{"title":"Lessons Learnt with Traditional Image Processing Techniques for Mushroom Detection","authors":"Sándor Tarsoly, A. I. Károly, P. Galambos","doi":"10.1109/ICCC202255925.2022.9922849","DOIUrl":null,"url":null,"abstract":"Mushrooms destined for the fresh market are harvested exclusively by hand. As a result, the mushroom industry is highly dependent on human labor. About half of the operating costs of mushroom farms are labor costs, which mainly consist of harvesting costs. Rising wages and stricter consideration of working hours and working conditions also increase manual labor problems. For these reasons, there is a significant need for automating mushroom picking. One of the first steps in automation is the detection of individual fungi, for which several approaches can be considered. Among these approaches, traditional image processing such as thresholding, noise reduction, morphological techniques, and segmentation methods are discussed through real-world examples. This study shows that the investigated classical approaches cannot fully meet the demands of morphological diversity. It is concluded that better results can be achieved by using soft computing technologies such as deep neural networks.","PeriodicalId":397323,"journal":{"name":"2022 IEEE 10th Jubilee International Conference on Computational Cybernetics and Cyber-Medical Systems (ICCC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE 10th Jubilee International Conference on Computational Cybernetics and Cyber-Medical Systems (ICCC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCC202255925.2022.9922849","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
Mushrooms destined for the fresh market are harvested exclusively by hand. As a result, the mushroom industry is highly dependent on human labor. About half of the operating costs of mushroom farms are labor costs, which mainly consist of harvesting costs. Rising wages and stricter consideration of working hours and working conditions also increase manual labor problems. For these reasons, there is a significant need for automating mushroom picking. One of the first steps in automation is the detection of individual fungi, for which several approaches can be considered. Among these approaches, traditional image processing such as thresholding, noise reduction, morphological techniques, and segmentation methods are discussed through real-world examples. This study shows that the investigated classical approaches cannot fully meet the demands of morphological diversity. It is concluded that better results can be achieved by using soft computing technologies such as deep neural networks.