• Uttara Gogate
• Aishwarya Ghorpade
• Nisha Solanki
• Shweta Raut

In this paper we introduce an approach for shape recognition on the basis of contour analysis for traffic signs. Our project describes the theoretical bases of contour analysis and aspects of its practical application for shape recognition. In our project we introduce an approach for shape matching that uses contour segment matching for shape similarity computation. Each contour segment is represented by rotation and scale invariant feature vector. The similarity of two shapes is determined by matching their contour segments using CA(contour analysis) complex-valued coding. The most significant feature of our project is (i) introduction of new features extraction technique for contour segment. (ii) the impressive robustness of method. A local contour based feature extraction method is designed for 2D shapes using ICF(inter-correlation function) and ACF(auto-correlation function). ICF is a measure of similarity of two contours and it is invariant to transposition, scaling, rotation and starting point shift. The advantage of our proposed algorithm is invariant to rotation, transposition and scaling. It can be use in various applications like CBIR, OCR.

Shape Recognition, Contour Analysis, ICF, ACF, Complex valued coding, C#.net, Traffic signs .

"Robust Shape Recognition Using Contour Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.500-505, April-2019, Available :http://www.jetir.org/papers/JETIR1904168.pdf

"Robust Shape Recognition Using Contour Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp500-505, April-2019, Available at : http://www.jetir.org/papers/JETIR1904168.pdf