Pattern Recognition

Pattern recognition is a child of modern technology; electronics and computers in particular have inspired research and made it possible to develop the subject in a way which would have been impossible otherwise. It is a rapidly growing research field which began to flourish in the 1960s and which is beginning to produce commercial devices. Significant developments have been made, both in the theory and practical engineering of the subject, but there is evidence of a schism developing between these two approaches. Practical machines have usually been designed on an ad hoc basis, with little use being made of advanced theory. It is difficult to provide a rigorous mathematical treatment of many problems pertinent to a practical situation. This is due, in part at least, to a conceptual rift between theory and practice. The mathematics of optimal systems is well developed, whereas pragmatists are more concerned with vaguer ideas of reasonable and sufficient. In some situations, the quest for optimality can constrain research and retard practical progress. This can occur, for example, if too narrow a view is taken of "optimal": the accuracy of a system may be optimal whereas its speed, cost, or physical size may be grossly suboptimal. The objective of this book is to present a glimpse of the pragmatic approach to pattern recognition; there already exist a number of excellent texts describing theoretical developments.

Methods and Machines.- 1 Setting the Scene.- 1.1. Sets.- 1.2. Motivation.- 1.3. Component Problems of Pattern Recognition.- 1.4. Relation between Pattern Recognition and Other Subjects.- 1.5. Lessons of This Book.- 2 A Review of Optical Pattern Recognition Techniques.- 2.1. Introduction.- 2.2. Nonholographic Optical Correlation.- 2.3. Holographic Cross-Correlation.- 2.4. Speech Recognition by Optical Correlation.- 2.5. Automatic Inspection.- 2.6. Normalized Cross-Correlation.- 2.7. Optoelectronic Transduction.- 2.8. Linear Discriminant Implementation.- 2.9. Numerical Discriminants.- 2.10. Transformations.- 2.11. Normalization and Segmentation.- 2.12. Feature Detection.- 2.13. Sequential Recognition Techniques.- 2.14. Interactive Pattern Recognition.- 2.15. Concluding Comment.- References.- 3 Pattern Recognition with Networks of Memory Elements.- 3.1. Introduction.- 3.2. The Random-Access Memory as a Learning Element.- 3.3. Combinational Networks.- 3.4. Sequential Learning Automata.- 3.5. The Computation of Some Global Properties.- 3.6. Other Forms of Feedback.- References.- 4 Classification and Data Analysis in Vector Spaces.- 4.1. Statement of the Problem.- 4.2. Classification Methods.- 4.3. Additional Data Analysis Techniques.- 4.4. Implementation in Hardware.- 4.5. Current Research.- 4.6. Appendix: Classifier Design Methods.- References.- 5 Decision Trees, Tables, and Lattices.- 5.1. Introduction.- 5.2. Feature Design for Decision Trees.- 5.3. The Design of Decision Trees.- 5.4. Decision Tables.- 5.5. Table Conversion Methods.- 5.6. Table-Splitting Methods.- 5.7. The Common Subtree Problem.- 5.8. Equivalence of Subtables.- 5.9. Table to Lattice Conversion.- 5.10. The Development of Decision Rules.- 5.11. Choosing the Set of Rules.- References.- 6 Parallel Processing Techniques.- 6.1. Introduction.- 6.2. Brief Survey of Proposed Parallel Processors.- 6.3. The CLIP Processors.- 6.4. Programming a CLIP Array.- 6.5. Processing Larger Image Areas.- 6.6. Future Trends.- References.- 7 Digital Image Processing.- 7.1. Introduction.- 7.2. Motivations for Image Processing.- 7.3. Image Processing Disciplines.- 7.4. Image Processing Equipment.- 7.5. Conclusions.- References.- 8 Cases in Scene Analysis.- 8.1. Introduction.- 8.2. Scope of Scene Analysis.- 8.3. Line Finding.- 8.4. Polyhedral Vision.- 8.5. Region Finding.- References.- Applications.- 9 The Control of a Printed Circuit Board Drilling Machine by Visual Feedback.- 9.1. Introduction.- 9.2. The Structure of a Practical Visually Controlled Machine.- 9.3. The Application of Visual Control to Drilling Printed Circuit Boards.- 9.4. Picture Processing Operators.- 9.5. Performance and Conclusions.- References.- 10 Industrial Sensory Devices.- 10.1. Introduction.- 10.2. Potential Areas of Application.- 10.3. Sensory Modalities.- 10.4. Applications.- 10.5. Constraints.- References.- 11 Image Analysis of Macro molecular Structures.- 11.1. Introduction.- 11.2. Two-Dimensional Image Filtering.- 11.3. Rotational Image Filtering.- 11.4. Image Simulation of Three-Dimensional Structures.- 11.5. Three-Dimensional Image Reconstruction.- References.- 12 Computer-Assisted Measurement in the Cytogenetic Laboratory.- 12.1. Introduction.- 12.2. The Laboratory Workload.- 12.3. Automatic Karyotyping.- 12.4. Classification.- 12.5. Counting and Finding Cells.- 12.6. Accurate Measurement.- References.- 13 Vehicle Sounds and Recognition.- 13.1. Introduction.- 13.2. Planning and Preprocessing.- 13.3. Feature Extraction.- 13.4. Moment Feature Space.- 13.5. Nonsinusoidal Transforms.- 13.5. Homomorphic Filtering.- 13.7. Conclusions.- References.- 14 Current Problems in Automatic Speech Recognition.- 14.1. Preliminaries.- 14.2. Isolated Word Recognizers.- 14.3. Machine Perception of Continuous Speech.- 14.4. Conclusions.- References.- 15 Pattern Recognition in Electroencephalography.- 15.1. Introduction and General Description of the Human Electroencephalogram.- 15.2. Clinical and Research Applications.- 15.3. The Motive for Using Pattern Recognition in Electroencephalography.- 15.4. Feature Extraction.- 15.5. Stepwise Discriminant Analysis.- 15.6. Pattern Recognition Applications.- 15.7. Current Research.- References.- 16 Scene Analysis: Some Basics.- 16.1. What Is Scene Analysis? — Robotics Problem.- 16.2. Views of Pattern Recognition — Summary.- 16.3. Why Scene Analysis Is Not Trivial.- 16.4. Examples of Work in the Area of Scene Analysis.- 16.5. Some Conclusions.- References.- 17 Social Aspects of Pattern Recognition.- 17.1. Introduction.- 17.2. The Case Against Pattern Recognition.- 17.3. In Defense of Pattern Recognition.- References.