Explore chapters and articles related to this topic
Sensor and data fusion in traffic management
Published in Lawrence A. Klein, ITS Sensors and Architectures for Traffic Management and Connected Vehicles, 2017
The syntactic methods, although listed here under physical models, appear again as part of pattern recognition, a subset of information theoretic techniques. Syntactic pattern recognition is applied when the significant information in a pattern is not merely the presence or absence of numerical values, but rather the interconnections of features that yield its structure. Pattern similarity is assessed by quantifying and extracting structural information utilizing, for example, the syntax of a formally defined language. Typically, syntactic approaches formulate hierarchical descriptions of complex patterns from simpler subpatterns or primitives.
Syntactic Image Pattern Recognition
Published in Edward R. Dougherty, Digital Image Processing Methods, 2020
A straightforward approach to syntactic pattern recognition is to construct a grammar for each class of patterns. A parser can then be constructed based on the grammar G, for each pattern class i. The parser will recognize a sentence only if it is in L(G,). For the chromosome example in Section II. A, a parser can be constructed for the medium, submedium, and acrocentric chromosome grammars. The recognition procedure can then be constructed as in Fig. 8.
Image Understanding
Published in Vipin Tyagi, Understanding Digital Image Processing, 2018
Unlike the previous approaches, the syntactic pattern recognition utilizes the structure of the patterns. Instead of carrying an analysis based strictly on quantitative characteristics of the pattern, we emphasize the interrelationships between the primitives, the components which compare the pattern. Patterns that are usually subject to syntactic pattern recognition are character recognition, fingerprint recognition, chromosome recognition, etc.
Automatic reservoir model identification using syntactic pattern recognition in well test interpretation
Published in Petroleum Science and Technology, 2022
Sihan Yang, Qiguo Liu, Xiaoping Li, Youjie Xu
Overall, we have obtained the following conclusions: Well test interpretation model recognition method based on syntactic pattern recognition shows high applicability and scalability. The method completes model identification tasks hierarchically, complex and diverse models can be identified and corresponding flow regime division method can be retained.By setting different initial windows and structural information judgment thresholds, there is no need to extract feature points in advance. Finite state machine is still an important tool in syntactic pattern recognition. Through curve tracing and primitive conversion, the primitive sequence diagram can be obtained to get the corresponding model.The interpretation model obtained by syntactic pattern recognition is only based on the morphology of the curve. It is necessary to further verify the correctness of model. TDS technology is precisely based on the characteristic points of each flow regime. Combined with TDS technology, the correctness of some output models can be verified.It is recommended to build a responsive primitive and model library based on this method. It is very suitable as options in well test analysis software to determine correct well test interpretation model and divide flow regimes. Which improve the efficiency of well test interpretation.