Pattern Recognition

Generally, pattern recognition refers to a process of inputting stimulating (pattern) information and matching with the information in long-term memory, then recognizing the category which the stimulation belongs to. Therefore, pattern recognition depends on people’s knowledge and experience. Without involving individual’s knowledge and experience, people cannot understand the meanings of the stimulating information pattern inputted, then neither possible to recognize the patterns, which means to recognize the objects. The process which a person distinguishes a pattern he percepts with others and identifies what it is means pattern recognition. Current cognitive psychology has proposed such theoretical models or hypothesis as the Theory of Template (Model of Template Matching), the Theory of Prototype (Model of Prototype Matching), Distinctive Features models, and The computational Approaches.

Theories of Patter Recognition

Template Matching Theory 

As the simplest theoretical hypothesis in pattern recognition, the Theory of Template mainly considers that people store various mini copies of exterior patterns formed in the past in the long-term memory. These copies, named templates, correspond with the exterior stimulation patterns one by one. When a simulation acts on people’s sense organs, the simulating information is first coded, compared and matched with pattern stored in brain, then identified as one certain pattern in brain which matches best. thus the pattern recognition effect is produced, otherwise the stimulation cannot be distinguished and recognized. Because every template relates to a certain meanings and some other information, the pattern recognized then will be explained and processed in other ways. 

According to the Theory of Template, people have to store an appropriate template before recognize a pattern. Although pre-processing course is added, these templates are still numerous, not only bringing heavy burden to memory but also leading pattern recognition less flexible and stiffer. The Theory of Template doesn’t entirely explain the process of human pattern recognition, but the template and template matching cannot be entirely denied. 

Prototype Model 

The Theory of Prototype, also named the Theory of Prototype Matching, has the outstanding characteristic that memory is not storing templates which matches one-by-one with outside patterns but prototypes. The prototype, rather than an inside copy of certain pattern, is considered as inside attribute of one kind of objects, which means abstractive characteristics of all individuals in one certain type or category. This theory reveals basic features of one type of objects. For instances, people know various kinds of airplanes, but a long cylinder with two wings can be the prototype of airplane. Therefore, according to the Theory of Prototype, in the process of pattern recognition, outside simulation only needs to be compared with the prototype, and the sense to objects comes from the matching between input information and prototype. Once outside simulating information matches best with a certain prototype in brain, the information can be ranged in the category of that prototype and recognized. In a certain extent the template matching is covered in the Theory of Prototype, which appears more flexible and more elastic. However, this model also has some drawbacks, only having up-down processing but no bottom-up processing, which is sometimes more important for the prototype matching in human perceptional process. 

Distinctive Features Model 

The distinctive-features models state that we make discrimination among stimuli on the basis of small number of characteristics. These characteristics that differentiate one stimulus from another are called distinctive features. Most of the research in this area focuses on our ability to recognize letters and number. Distinctive-features models are consistent with both psychological and physiological research. People required a relatively long time to decide whether some letters are different from one another when those letters share a large number of critical features (Gibson, 1969). Research by Garner (1979) confirmed that decision speed depends upon the number of shared distinctive features. Unique combinations of features do not produce unique activity in a single feature map, and therefore cannot pop out. Instead, they require additional processing in order to be detected. First, attentional resources must be used to bring the various independent feature maps into register with respect to a master map of locations. This master map of locations will indicate what combinations of features coexist at each location in the map. Second, a “spotlight” of attention is used to scan the master map of locations in search of a unique object. Because this attentional spotlight can only process a portion of the master map at any given time, and because it must be scanned from location to location on the master map, it takes longer for unique combinations of features to be found. Furthermore, the search of the master map will become longer and longer as more of its locations are filled, explaining why the latency to detect unique feature combinations is affected by the number of distractors present. 

Some basic problems of the distinctive-features approach: 

A theory of pattern recognition should not simply list the features found in a stimulus; it must also describe the physical relationship among those features (Bruce, 1988). 

The distinctive-features models were constructed to explain the relatively simple recognition of letters. However, the shapes that occur in nature are much more complex. How can people recognize more complex kinds of stimuli found in everyday life? 

The Computational Approach 

The computational approach contains components of both prototype approach and distinctive-features approach. One of computational approach to pattern recognition was developed by Irving Biederman (1987, 1990) that explored the categorization of 3-D shapes in a theory called recognition-by-components. The basic assumption of this theory is that a given view of an object can be represented as an arrangement of simple 3-D shapes. Biederman calls these 3-D shapes geons, a name that stands for geometrical ions. Like letters of the alphabet. Geons can be combined to form something meaningful. 

The recognition-by-components model has not yet been extensively tested. Some early reports on normal humans and on people with specific visual deficits are compatible with the model (Banks & Krajicek, 1991). However, other research by Cave and Kosslyin (1993) asked observer to identify sketches of objects that were either broken into “natural” parts (consistent with geons) or broken into “unnatural” parts.  The observers were equally quick and accurate in the two conditions. These result suggest that people encode the overall shape first and analyze the parts afterwards—the reverse of the recognition-by-components model.