Performance evaluation of object detection algorithms
- 25 June 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 965-969 vol.3
- https://doi.org/10.1109/icpr.2002.1048198
Abstract
The continuous development of object detection algorithms is ushering in the need for evaluation tools to quantify algorithm performance. In this paper a set of seven metrics are proposed for quantifying different aspects of a detection algorithm's performance. The strengths and weaknesses of these metrics are described. They are implemented in the Video Performance Evaluation Resource (ViPER) system and will be used to evaluate algorithms for detecting text, faces, moving people and vehicles. Results for running two previous text-detection algorithms on a common data set are presented.Keywords
This publication has 7 references indexed in Scilit:
- An Automatic Performance Evaluation Protocol for Video Text Detection AlgorithmsIEEE Transactions on Circuits and Systems for Video Technology, 2004
- Locating uniform-colored text in video framesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Tracking humans from a moving platformPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Tools and techniques for video performance evaluationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A statistical method for 3D object detection applied to faces and carsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Detecting faces in images: a surveyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Automatic text detection and tracking in digital videoIEEE Transactions on Image Processing, 2000