This paper presents an off-line handwritten, isolated character recognizer based on the artificial immune system (AIS) and qualitative rules-based system (QRBS). AIS acts as an optimizer. It selects the best candidates for training. Each candidate is used from several character features previously selected based on some structural and statistical techniques. QRBS works as a qualitative recognizer system. It utilizes qualitative rules to recognize characters. It handles both imprecision and uncertainty in handwriting during the training and classification phases that make some characters unreadable and may decrease the accuracy of the overall process. Experiments are conducted on the MNIST and English letter databases. Comparisons with other recent approaches using the same database indicate that this approach is effective.
AlexandrinoJ.L. and FilhoE.C.D.B.C., Investigation of a new artificial immune system model applied to pattern recognition, in: Sixth International Conference on Hybrid Intelligent Systems, HIS'06, IEEE, (2006), 16-16.
2.
AminA., Off-line arabic character recognition: The state of the art, Pattern Recognition31(5) (1998), 517-530.
3.
AzmiR., PishgooB., NoroziN., KoohzadiM. and BaesiF., A hybrid GA and SA algorithms for feature selection in recognition of hand-printed farsi characters, in: IEEE International Conference on Intelligent Computing and Intelligent Systems (ICIS), IEEE 3 (2010), 384-387.
4.
BabuU.R., VenkateswarluY. and ChinthaA.K., Handwritten digit recognition using K-nearest neighbour classifier, in: World Congress on Computing and Communication Technologies (WCCCT), IEEE, (2014), 60-65.
5.
KacemS.B.H., BorgiA. and TaginaM., Approximate reasoning based on Linguistic modifiers in a learning system, in: ICSOFT (2) (2010), 431-437.
6.
BorgiA., BazinJ.M. and AkdagH., Supervised classification by automatic rules generation, in: The Fourth World Congress on Expert Systems, Application of Advanced Information Technologies, Mexico, (1998), 561-568.
7.
CaiJ. and LiuZ., Integration of structural and statistical information for unconstrained handwritten numeral recognition, IEEE Transactions on Pattern Analysis And Machine Intelligence21(3) (1999), 263-270.
8.
CardosoA. and WichertA., Handwritten digit recognition using biologically inspired features, Neurocomputing99 (2013), 575-580.
9.
CashG.L. and HatamianM., Optical character recognition by the method of moments, Computer Vision, Graphics and Image Processing39(3) (1987), 291-310.
10.
ChenJ., ZhaoS. and ZhangY., Hierarchical covering algorithm, Tsinghua Science and Technology1 (2014), 008.
11.
CherietM., Strategies for visual arabic handwriting recognition: Issues and case study, in: 9th International Symposium on Signal Processing and Its Applications, ISSPA2007, IEEE, (2007), 1-6.
12.
CheungK.W., YeungD.Y. and ChinR.T., A bayesian framework for deformable pattern recognition with application to handwritten character recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence20(12) (1998), 1382-1388.
13.
ChikhM.A., SaidiM. and SettoutiN., Diagnosis of diabetes diseases using an artificial immune recognition system2 (AIRS2) with fuzzy k-nearest neighbor, Journal of Medical Systems36(5) (2012), 2721-2729.
14.
ChimY.C., KassimA.A. and IbrahimY., Character recognition using statistical moments, Image and Vision Computing17(3) (1999), 299-307.
15.
DeS.B., SabourinR., BortolozziF. and SuenC.Y., Foreground and background information in an HMM-based method for recognition of isolated characters and numeral strings, in: Ninth International Workshop on Frontiers in Handwriting Recognition, IWFHR-9 2004, IEEE, (2004), 371-376.
16.
De CastroL.N., Fundamentals of natural computing: an overview, Physics of Life Reviews4(1) (2007), 1-36.
17.
De StefanoC., FontanellaF., MarroccoC. and Scotto di FrecaA., A GA-based feature selection approach with an application to handwritten character recognition, Pattern Recognition Letters35 (2014), 130-141.
