Detection and matching of object using proposed signature - Emerging Trends in Image Processing, Computer Vision, and Pattern Recognition - page 491

CHAPTER 38
Detection and matching of
object using proposed
signature
Hany A. Elsalamony Mathematics Department, Faculty of Science, Helwan University, Cairo, Egypt
Abstract
Most of algorithms of object detection and classifications are only locating regions in the image, whether
it is within a template-sliding mask or interested region blobs. However, such regions may be ambigu-
ous, especially when the object of interest is very small, unclear, or anything else. This chapter presents
proposed algorithm for automatic object detection and matching based on its own proposed signature
using morphological segmentation tools. Moreover, the algorithm tries to match the objects; neither
among object's blobs nor among regions of interest; but among the constructed proposed objects' sig-
natures. In the matching process, speeded up to robust features (SURF) method has been presented to
make a comparison on the experimental results. The performance has been tested 120 from a wide vari-
ety of unlike objects; it has been achieved 100% in the case of constructing object signatures, also it has
been achieved 96% of right matching whereas SURF has achieved 85% for all test objects.
Keywords
Object detection and matching
Signature
SURF
Segmentation
1 Introduction
The object detection plays an important role in the area of computer vision research. Nowadays,
many of its applications require the locations of objects in images. In fact, there are two closely
related definitions, object presence detection, and object localization. The determinations of one
or more of an object class are presented (at any location or scale) in an image, which means
of an object's presence detection or image classification, and can be suitable for image retrieval