{"title":"Price look out using web browser for the objects detected in the image","authors":"Sreesh Sangra, Smitha N. Pai","doi":"10.1109/DISCOVER50404.2020.9278110","DOIUrl":null,"url":null,"abstract":"Object Detection and Recognition in the field of computer vision is gaining popularity due to enormous number of applications associated with them. Number of algorithm are developed for object detection and recognition along with localization. In the current paper, a relative comparison of various object detecting algorithm in terms of speed is carried out and “You only look once (YOLO)” is selected for further studies. It is one of the prominent deep learning algorithm associated with object detection at real time. The algorithm scans the image only once to localize and detect multiple objects present in the image. Training is a memory and time intensive process, hence trained weights are directly used for computation. Based on the labels that are obtained from the detected objects their pricing information are obtained. This saves considerable amount of time when pricing information of objects are required in large numbers of multi-object images.","PeriodicalId":131517,"journal":{"name":"2020 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"1945 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DISCOVER50404.2020.9278110","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Object Detection and Recognition in the field of computer vision is gaining popularity due to enormous number of applications associated with them. Number of algorithm are developed for object detection and recognition along with localization. In the current paper, a relative comparison of various object detecting algorithm in terms of speed is carried out and “You only look once (YOLO)” is selected for further studies. It is one of the prominent deep learning algorithm associated with object detection at real time. The algorithm scans the image only once to localize and detect multiple objects present in the image. Training is a memory and time intensive process, hence trained weights are directly used for computation. Based on the labels that are obtained from the detected objects their pricing information are obtained. This saves considerable amount of time when pricing information of objects are required in large numbers of multi-object images.
由于大量的应用与之相关,计算机视觉领域的目标检测和识别越来越受欢迎。在定位过程中,提出了多种目标检测与识别算法。本文对各种目标检测算法在速度方面进行了相对比较,并选择“You only look once (YOLO)”算法进行进一步研究。它是与实时目标检测相关的著名深度学习算法之一。该算法只扫描图像一次,以定位和检测图像中存在的多个物体。训练是一个内存和时间密集的过程,因此训练后的权值直接用于计算。根据从检测到的对象中获得的标签,获得它们的定价信息。当大量的多目标图像需要对象的定价信息时,这节省了大量的时间。