On Visual Semantic Algebra (VSA): A Denotational Mathematical Structure for Modeling and Manipulating Visual Objects and Patterns

A new form of denotational mathematics known as Visual Semantic Algebra (VSA) is presented for abstract visual object and architecture manipulations. A set of cognitive theories for pattern recognition is explored such as cognitive principles of visual perception and basic mechanisms of object and pattern recognition. The cognitive process of pattern recognition is rigorously modeled using VSA and Real-Time Process Algebra (RTPA), which reveals the fundamental mechanisms of natural pattern recognition by the brain. Case studies on VSA in pattern recognition are presented to demonstrate VAS’ expressive power for algebraic manipulations of visual objects. VSA can be applied not only in machinable visual and spatial reasoning, but also in computational intelligence as a powerful man-machine language for representing and manipulating visual objects and patterns. On the basis of VSA, computational intelligent systems such as robots and cognitive computers may process and inference visual and image objects rigorously and efficiently. DOI: 10.4018/jssci.2009062501 IGI PUBLISHING This paper appears in the publication, International Journal of Software Science and Computational Intelligence, Volume 1, Issue 4 edited by Yingxu Wang © 2009, IGI Global 701 E. Chocolate Avenue, Hershey PA 17033-1240, USA Tel: 717/533-8845; Fax 717/533-8661; URL-http://www.igi-global.com ITJ 5373 2 International Journal of Software Science and Computational Intelligence, 1(4), 1-16, October-December 2009 Copyright © 2009, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited. recognition, particularly how the natural intelligence processes visual objects and patterns (Wang, 2008d), as well as their denotational mathematical models (Wang, 2008a, 2008b). The gestalt (holistic) principles of visual perception were developed in Germany based on experiments conducted in the 1920s and 1930s (Gray, 1994; Westen, 1999). Five gestalt principles for object and pattern perception were elicited (Kanizsa, 1979), such as similarity, proximity, good continuation, simplicity, closure, and background contrast. The gestalt principles reveal a set of important natural tendencies of human visual perception. Another set of seven cognitive informatics principles of visual object perception is identified in (Wang, 2009c) known as association, symmetry, perfection, abstraction, categorization, analysis, and appreciation, which are used in perception and identification of human figures, physical objects, abstract structure, mathematics entities, and nature. A variety of theories and approaches are proposed for visual object and pattern recognition. Marr proposed a method for object recognition in the algorithmic approach known as the computational method (Marr, 1982). Biederman developed a method for object recognition in the analytic approach called recognition by components (Biedeman, 1987). Various methods and technologies are developed for pattern recognition in the fields of cognitive psychology (payne and Wenger, 1998; Reed, 1972; Wilson and Keil, 2001), computer science (Bender, 2000; bow, 1992; Miclet, 1986; Storer, 2002), and robotics (Horn, 1986; Murry et al., 1993). Wang presents a cognitive theory of visual information processing as well as the unified framework of human visual processing systems (Wang, 2009c) in the development of cognitive informatics – a formal theory for explaining the natural and computational intelligence (Wang, 2002a, 2003, 2007b; Wang and Kinsner, 2006; Wang et al., 2002, 2008b, 2009a, 2009b). A set of denotational mathematics (Wang, 2006, 2008a), such as concept algebra (Wang, 2008c), system algebra (Wang, 2008d), Real-Time Process Algebra (RTPA) (Wang, 2002b, 2007a, 2008b), and granular algebra (Wang, 2009d), are created in order to rigorously manipulate complex mental processes and computational intelligence. This article presents the cognitive process of pattern recognition and the denotational mathematical means known as Visual Semantic Algebra (VSA). The cognitive informatics theories for pattern recognition are explored such as cognitive principles of visual perception and basic mechanisms of object and pattern recognition. A generic denotational mathematical means, VSA, is developed to manipulate basic geometric shapes and figures, as well as their compositions by a set of algebraic operations. A number of case studies are provided to explain the expressive power of VSA and its applications. COGNITIVE INFORMATICS THEORIES FOR PATTERN RECOGNITION It is recognized that the brain tends to perform inference and reasoning using abstract semantic objects rather than direct visual (diagram-based) objects (Coaen et al., 1994; Wang, 2009c). This is evidenced by that the brain cannot carry out concrete image inference in Short-Term Memory (STM) without looking at them in external media such as figures or pictures on article, because this cognitive process requires too large memory beyond the capacity of STM in the brain basic Mechanisms of Object Recognition Definition 1. Object recognition is a special type of pattern recognition where the patterns are frequently used 2-D shapes, 3-D solid figures, and their compositions. 14 more pages are available in the full version of this document, which may be purchased using the "Add to Cart" button on the product's webpage: www.igi-global.com/article/visual-semantic-algebra-

[1]  H. Bastian Sensation and Perception.—I , 1869, Nature.

[2]  A. Einstein Relativity: The Special and the General Theory , 2015 .

[3]  Carla H. Lagorio,et al.  Psychology , 1929, Nature.

[4]  U. Neisser Cognitive Psychology: Classic Edition , 1967 .

[5]  Stephen K. Reed,et al.  Pattern recognition and categorization , 1972 .

[6]  G. Kanizsa,et al.  Organization in Vision: Essays on Gestalt Perception , 1979 .

[7]  S. Coren,et al.  In Sensation and perception , 1979 .

[8]  Laurent Miclet,et al.  Structural Methods in Pattern Recognition , 1986 .

