ABSTRACT
This chapter describes string grammers for pattern description/analysis. It describes syntactic pattern recognition procedures, including parsing, error-correcting parsing, and sentence-to-sentence clustering techniques. The chapter describes two-dimensional grammars for image patterns. In machine recognition of image patterns and shapes, features are extracted and subject to statistical analysis; or primitives are selected and subject to syntax analysis. The former is called the statistical or decision-theoretic approach, and the latter is called the syntactic or structural approach, The statistical or decision-theoretic approach is the traditional approach to pattern recognition that has been studied since the 1960s. Depending on the image pattern, different segmentation or decomposition processes can be applied. Once the primitives are extracted, they are represented symbolically using a string or a sentence, or other pattern representation languages.
