The visual detection of bullet holes in a target

The visual detection of bullet holes in a target image usually can be formulated as a problem of how to exactly locate in an image the isolated and overlapping spots, which are treated as structures without inner detail and texture. In this paper we present a model based on a feedback algorithm to d...

Full description

Saved in:
Bibliographic Details
Main Authors: Shao Yafei, Zhang Li, Wu Guowei
Format: Conference Proceeding
Language:English
Subjects:
Abstracts
Background noise
Feedback
Gaussian noise
Information filtering
Information filters
Inspection
Matched filters
Noise shaping
Wavelet transforms
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The visual detection of bullet holes in a target image usually can be formulated as a problem of how to exactly locate in an image the isolated and overlapping spots, which are treated as structures without inner detail and texture. In this paper we present a model based on a feedback algorithm to deal with this problem and take full consideration of the gradient information and the various size and background. Experiments show it works well and achieves high reliability in real applications.
DOI:10.1109/ICOSP.2000.891669