Basic techniques and symbol-level recognition — An overview

This is an overview paper that describes methods used in graphics recognition from the stage of the initial scanned image to that of the graphics features. The objective is to give context and background to the papers in this section — and, because it is introductory material — to the rest of the papers in this book.Methods are described under the categories of: pixel-level processing, line-level processing, and feature detection. In the pixel-level processing section, thresholding, noise reduction, and compression are discussed. In the line-level processing section, thinning, chain coding, region detection, and polygonalization are discussed. And in the final section on feature detection, critical point detection, line and curve fitting, and shape recognition are discussed.