In the computer vision, pattern recognition is a wide area to study. Handwritten digit recognition is an important research topic of pattern recognition. There are various ways to write any digit. To recognize it is a challenging task. This paper shows the effective results of handwritten digit recognition on well-known, reliable handwritten digit database using CNN (Convolutional Neural Network). In the current scenario, the convolution neural network (CNN) shows a remarkable success in most of the computer vision and recognition tasks. CNN is well-known feed-forward architecture important for object recognition. We have tested our work on MNIST database. In this paper we analyzed the accuracy using CNN depending on different parameters like Number of hidden layers, Number of CNN layers, Number of neurons in each layer, Number of iterations and on the optimizer that we are using optimize the result. Aim of this paper is to know how the accuracy varies due to changes in these parameters. Increasing or decreasing the number of parameters leads to change in the performance. These results demonstrate the advantage or effect of different parameters on the result.

CNN(Convolution Neural Network), MNIST(Modified National Institute of Standards and Technology), Deep learning, ANN(Artificial Neural Network)

[1] Chang, Yeong-Hwa, Ping-Lun Chung, and Hung-Wei Lin "Deep learning for object identification in ROS-based mobile robots", In 2018 IEEE International Conference on Applied System Invention (ICASI),pp. 66-69, 2018.
[2] Vidushi, M.Agarwal, “Comprehensive and Comparative Analysis of Neural Network”, International Journal of Computer Application, Vol. 2, Issue 8, pp.126-137, 2018.
[3] C.P.Patidar, Meena Sharma, Varsha Sharda, "Detection of Cross Browser Inconsistency by Comparing Extracted Attributes", International Journal of Scientific Research in Computer Science and Engineering, Vol.5, Issue.1, pp.1-6, 2017.
[4] G. Sharma, A. Kumar, "REVIN: Reduced Energy Virtuous Immune Network for WSN", International Journal of Scientific Research in Computer Science and Engineering, Vol.5, Issue.2, pp.1-8, 2017.
[5] Heusel, Martin, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. "Gans trained by a two time-scale update rule converge to a local nash equilibrium." In Advances in Neural Information Processing Systems, pp. 6626-6637. 2017.
[6] Z.Qiu, B.Z. Allison, J. Jin, Y. Zhang, X. Wang, W. Li, A. Cichocki, "Optimized motor imagery paradigm based on imagining Chinese characters writing movement", IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol. 25, Issue. 7, 2017.
[7] D.C. Aishwarya, C.N. Babu, "Prediction of Time Series Data Using GA-BPNN Based Hybrid ANN Model", In 2017 IEEE 7th International Advance Computing Conference (IACC), pp. 848-853, 2017.
[8] D. Wu, W. Zou, X. Li, Y.Zhao, "Kernalised Multi-resolution Convnet for Visual Tracking", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 66-73, 2017.
[9] N. Zhang, W. Karimoune, L. Thompson, H.Dang, "A between-class overlapping coherence-based algorithm in KNN classification", In Systems, Man, and Cybernetics (SMC), 2017 IEEE International Conference on, pp. 572-577, 2017.
[10] P.H. Kassani, A.B.J. Teoh, E. Kim,"Evolutionary-modified fuzzy nearest-neighbor rule for pattern classification", Expert Systems with Applications, Vol. 88, pp. 258-269, 2017.
[11] D. Suryani, P. Doetsch, H. Ney, "On the benefits of convolutional neural network combinations in offline handwriting recognition", In 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 193-198, 2016.
[12] Y. Tang, L. Peng, Q. Xu, Y. Wang, A. Furuhata, "Cnn based transfer learning for historical chinese character recognition" In Document Analysis Systems (DAS), 2016 12th IAPR Workshop on, pp. 25-29, 2016.
[13] M. Sharma, K.K. Sharma, "Learning aided mood and dialect recognition using telephonic speech." In Accessibility to Digital World (ICADW), 2016 International Conference on, pp. 163-167, 2016.
[14] Y. Zhu, Y. Jia, L. Wang, "Partial discharge pattern recognition method based on variable predictive model-based class discriminate and partial least squares regression" IET Science, Measurement & Technology 10, Vol. 10, Issue. 7, pp. 737-744, 2016.
[15] F. Faizan, S. Tandon, P. Parashar, P. Sengar. "Vectorized code implementation of Logistic Regression and Artificial Neural Networks to recognize handwritten digit", In Power Electronics, Intelligent Control and Energy Systems (ICPEICES), IEEE International Conference on, pp. 1-5., 2016.
[16] R. Rostaminia, M. Saniei, M. Vakilian, S.S. Mortazavi, V. Parvin, "Accurate power transformer PD pattern recognition via its model." IET Science, Measurement & Technology, Vol. 10, Issue. 7, pp. 745-753, 2016.
[17] F. Zhu, L. Shao, Y. Fang, "Boosted cross-domain dictionary learning for visual categorization", IEEE Intelligent Systems, Vol. 31,Issue. 3, pp. 6-18, 2016.
[18] K. Abhishek, B.B. Misra, "Hybrid Genetic Algorithm and time delay neural network model for Forecasting Traffic flow" In 2016 IEEE International Conference on Engineering and Technology (ICETECH), pp. 178-183, 2016.
[19] R. F. Alvear-Sandoval , A. R. Figueiras-Vidal, "Does diversity improve deep learning?", In Signal Processing Conference (EUSIPCO), 2015 23rd European, pp. 2496-2500, 2015.
