Comparative analysis of Online/Offline Gregg Shorthand Recognition using CANN and BP

Gregg shorthand is a form of stenography that was invented by John Robert Gregg in 1888. Like cursive longhand, it is completely based on elliptical figures and lines that bisect them. Gregg shorthand is the most popular form of pen stenography in the United States and its Spanish adaptation is fairly popular in Latin America. With the invention of dictation machines, shorthand machines, and the practice of executives writing their own letters on their personal computers, the use of shorthand has gradually declined in the business and reporting world. However, Gregg shorthand is still in use today. The need to process documents on paper by computer has led to an area of research that may be referred to as Document Image Understanding (DIU).The goal of DIU system is to convert a raster image representation of a document. For Example, A hand written Gregg shorthand character or word is converted into an appropriate Symbolic Character in a computer (It may be a scanned character or online written character).Thus it involves many disciplines of computer science including image processing, pattern recognition, natural language processing, artificial intelligence, neural networks and database system. The ultimate goal of this paper is to recognize hand written Gregg shorthand character and analyse it with CANN (Competitive Artificial Neural Network) and BP (Back Propagation) method.