Binary Image Classification Through an Optimal Topology for Convolutional Neural Networks

  • Arman Sarraf Department of Electrical and Computer Engineering Islamic Azad University North Tehran Branch
Keywords: Deep Learning, Computer Vision, Image Classification, Convolutional Neural Networks


Deep learning applications in computer vision have expanded over the past years. Image classification, which is the fundamental of most algorithms in the field, has been of interest to many researchers. Advances in hierarchical feature extractions using convolutional neural networks as one of the deep learning architectures have enabled experts to improve the performance of classification significantly. In this work, an optimal binary classifier to distinguish cat and dog images was explored where various architectures and parameters were employed to achieve the best results. To design our experiment, we considered the architectures with two and three convolutional layers using two input image size when models were trained with and without Dropout against an identical dataset. The analysis demonstrated that an accuracy rate of 99.26% for the testing dataset was achieved from a three-layer model with an input image size of 32x32 with Dropout. The classification report of any models was produced to explore other metrics such as precision, recall, and F1-score, and they were aligned with the accuracy rates as this experiment was a balanced data situation.


. Domingos, P., A few useful things to know about machine learning. Communications of the ACM, 2012. 55(10): p. 78-87.

. Sarraf, S., Binary Image Segmentation Using Classification Methods: Support Vector Machines, Artificial Neural Networks and K th Nearest Neighbours. International Journal of Computer (IJC), 2017. 24(1): p. 56-79.

. Shaikh, F., 10 advanced deep learning architectures data scientists should know. 2017.

. Gu, J., et al., Recent advances in convolutional neural networks. Pattern Recognition, 2018. 77: p. 354-377.

. Chen, Y., et al., Deep learning-based classification of hyperspectral data. IEEE Journal of Selected topics in applied earth observations and remote sensing, 2014. 7(6): p. 2094-2107.

. [6] Dureja, A. and P. Pahwa, Analysis of non-linear activation functions for classification tasks using convolutional neural networks. Recent Patents on Computer Science, 2019. 12(3): p. 156-161.

. Sarraf, S., et al. Brain network extraction from probabilistic ICA using functional Magnetic Resonance Images and advanced template matching techniques. in 2014 IEEE 27th Canadian Conference on Electrical and Computer Engineering (CCECE). 2014. IEEE.

. Shanmukhi, M., et al., Convolutional neural network for supervised image classification. International Journal of Pure and Applied Mathematics, 2018. 119(14): p. 77-83.

. Shiddieqy, H.A., F.I. Hariadi, and T. Adiono. Implementation of deep-learning based image classification on single board computer. in 2017 International Symposium on Electronics and Smart Devices (ISESD). 2017. IEEE.

. Liu, B., Y. Liu, and K. Zhou, Image classification for dogs and cats. 2014.

. Sarraf, S. French Word Recognition Through a Quick Survey on Recurrent Neural Networks Using Long-Short Term Memory RNN-LSTM. American Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS), 39, no. 1 (2018): 250-267.

. Cengil, E., A. Çinar, and Z. Güler. A GPU-based convolutional neural network approach for image classification. in 2017 International Artificial Intelligence and Data Processing Symposium (IDAP). 2017. IEEE.

. Bandhu, A. and S.S. Roy. Classifying multi-category images using deep learning: A convolutional neural network model. in 2017 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT). 2017. IEEE.

. Jajodia, T. and P. Garg, Image Classification–Cat and Dog Images. Image, 2019. 6(12).

. Naidoo, K., O. Konan, and L. Schwartzkopff. Hardware Accelerated Convolutional Neural Networks. in Proceedings of 2010 IEEE International Symposium on Circuits and Systems (ISCAS).

. Sarraf, S., Hair color classification in face recognition using machine learning algorithms. American Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS), 2016. 26(3): p. 317-334.

. Sarraf, S., C. Saverino, and A.M. Golestani. A robust and adaptive decision-making algorithm for detecting brain networks using functional mri within the spatial and frequency domain. in 2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI). 2016. IEEE.

. Sarraf, S. and G. Tofighi. Deep learning-based pipeline to recognize Alzheimer’s disease using fMRI data. in 2016 Future Technologies Conference (FTC). 2016. IEEE.

. Sarraf, S., et al., MCADNNet: Recognizing Stages of Cognitive Impairment Through Efficient Convolutional fMRI and MRI Neural Network Topology Models. IEEE Access, 2019. 7: p. 155584-155600.

. [20] Sarraf, S., G. Tofighi, and A.s.D.N. Initiative, DeepAD: Alzheimer’s disease classification via deep convolutional neural networks using MRI and fMRI. BioRxiv, 2016: p. 070441.

. Hinton, G.E., et al., Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580, 2012.

. Gavrilov, A.D., et al., Preventing model overfitting and underfitting in convolutional neural networks. International Journal of Software Science and Computational Intelligence (IJSSCI), 2018. 10(4): p. 19-28.