18.
DevijverP.A. and KittlerJ., Pattern recognition: A statistical approach, London: Prentice-Hall, 1982.
19.
FarmerJ.D., PackardN.H. and PerelsonA.S., The immune system, adaptation and machine learning, Physica D: Nonlinear Phenomena22(1) (1986), 187-204.
20.
GauravD.D., Feature extraction for character recognition on http://www.mathworks.com/matlabcentral/fileexchange/2462 4-feature-extraction-for-character-recognition, 2009.
21.
GauravD.D. and RameshR., A feature extraction technique based on character geometry for character recognition, arXiv preprint arXiv: 1202.3884, 2012.
22.
HanmandluM., Murali MohanK.R., ChakrabortyS., GoyalS. and ChoudhuryD.R., Unconstrained handwritten character recognition based on fuzzy logic, Pattern Recognition36(3) (2003), 603-623.
23.
HiranoT., OkadaY. and YodF., Structural character recognition using simulated annealing, in: Proceedings of the Fourth International Conference on Document Analysis and Recognition, IEEE 2 (1997), 507-510.
24.
HussainS., LiuS.C. and BasuA., Improved margin multi-class classification using dendritic neurons with morphological learning, in: 2014 IEEE International Symposium on Circuits and Systems (ISCAS), IEEE, (2014), 2640-2643.
25.
ImpedovoS., ManginiF.M. and PirloG., A new adaptive zoning technique for handwritten digit recognition, in: Image Analysis and Processing-ICIAP 2013, Springer Berlin Heidelberg, (2013), 91-100.
26.
ImpedovoD. and PirloG., Zoning methods for handwritten character recognition: A survey, Pattern Recognition47(3) (2014), 969-981.
27.
JagtapV.N. and MishraS.K., Fast efficient artificial neural network for handwritten digit recognition, International Journal of Computer Science and Information Technologies5(2) (2014), 2302-2306.
28.
JiangW. and ChungF.L., A trace ratio maximization approach to multiple kernel-based dimensionality reduction, Neural Networks49 (2014), 96-106.
29.
JouC. and LeeH.C., Handwritten numeral recognition based on simplified structural classification and fuzzy memberships, Expert Systems with Applications36(9) (2009), 11858-11863.
30.
KimuraF. and ShridharM., Segmentation-recognition algorithm for zip code field recognition, Machine Vision and Applications5(3) (1992), 199-210.
31.
LajishV.L., Handwritten character recognition using perceptual fuzzy-zoning and class modular neural networks, in: IIT'07, 4th International Conference on Innovations in Information Technology, IEEE, (2007), 188-192.
32.
LecunY., On http://yann.lecun.com/exdb/mnist/, 1998.
33.
LiuC.L., NakashimaK., SakoH. and FujisawaH., Handwritten digit recognition: Benchmarking of state-of-the-art techniques, Pattern Recognition36(10) (2003), 2271-2285.
34.
LiuC.L., NakashimaK., SakoH. and FujisawaH., Handwritten digit recognition: Investigation of normalization and feature extraction techniques, Pattern Recognition37(2) (2004), 265-279.
35.
MontazerG.A., SaremiH.Q. and KhatibiV., A neuro-fuzzy inference engine for farsi numeral characters recognition, Expert Systems with Applications37(9) (2010), 6327-6337.
36.
MotodaH. and LiuH., Feature selection, extraction and construction, Communication of IICM (Institute of Information and Computing Machinery, Taiwan)5 (2002), 67-72.
37.
MurthyO.R. and HanmandluM., Interactive fuzzy model based recognition of handwritten characters, Journal of Pattern Recognition Research2 (2011), 154-165.
38.
NebtiS. and BoukerramA., Handwritten characters recognition based on nature-inspired computing and neuro-evolution, Applied Intelligence38(2) (2013), 146-159.
39.
