Finally, classification using LSVR process improves images quality and assists the industry in segregating products. The use of images in the automated packaging process improves the quality of the results in a better way than ever before. Use this approach and smart logistics to keep track of the transaction process. The purpose of this work is primarily to minimize or eliminate waste.