Imaging Reality and Abstraction an Exploration of Natural and Symbolic Patterns

Understanding visual symbols is a strictly human skill, as opposed to comprehending natural scenes—which is an essential survival skill, common to many species. As an illustration of the natural vs. symbolic dichotomy, selective features are computed for differentiating a satellite photograph from a map of the same geographical region. Images of physical scenes /objects are currently captured in all parts of the electromagnetic spectrum. Symbols, whether produced by man or machine, are almost always imaged in the visible range. Although natural and symbolic images differ in many ways, there is no universal set of differentiating characteristics. With respect to the traditional branches of pattern recognition, it is tempting to suggest that statistical, neural network and genetic/evolutionary pattern recognition methods are eminently suitable for images of scenes and simple symbols, whereas structural and syntactic approaches are best for more complex, composite

[1]  Lawrence O'Gorman.  PRIMITIVES CHAIN CODE , 1988 .

[2]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Richard Bellman,et al.  Adaptive Control Processes: A Guided Tour , 1961, The Mathematical Gazette.

[4]  G. Punzi,et al.  Information and Perception of Meaningful Patterns , 2013, PloS one.

[5]  Dustin Stokes,et al.  The dominance of the visual , 2014 .

[6]  George Nagy,et al.  Disruptive developments in document recognition , 2016, Pattern Recognit. Lett..

[7]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[8]  Elizabeth Warren,et al.  Young Children's Ability to Generalise the Pattern Rule for Growing Patterns. , 2005 .

[9]  George Nagy,et al.  Cracking, damage and fracture in four dimensions , 2007 .

[10]  Muhammed Jassem Al-Muhammed,et al.  On the Fly Access Request Authentication: Two-Layer Password-Based Access Control Systems for Securing Information , 2018 .

[11]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[12]  J A Anderson,et al.  Search for hidden chambers in the pyramids. , 1970, Science.

[13]  M. Mitchelmore,et al.  Awareness of pattern and structure in early mathematical development , 2009 .

[14]  Alexandra Branzan Albu,et al.  Symbol spotting for architectural drawings: state-of-the-art and new industry-driven developments , 2019, IPSJ Transactions on Computer Vision and Applications.

[15]  Hermiae Ammonius,et al.  On Aristotle Categories , 1991 .

[16]  Josep Lladós,et al.  Symbol recognition using graphs , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[17]  Tom Drummond,et al.  Fusing points and lines for high performance tracking , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[18]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[19]  Benoit Gaüzère,et al.  Graph Neural Network for Symbol Detection on Document Images , 2019, 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW).

[20]  O. Firschein,et al.  Syntactic pattern recognition and applications , 1983, Proceedings of the IEEE.

[21]  Camille Couprie,et al.  Learning Hierarchical Features for Scene Labeling , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Kaspar Riesen,et al.  Towards the unification of structural and statistical pattern recognition , 2012, Pattern Recognit. Lett..

[23]  David B. Searls,et al.  Document Image Analysis Using Logic-Grammar-Based Syntactic Pattern Recognition , 1992 .

[24]  Razvan Pascanu,et al.  Relational inductive biases, deep learning, and graph networks , 2018, ArXiv.

[25]  M. Mattson.  Superior pattern processing is the essence of the evolved human brain , 2014, Front. Neurosci..