PalU., JayadevanR. and SharmaN., Handwriting recognition in indian regional scripts: A survey of offline techniques, ACM Transactions on Asian Language Information Processing (TALIP)11(1) (2012), 1.
40.
PerelsonA.S. and OsterG.F., Theoretical studies of clonal selection: Minimal antibody repertoire size and reliability of self-non-self discrimination, Journal of Theoretical Biology81(4) (1979), 645-670.
41.
RoyA., DasN., SarkarR., BasuS., KunduM. and NasipuriM., Region selection in handwritten character recognition using artificial bee colony optimization, in: 2012 Third International Conference on Emerging Applications of Information Technology (EAIT), IEEE, (2012), 183-186.
42.
RoyA., DasN., SarkarR., BasuS., KunduM. and NasipuriM., An axiomatic fuzzy set theory based feature selection methodology for handwritten numeral recognition, in: ICT and Critical Infrastructure: Proceedings of the 48th Annual Convention of Computer Society, Springer International Publishing, IndiaI (Jan 2014), 133-140.
43.
SahaS. and SomT., Handwritten character recognition using fuzzy membership function, IJETSE International Journal of Emerging Technologies in Sciences and Engineering5(2) (2011).
44.
ŞahanS., PolatK., KodazH. and GüneşS., A new hybrid method based on fuzzy-artificial immune system and k-nn algorithm for breast cancer diagnosis, Computers in Biology and Medicine37(3) (2007), 415-423.
45.
SeridiH., AkdagH., MansouriR. and NemissiM., Approximate reasoning in supervised classification systems, Journal of Advanced Computational Intelligence and Intelligent Informatics10(4) (2006), 586-593.
46.
SeridiH., AkdagH. and MeddourA., Une approche qualitative sur le traitement de l'incertain: Application au système expert, in: Science and Technologie, Algerie, (19) (Jun 2003), 13-19.
47.
ShahA.D., A genetic learning method for OCR in english language, 2014 PISER Journal, PISER 12, 02(2) (2014), 241-247.
48.
SiddharthK.S., DhirR. and RaniR., Handwritten gurmukhi numeral recognition using different feature sets, International Journal on Computer Applications (IJCA)28(2) (2011), 20-24.
49.
SouzaS. and AbeJ.M., Handwritten numerical character recognition based on paraconsistent artificial neural networks, in: Recent Developments in Computational Collective Intelligence, Springer International Publishing, (2014), 93-102.
50.
TimmisJ., Artificial immune systems: A novel data analysis technique inspired by the immune network theory, Ph D Dissertation, Department of Computer Science University of Wales, (Aug 2000).
51.
TrierØ.D., JainA.K. and TaxtT., Feature extraction methods for character recognition-a survey, Pattern Recognition29(4) (1996), 641-662.
52.
TongX.J., ZengS., SangN. and ZengL.H., Hand-written numeral recognition based on fuzzy $C$-means algorithm, in: 2010 Ninth International Symposium on Distributed Computing and Applications to Business Engineering and Science (DCABES), IEEE, (Aug 2010), 528-532.
53.
WatkinsA.B. and BoggessL.C., A resource limited artificial immune classifier, in: Proceedings of Congress on Evolutionary Computation, Part of the 2002 IEEE World Congress on Computational Intelligence held in Honolulu, HI, USA, (12-17 May 2002), 926-931.
54.
YangY., Application of artificial immune system in handwritten russian uppercase character recognition, in: 2011 International Conference on Computer Science and Service System (CSSS), IEEE, (Jun 2011), 238-241.
55.
ZhaoW. and DavisC.E., A modified artificial immune system based pattern recognition approach: An application to clinical diagnostics, Artificial Intelligence in Medicine52(1) (2011), 1-9.
56.
ZhuC.H., ShiC.Y., WangJ.P. and XuX.B., Study of off-line handwritten Chinese character recognition based on dynamic pruned FSVMs, in: International Conference on Electrical and Control Engineering (ICECE), IEEE, (2011), 395-398.
