Classification Of Guarantee Fruit Murability Based on HSV Image With K-Nearest Neighbor

Abstract

Guava bol is one of the fruits from Indonesia that is favored by many Indonesian people. The guava itself has a soft and dense flesh texture compared to water guava. The guava itself has a pink color if it is raw but if the guava is ripe it will be dark red. From a glance, when viewed from human vision, it is very easy to distinguish between them, but from most people it is still difficult to distinguish which guava is ripe, half-ripe and unripe guava because of differences in opinion from one human eye to another. Based on these problems, researchers have developed a system that is able to detect the maturity level of guava fruit by utilizing the Hue Saturation Value (HSV) feature extraction with K-Nearest Neighbor (KNN). The data used in this study were 465 datasets which were divided into 324 training data and 141 test data. The data had classes, namely ripe, half-cooked, and raw. The data is then classified using the K-Nearest Neighbor method by calculating the closest distance with a value of K = 3. From this study resulted in an accuracy of 97.16%.

Object Detection and Recognition Techniques Based on Digital Image Processing and Traditional Machine Learning for Fruit and Vegetable Harvesting Robots: An Overview and Review

“…Since machine learning can derive laws from sample data that can hardly be summarized by theoretical analysis, many researchers have conducted extensive and in-depth research on techniques for object detection and recognition of fruits and vegetables based on the K-means clustering algorithm [68][69][70][71][72][73][74][75], SVM algorithm [54,57,69,73,[76][77][78][79][80][81][82][83][84], KNN clustering algorithm [36,[85][86][87][88][89][90][91], AdaBoost algorithm [62,[92][93][94][95][96][97][98][99], decision tree algorithm [100][101][102][103][104][105][106][107], and Bayesian algorithm [108]…”

“…Techniques for object detection and recognition of fruits and vegetables based on the KNN clustering algorithm are more widely used. Based on the KNN clustering algorithm, Tan et al [36], Astuti et al [90], Suban et al [89], Sarimole and Rosiana [85], and Sarimole and Fadillah [86] detected and recognized the ripeness of blueberries, oil palms, papayas, betel nuts, and pomegranates, respectively.…”

“…(2) Image segmentation and classifiers based on traditional machine learning, such as K-means clustering algorithm-based methods [68][69][70][71][72][73][74][75], SVM (Support Vector Machine) algorithm-based methods [54,57,69,73,[76][77][78][79][80][81][82][83][84], KNN (K Nearest Neighbor) clustering algorithm-based methods [36,[85][86][87][88][89][90][91], AdaBoost (Adaptive Boosting) algorithm-based methods [62,[92][93][94][95][96][97][98][99], decision tree algorithm-based methods [100][101][102][103][104][105][106][107], and Bayesian algorithmbased methods [108]…”

Twitter Data Analysis and Text Normalization in Collecting Standard Word

“…The goal was to prepare data or text obtained from unstructured social media into good data and could be easily processed for further processing (Jimenez-Marquez et al, 2019;Shu et al, 2017;Iskandar & Marjuki, 2022). In the preprocessing technique there were several processes such as parsing, case folding, tokenizing, stemming, filtering/stop words, normalization (Chen et al, 2020;Baccouche et al, 2020;Sarimole & Fadillah, 2022). In the text normalization stage, it was very important to be able to help parse Indonesian language that could understand lexical meaning well, performance in processing structural and unstructured words could be improved if the preprocessing stages were carried out properly, especially normalization for unstructured words (Izonin et al, 2022;Basan et al, 2022).…”