• icon+90(533) 652 66 86
  • iconnwsa.akademi@hotmail.com
  • icon Fırat Akademi Samsun-Türkiye

Article Details

Article Details

  • Article Code : FIRAT-AKADEMI-9279-5542
  • Article Type : Araştırma Makalesi
  • Publication Number : 2A0189
  • Page Number : 54-61
  • Doi : 10.12739/NWSA.2022.17.4.2A0189
  • Abstract Reading : 434
  • Download : 101
  • Share :

  • PDF Download

Issue Details

  • Year : 2022
  • Volume : 17
  • Issue : 4
  • Number of Articles Published : 1
  • Published Date : 1.10.2022

Cover Download Context Page Download
Dergi Kapağı
Technological Applied Sciences

Serial Number : 2A
ISSN No. : 1308-7223
Release Interval (in a Year) : 4 Issues

İsmail AKGÜL1 , Yıldız AYDIN2

Keywords

OBJECT RECOGNITION WITH DEEP LEARNING AND MACHINE LEARNING METHODS

İsmail AKGÜL1 , Yıldız AYDIN2

The field of computer vision, which is widely studied area, is basically the imitation of the human vision system with digital devices. Computer systems perform operations through digital images or video images and decide according to the result. In this context, object recognition must be performed at the first stage in order to extract meaningful information from the image. In this study, the application of object recognition was developed using the deep learning method, which is especially popular in recent years. It has also been compared with classical machine learning methods often used in recognition applications. The proposed method developed with Convolutional Neural Network (CNN) has been compared by using the Histogram of Oriented Gradient (HOG) features and classifying them with Support Vector Machines (SVM) and K-Nearest Neighbor (KNN) methods. Experimental results show that the proposed CNN method is more successful than HOG+SVM, and HOG+KNN methods.

Keywords
CNN, HOG, SVM, KNN, Object Recognition,

Details
   

Authors

İsmail AKGÜL (1) (Corresponding Author)
Erzincan Binali Yıldırım University
iakgul@erzincan.edu.tr | 0000-0003-2689-8675

Yıldız AYDIN (2)

erzincan binali yıldırım üniversitesi mühendislik-mimarlık fakültesi
yciltas@erzincan.edu.tr | 0000-0002-3877-6782

Supporting Institution

 :

Project Number

 :

Thanks

 :
References
[1] Dalal, N. and Triggs, B., (2005). Histograms of oriented gradients for human detection. In 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05), San Diego, CA, USA, pp:886-893. https://doi.org/10.1109/cvpr.2005.177.

[2] Cortes, C. and Vapnik, V., (1995). Support-vector networks. Machine learning, 20(3):273-297. https://doi.org/10.1007/bf00994018.

[3] Cover, T. and Hart, P., (1967). Nearest neighbor pattern classification. IEEE transactions on information theory, 13(1):21-27. https://doi.org/10.1109/TIT.1967.1053964.

[4] Alaeddine, H. and Jihene, M., (2021). Deep residual network in network. Computational Intelligence and Neuroscience, 2021. https://doi.org/10.1155/2021/6659083.

[5] Abouelnaga, Y., Ali, O. S., Rady, H., and Moustafa, M., (2016). Cifar-10: Knn-based ensemble of classifiers. In 2016 International Conference on Computational Science and Computational Intelligence (CSCI), Las Vegas, NV, USA, pp:1192-1195. https://doi.org/10.1109/csci.2016.0225

[6] Thakkar, V., Tewary, S., and Chakraborty, C., (2018). Batch Normalization in Convolutional Neural Networks—A comparative study with CIFAR-10 data. In 2018 fifth international conference on emerging applications of information technology (EAIT), Kolkata, India, pp:1-5. https://doi.org/10.1109/eait.2018.8470438.

[7] Coates, A., Ng, A., and Lee, H., (2011). An analysis of single-layer networks in unsupervised feature learning. In Proceedings of the fourteenth international conference on artificial intelligence and statistics, pp:215-223.

[8] Xu, B., Wang, N., Chen, T., and Li, M., (2015). Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853.

[9] Giuste, F.O. and Vizcarra, J.C., (2020). CIFAR-10 Image Classification Using Feature Ensembles. arXiv preprint arXiv:2002.03846.

[10] Romanuke, V.V., (2017). Appropriateness of DropOut layers and allocation of their 0.5 rates across convolutional neural networks for CIFAR-10, EEACL26, and NORB datasets. Applied Computer Systems, 22(1):54-63. https://doi.org/10.1515/acss-2017-0018.

[11] Tang, Y., (2013). Deep learning using linear support vector machines. arXiv preprint arXiv:1306.0239.

[12] Krizhevsky, A. and Hinton, G., (2009). Learning multiple layers of features from tiny images (Technical Report). University of Toronto.

[13] Rudnicky, A.I., Brennan, R.A., and Polifroni, J.H., (1988). Interactive problem solving with speech. The Journal of the Acoustical Society of America, 84(S1):S213-S213. https://doi.org/10.1121/1.2026163.