[20] S.K. Sahu, A.K. Pujari, V. Kumar, V.R. Kagita, V. Padmanabhan, "Greedy partitioning based tree structured multiclass SVM for Odia OCR", In Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG), 2015 Fifth National Conference on, pp. 1-4, 2015.
[21] J. Khanapuri, L. Kulkarni, "An efficient fuzzy based approach for color image retrieval with dual tree—Rotated complex wavelet and fuzzy histogram using selective relevance feedback approach ", In Convergence of Technology (I2CT), 2014 International Conference for, pp. 1-8, 2014.
[22] A. Rahaman, M.M. Hasan, M.F. Shuvo, M.A.S. Ovi, M.M. Rahman, "Analysis on handwritten Bangla character recognition using ANN" In Informatics, Electronics & Vision (ICIEV), 2014 International Conference on, pp. 1-5, 2014.
[23] V. Sharma, A.K. Gupta,.” A Comprehensive Study of Fuzzy Logic”, International Journal of Advanced Research in Computer Science and Software Engineering, Vol. 3, Issue. 2, pp. 398-403, 2013.
[24] C. Wu, W. Wei, J. Lin, W. Lee, "Speaking effect removal on emotion recognition from facial expressions based on eigenface conversion", IEEE Transactions on Multimedia, Vol. 15, Issue. 8, pp. 1732-1744, 2013.
[25] Y. Reisinger, L. Turner, "Cultural differences between Mandarin-speaking tourists and Australian hosts and their impact on cross-cultural tourist-host interaction", Journal of Business Research, Vol. 42, Issue. 2, pp. 175-187, 1998.
[26] A. Krizhevsky, I. Sutskever, G.E. Hinton, "Imagenet classification with deep convolutional neural networks." In Advances in neural information processing systems, pp. 1097-1105, 2012.
[27] V. Sharma, A. Dev, S. Rai, “A Comprehensive Study of Cellular Automata”,. International Journal of Advanced Research in Computer Science and Software Engineering, Vol. 2, Issue. 10, 2012.
[28] V. Sharma, S. Rai, A. Dev, “A Comprehensive Study of Artificial Neural Network”,. International Journal of Advanced Research in Computer Science and Software Engineering, Vol. 2, Issue. 10, 2012.
[29] K. Dutta, K.K. Sarma, "Multiple feature extraction for RNN-based assamese speech recognition for speech to text conversion application", In Communications, Devices and Intelligent Systems (CODIS), 2012 International Conference on, pp. 600-603, 2012.
[30] S.N. Hajimirja, M.J. Proulx, E. Izquierdo, "Reading users` minds from their eyes: a method for implicit image annotation", IEEE Transactions on Multimedia, Vol. 14, Issue. 3, pp. 805-815, 2012.
[31] X. Li, H. Lu, "Object tracking based on local learning", In Image Processing (ICIP), In 2012 19th IEEE International Conference on, pp. 413-416, 2012.
[32] J. Tanha, M.V. Someren, M.D. Bakker, W. Bouteny, J. Shamoun-Baranesy, H. Afsarmanesh, "Multiclass Semi-supervised Learning for Animal Behavior Recognition from Accelerometer Data", In ICTAI, pp. 690-697. 2012.
[33] S. Ghorpade, J. Ghorpade, S. Mantri, "Pattern recognition using neural networks", International Journal of Computer Science & Information Technology (IJCSIT), Vol. 2, Issue. 6, pp. 92-98, 2010.
[34] S. Rahman, S.M. Naim, A.A. Farooq, M.M. Islam, "Performance of mpeg-7 edge histogram descriptor in face recognition using principal component analysis", In 2010 13th International Conference on Computer and Information Technology (ICCIT), pp. 476-481, 2010.
[35] Q. Zhu, Q. Lao, "Construction of NPR biorthogonal wavelet and its application in edge detection", In 2010 3rd International Congress on Image and Signal Processing, vol. 3, pp. 1049-1053, 2010.
[36] H.C. Tseng, B. Almogahed, "Modular neural networks with applications to pattern profiling problems”, Neurocomputing , Vol. 72,Issue. 10-12, pp. 2093-2100, 2009.
[37] U. Bhattacharya, B.B. Chaudhri, "Handwritten numeral databases of Indian scripts and multistage recognition of mixed numerals", IEEE transactions on pattern analysis and machine intelligence, Vol. 31, Issue. 3, pp. 444-457, 2009.
[38] Visakhasart, Sathaporn, O. Chitsobhuk, "Multi-Pipeline Architecture for face recognition on FPGA" In Digital Image Processing, 2009 International Conference on, pp. 152-156, 2009.
[39] J. Naiborhu, S. M. Nababan, R. Saragih, I. Pranoto. "Direct Gradient Descent Control as a Dynamic Feedback Control for Linear System." Bulletin of the Malaysian Mathematical Sciences Society, Vol. 29,Issue. 2, 2006.
[40] K. Shimizu, S. Ito, S. Suzuki, "Tracking control of general nonlinear systems by a direct gradient descent method", Nonlinear Dynamics and Systems Theory, Vol. 5, Issue. 1, pp. 91-105, 2005.
[41] Kussul, Ernst, and Tatiana Baidyk. "Improved method of handwritten digit recognition tested on MNIST database." Image and Vision Computing 22, no. 12 (2004): 971-981.