AMSC 664 Final Report: Collaborative Image Triage with Humans and Computer Vision
نویسنده
چکیده
We introduce an image triage system which facilitates the collaboration of human analysts, augmented human analysts, and automated technology to efficiently and accurately classify a two-class database of images. The system iteratively allocates images for binary classification among heterogeneous agents according to the Generalized Assignment Problem (GAP) and combines the classification results using the Spectral Meta-Learner (SML). In simulation, we demonstrate that the proposed system achieves significant speed-up over a naive parallel assignment strategy without sacrificing accuracy.
منابع مشابه
Two New Methods of Boundary Correction for Classifying Textural Images
With the growth of technology, supervising systems are increasingly replacing humans in military, transportation, medical, spatial, and other industries. Among these systems are machine vision systems which are based on image processing and analysis. One of the important tasks of image processing is classification of images into desirable categories for the identification of objects or their sp...
متن کاملMetastats 2.0: An improved method and software for analyzing metagenomic data
This document outlines the project proposal for the 2011-2012 AMSC 663/664 course series. The project is to develop Metastats 2.0, a software package analyzing metagenomic data. We propose two major improvements to the Metastats software and the underlying statistical methods. The first extension of Metastats is a mixed-model zero-inflated Gaussian distribution that allows Metastats to account ...
متن کاملSocial Computing for Collaborative Image Understanding
With the advance of the Internet and the increasing accessibility of computing resources, humans and computer systems are now brought together in powerful new ways. In this paper, we propose a humancentered computing framework to harness the essential characteristics of both humans and computers for achieving collaborative image understanding (i.e., training large numbers of inter-related class...
متن کاملارزیابی یک سیستم بینایی ماشین از راه اندازهگیری و تخمین شماری از ویژگیهای فیزیکی پسته
In order to increase the role of machine vision in agricultural research in Iran, especially for measuring physical attributes of seeds, a machine vision system was developed using a computer, a capture card, a video camera and a light box. All equipment was purchased from domestic markets. Computer programs were developed for hardware setup and for image processing applications. The programs p...
متن کاملارزیابی یک سیستم بینایی ماشین از راه اندازهگیری و تخمین شماری از ویژگیهای فیزیکی پسته
In order to increase the role of machine vision in agricultural research in Iran, especially for measuring physical attributes of seeds, a machine vision system was developed using a computer, a capture card, a video camera and a light box. All equipment was purchased from domestic markets. Computer programs were developed for hardware setup and for image processing applications. The programs p...
متن کامل