Syntactic and Structural Pattern Recognition

Thirty years ago pattern recognition was dominated by the learning machine concept: that one could automate the process of going from the raw data to a classifier. The derivation of numerical features from the input image was not considered an important step. One could present all possible features to a program which in turn could find which ones would be useful for pattern recognition. In spite of significant improvements in statistical inference techniques, progress was slow. It became clear that feature derivation was a very complex process that could not be automated and that features could be symbolic as well as numerical. Furthennore the spatial relationship amongst features might be important. It appeared that pattern recognition might resemble language analysis since features could play the role of symbols strung together to form a word. This led. to the genesis of syntactic pattern recognition, pioneered in the middle and late 1960's by Russel Kirsch, Robert Ledley, Nararimhan, and Allan Shaw. However the thorough investigation of the area was left to King-Sun Fu and his students who, until his untimely death, produced most of the significant papers in this area. One of these papers (syntactic recognition of fingerprints) received the distinction of being selected as the best paper published that year in the IEEE Transaction on Computers. Therefore syntactic pattern recognition has a long history of active research and has been used in industrial applications.

I. Matching and Parsing I.- A string correction method based on the context-dependent similarity.- An error-correcting parser for a context-free language based on the context-dependent similarity.- Ordered structural matching.- II. Matching and Parsing II.- A parsing algorithm for weighted grammars and substring recognition.- Computing the minimum error distance of graphs in 0 (n3) time with precedence graph grammars.- A unified view on tree metrics.- III. Applications I.- Problems in recognition of drawings.- Application of structural pattern recognition in histopathology.- Applications of multidimensional search to structural feature identification.- IV. Grammatical Inference and Clustering.- Learning from examples in sequences and grammatical inference.- An efficient algorithm for the inference of circuit-free automata.- Voronoi trees and clustering problems.- V. Image Understanding.- Hough-space decomposition for polyhedral scene analysis.- Running efficiently arc consistency.- Smith: an efficient model-based two dimensional shape matching technique.- Training and model generation for a syntactic curve network parser.- VI. Applications II.- Knowledge-based computer recognition of speech.- Computers viewing artists at work.- Face recognition from range data by structural analysis.- Cryptosystems for picture languages.- VII. Hybrid Approaches I.- Hybrid approaches.- An AI-structural approach to edge detection.- Building hierarchies-an algorithmic approach.- VIII. Hybrid Approaches II.- Combining logic based and syntactic techniques: a powerful approach.- A syntactic approach to planning.- IX. Working Sessions.- Working Group A: 2D and 3D Image Understanding.- Working Group B: Waveform and Speech Recognition.- Working Group C: Hybrid Techniques.- Working Group D: Models and Inference.- X. Panel.- Artificial Intelligence Versus Syntactic Techniques: Theoretical and Practical Issues.- XL List of Participants.