Elizabeth Nurmiyati Tamatjita, Rouly Doharma Sihite
{"title":"Banana Ripeness Classification using HSV Colour Space and Nearest Centroid Classifier","authors":"Elizabeth Nurmiyati Tamatjita, Rouly Doharma Sihite","doi":"10.52731/iee.v8.i1.687","DOIUrl":null,"url":null,"abstract":"Banana is a common fruit which is found throughout Southeast Asia and are beneficial both as delicacy and as a dessert which is good for health. Although quite common and easy to obtain, many people today find it difficult to identify the correct ripeness stage of banana, especially when purchasing from traditional vendors, where varying degree of ripeness are available. This research sought for a possibility to classify banana ripeness by its peel colour with HSV colour space as the feature and classified using Nearest Centroid Classifier (NCC). ‘Ambon Lumut’, ‘Kepok’ and ‘Raja’ bananas are used as examples for the research as they are among the most common types of banana available for many use in Indonesia, and its ripeness is divided into 4 classes according to different usage of the banana: unripe, almost ripe, ripe, and overripe. Photographic images of ‘Ambon Lumut’, ‘Kepok’ and ‘Raja’ bananas are used as training and test data. The experiment is conducted using cleaned images which have the background re-moved, and this experiment also resulting in 73.33% recognition. The recognition results for each class respectively are: Green = 93.33%; Almost Ripe=80%; Ripe=66.67% and Overripe=53.33%.","PeriodicalId":416504,"journal":{"name":"Information Engineering Express","volume":"33 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Information Engineering Express","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.52731/iee.v8.i1.687","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
Abstract
Banana is a common fruit which is found throughout Southeast Asia and are beneficial both as delicacy and as a dessert which is good for health. Although quite common and easy to obtain, many people today find it difficult to identify the correct ripeness stage of banana, especially when purchasing from traditional vendors, where varying degree of ripeness are available. This research sought for a possibility to classify banana ripeness by its peel colour with HSV colour space as the feature and classified using Nearest Centroid Classifier (NCC). ‘Ambon Lumut’, ‘Kepok’ and ‘Raja’ bananas are used as examples for the research as they are among the most common types of banana available for many use in Indonesia, and its ripeness is divided into 4 classes according to different usage of the banana: unripe, almost ripe, ripe, and overripe. Photographic images of ‘Ambon Lumut’, ‘Kepok’ and ‘Raja’ bananas are used as training and test data. The experiment is conducted using cleaned images which have the background re-moved, and this experiment also resulting in 73.33% recognition. The recognition results for each class respectively are: Green = 93.33%; Almost Ripe=80%; Ripe=66.67% and Overripe=53.33%.