A pattern recognition based Holographic Graph Neuron for Persian alphabet recognition

In this article a Vector Symbolic Architectures is purposed to implement a hierarchical Graph Neuron for memorizing patterns of Persian/Arabic isolated characters. The main challenge in this topic is using Vector Symbolic representation as a one-layered design for neural network while maintaining the previously reported properties and performance characteristics of hierarchical Graph Neuron. The designed architecture is robust to noise and enables a linear (with respect to the number of stored entries) time search for an arbitrary sub-pattern. The proposed method was implemented on a standard Persian database and the obtained results showed the ability of (not necessarily better) Graph neuron to recognize the Persian isolated character patterns.

[1]  Lianwen Jin,et al.  Radical aggregation network for few-shot offline handwritten Chinese character recognition , 2019, Pattern Recognit. Lett..

[2]  Tony A. Plate,et al.  Holographic reduced representations , 1995, IEEE Trans. Neural Networks.

[3]  Raymond W. Ptucha,et al.  Intelligent character recognition using fully convolutional neural networks , 2019, Pattern Recognit..

[4]  Ross W. Gayler.  Vector Symbolic Architectures answer Jackendoff's challenges for cognitive neuroscience , 2004, ArXiv.

[5]  Simon D. Levy,et al.  Vector Symbolic Architectures: A New Building Material for Artificial General Intelligence , 2008, AGI.

[6]  Suraj Bajracharya,et al.  Learning Behavior Hierarchies via High-Dimensional Sensor Projection , 2013, AAAI Workshop: Learning Rich Representations from Low-Level Sensors.

[7]  Abdorreza Alavi Gharahbagh,et al.  Gradient-based approach to offline text-independent Persian writer identification , 2018, IET Biom..

[8]  Stephen I. Gallant,et al.  Representing Objects, Relations, and Sequences , 2013, Neural Computation.

[9]  Ismael Ahmad Jannoud.  Automatic Arabic Hand Written Text Recognition System , 2007 .

[10]  Branislav M. Popovic,et al.  Generalized chirp-like polyphase sequences with optimum correlation properties , 1992, IEEE Trans. Inf. Theory.

[11]  Pentti Kanerva,et al.  Hyperdimensional Computing: An Introduction to Computing in Distributed Representation with High-Dimensional Random Vectors , 2009, Cognitive Computation.

[12]  Levan Shugliashvili,et al.  On Georgian Handwritten Character Recognition , 2018 .

[13]  Thomas Burger,et al.  A Dempster-Shafer Theory based combination of handwriting recognition systems with multiple rejection strategies , 2015, Pattern Recognit..

[14]  Yakkaldevi Ashok,et al.  A LITERATURE REVIEW ON HAND WRITTEN CHARACTER RECOGNITION , 2013 .

[15]  Abdelhamid Djeffal,et al.  Puzzle based system for improving Arabic handwriting recognition , 2016, Eng. Appl. Artif. Intell..

[16]  Y. Ahmet Sekercioglu,et al.  Holographic Graph Neuron: A Bioinspired Architecture for Pattern Processing , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[17]  M. S. Farag.  HandwrittenText Recognition System for Automatic Reading of Historical Arabic Manuscripts , 2012 .

[18]  Anang Hudaya Muhamad Amin,et al.  One Shot Associative Memory Method for Distorted Pattern Recognition , 2007, Australian Conference on Artificial Intelligence.

[19]  Raid Saabni,et al.  Fast Key-Word Searching via Embedding and Active-DTW , 2011, 2011 International Conference on Document Analysis and Recognition.

[20]  Abdel Belaïd,et al.  Structural Features Extraction for Handwritten Arabic Personal Names Recognition , 2012, 2012 International Conference on Frontiers in Handwriting Recognition.