Title :
A comparative study between different new techniques for object detection on a structured background
Author :
Serhane, Khaled ; Devars, Jean
Author_Institution :
Lab. PARC, Univ. Pierre et Marie Curie, Paris, France
Abstract :
A comparative study between different techniques for object detection on a structured background is considered. A summary of existing works is presented and the concept of a structured background is introduced with an original concept of object detection. We describe the proposed methods and then a comparison was done to choose the method which performed best according to some commonly used criterion in object detection such as processing time, false alarms, missed detection, and the average distance between the theoretic zone and detected zone. The proposed methods have been tested on a variety of synthetic images and yielded promising results
Keywords :
image recognition; object detection; FFT method; algorithms; average distance; cooccurrence matrices; detected zone; false alarms; hit or miss method; missed detection; morphological method; object detection; processing time; structured background; superposition method; synthetic images; theoretic zone; zeros submatrices; Image processing; Layout; Object detection; Robustness; Shape; Testing;
Conference_Titel :
Signal Processing, 1996., 3rd International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-2912-0
DOI :
10.1109/ICSIGP.1996.566243