Abstract

Introduction

In this work we develop a system, that will help to perceive separate regions in the different images. I mean the development of distinguished object-retrieval and processing automated system in images with the help of contour analysis methods. About these methods I’ll tell you a little bit later. As a data domain we use the cars photos. Objects, that we are interested in, are the regions with the number plate.
The aim of this system is to find the contours of all the objects in the image using the contour analysis methods and after that with the help of certain characteristics to determine the number plate region. Then distinguished region will be send to the symbol clarification system.
This system is assigned for tracing cars, which exceed speed and for cars that are wanted. We investigate the car photos, which were taken during car traffic with the help of special photosensors. These sensors work not all the time, only both with speed control sensors, which are situated in the different places of the road. The photo is taken only if speed sensors fix the rate exceeding.

Short description of the methods

As I have said, we use the contour analysis methods, exactly, the traditional active contour method and the active contour method without edges.
First method is a two-step snake algorithm whose energy functional is minimized by the dynamic programming method. It is more robust to local minima because it finds the solution by searching the entire energy space. To reduce the complexity of the minimization process, the watershed transformation and a coarse-to-fine strategy are used. The classical snakes methods are based on the gradient.
The difference between traditional method and the second one is that the active contour without edges can detect objects whose boundaries are not necessarily defined by gradient. The evolving active contour stops on the desired boundary. The stopping term is related to a particular segmentation of the image. The initial curve can be anywhere in the image, and interior contours are automatically detected.

References

• 1. Kaas M., Witkin A., Terzopoulos D. Snakes: Active Contour Models. // Int. Journal of Computer Vision. - 1987, N1, -p.312-331.
• 2. D.J. Williams and M. Shah, "A Fast Algorithm for Active Contours and Curvature Estimation," Computer Vision, Graphics, and Image Processing, vol. 55, pp. 14-26, 1992.