[9]  I. Biederman Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

[10]  O. G. Selfridge,et al.  Pandemonium: a paradigm for learning , 1988 .

[11]  Y. J. Tejwani,et al.  Robot vision , 1989, IEEE International Symposium on Circuits and Systems,.

[12]  Sing-Tze Bow,et al.  Pattern recognition and image preprocessing , 1992 .

[13]  Richard M. Murray,et al.  A Mathematical Introduction to Robotic Manipulation , 1994 .

[14]  Edward A. Bender,et al.  Mathematical methods in artificial intelligence , 1996 .

[15]  D. Westen Psychology: Mind, brain, & culture, 2nd ed. , 1999 .

[16]  Robert A. Wilson,et al.  Book Reviews: The MIT Encyclopedia of the Cognitive Sciences , 2000, CL.

[17]  Refractor Vision , 2000, The Lancet.

[18]  J. Storer An Introduction to Data Structures and Algorithms , 2002, Birkhäuser Boston.

[19]  Yingxu Wang,et al.  The Real-Time Process Algebra (RTPA) , 2002, Ann. Softw. Eng..

[20]  Yingxu Wang On Cognitive Informatics , 2003 .

[21]  Shushma Patel,et al.  A layered reference model of the brain (LRMB) , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[22]  Yingxu Wang,et al.  Editorial Recent Advances in Cognitive Informatics , 2006, IEEE Trans. Syst. Man Cybern. Syst..

[23]  Yingxu Wang,et al.  Cognitive Informatics and Contemporary Mathematics for Knowledge Manipulation , 2006, RSKT.

[24]  Yingxu Wang,et al.  The OAR Model of Neural Informatics for Internal Knowledge Representation in the Brain , 2007, Int. J. Cogn. Informatics Nat. Intell..

[25]  Du Zhang,et al.  Advances in Machine Learning Applications in Software Engineering , 2007 .

[26]  Yingxu Wang,et al.  The Theoretical Framework of Cognitive Informatics , 2007, Int. J. Cogn. Informatics Nat. Intell..

[27]  Martin Shepperd,et al.  Applying Rule Induction in Software Prediction , 2007 .

[28]  Yingxu Wang,et al.  Software Engineering Foundations: A Software Science Perspective , 2007 .

[29]  Yingxu Wang The cognitive processes of analysis and synthesis in formal inferences , 2008, 2008 7th IEEE International Conference on Cognitive Informatics.

[30]  Yingxu Wang,et al.  RTPA: A Denotational Mathematics for Manipulating Intelligent and Computational Behaviors , 2008, Int. J. Cogn. Informatics Nat. Intell..

[31]  Yingxu Wang,et al.  On Concept Algebra: A Denotational Mathematical Structure for Knowledge and Software Modeling , 2008, Int. J. Cogn. Informatics Nat. Intell..

[32]  Yingxu Wang,et al.  On System Algebra: A Denotational Mathematical Structure for Abstract System Modeling , 2008, Int. J. Cogn. Informatics Nat. Intell..

[33]  Yingxu Wang,et al.  On Contemporary Denotational Mathematics for Computational Intelligence , 2008, Trans. Comput. Sci..

[34]  Yingxu Wang,et al.  On Cognitive Computing , 2009, Int. J. Softw. Sci. Comput. Intell..

[35]  Witold Pedrycz,et al.  A Doctrine of Cognitive Informatics (CI) , 2009, Fundam. Informaticae.

[36]  Yingxu Wang Formal Descriptions of Cognitive Processes of Perceptions on Spatiality, Time, and Motion , 2009, Int. J. Cogn. Informatics Nat. Intell..

[37]  Yingxu Wang,et al.  Granular algebra for modeling granular systems and granular computing , 2009, 2009 8th IEEE International Conference on Cognitive Informatics.

[38]  Yingxu Wang,et al.  On Abstract Intelligence: Toward a Unifying Theory of Natural, Artificial, Machinable, and Computational Intelligence , 2009, Int. J. Softw. Sci. Comput. Intell..

[39]  Yingxu Wang,et al.  The Cognitive Informatics Theory and Mathematical Models of Visual Information Processing in the Brain , 2009, Int. J. Cogn. Informatics Nat. Intell..

[40]  Slawomir Zadrozny,et al.  Protoforms of Linguistic Database Summaries as a Human Consistent Tool for Using Natural Language in Data Mining , 2009, Int. J. Softw. Sci. Comput. Intell..

[41]  Juan A. Barceló An Automated Approach to Historical and Social Explanation , 2009 .

[42]  Yingxu Wang,et al.  Contemporary Cybernetics and Its Facets of Cognitive Informatics and Computational Intelligence , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[43]  Eduardo Alonso,et al.  Computational Neuroscience for Advancing Artificial Intelligence: Models, Methods and Applications , 2010 .

[44]  Tarek Helmy,et al.  Adaptive Ensemble Multi-Agent Based Intrusion Detection Model , 2010 .

[45]  Eduardo Alonso,et al.  Computational models of learning and beyond: Symmetries of associative learning , 2010 .

[46]  Yingxu Wang,et al.  The Formal Design Model of a Real-Time Operating System (RTOS+): Static and Dynamic Behaviors , 2010, Int. J. Softw. Sci. Comput. Intell..

[47]  D. Wegner,et al.  Psychology (2nd ed.) , 2011 .

[48]  H. Piaggio,et al.  Space and Time , 1925 .