Recognition a Hand Drawn Chemical Structure Diagrams Using the Discrete B-Spline Wavelet Transform

Abstract

Chemical structures are a suitable way to represent the chemical equations perfectly in 2D space. But sometimes a hands drawn structures have some complicated when one take them as a document image and then recognized it to its full meaning to be accepted in machine datamining techniques so far. The wavelets with Spline are verysteady and commonly symmetric or anti-symmetric.B-Spline has the preferableparataxisproperties over all different types of wavelets in order L-1.In this paper a unified framework was built to include the organic and inorganic expressions. A suitable way was presented to classify hand drawn chemical structures using the B-Spline wavelet transform as a tool for image classification. Inempiricalvaluationone can show that an enforcement of thismethodexceed the open source system available.The proposed framework achieved in Test-5 with 84.7% data accuracy for recognition the handwrittenchemical expression database. Also with 77.8% classification accuracy using discrete B-Spline wavelet transforms.