Perbandingan Kinerja ANN dan CNN dalam Tugas Klasifikasi Citra Berbasis Pembelajaran Mesin
DOI:
https://doi.org/10.30989/teknomatika.v18i1.1561Keywords:
Artificial Neural Network, Convolutional Neural Network, Classification, Image Processing , Machine LearningAbstract
Advances in machine learning have brought great impact on image recognition through Artificial Neural Network (ANN) and Convolutional Neural Network (CNN) approaches. This study compares the performance of both algorithms in image classification with a dataset of two classes, namely Green and Red Keychains. The dataset consists of 100 images processed through augmentation and data division of 65% for training and 35% for testing. The evaluation results show that CNN has higher accuracy, which is 88.24% to 93.94%, compared to ANN which reaches 62.12% to 67.65%. CNN is also more efficient in training time. The advantage of CNN lies in its ability to extract spatial features through convolution layers, while ANN is more suitable for simple data. This study concludes that CNN is superior for color-based image classification, although further research is needed with larger datasets.
References
[1] A. Pratap and N. Sardana, “Machine learning-based image processing in materials science and engineering: A review,” in Materials Today: Proceedings, 2022, pp. 7341–7347. doi: https://doi.org/10.1016/j.matpr.2022.01.200.
[2] X. Zhao, L. Wang, Y. Zhang, X. Han, M. Deveci, and M. Parmar, “A review of convolutional neural networks in computer vision,” Artif. Intell. Rev., vol. 57, no. 4, p. 99, 2024, doi: 10.1007/s10462-024-10721-6.
[3] M. I. Vawda, R. Lottering, O. Mutanga, K. Peerbhay, and M. Sibanda, “Comparing the Utility of Artificial Neural Networks (ANN) and Convolutional Neural Networks (CNN) on Sentinel-2 MSI to Estimate Dry Season Aboveground Grass Biomass,” Sustainability, vol. 16, no. 3, 2024, doi: 10.3390/su16031051.
[4] D. Anggraeni, A. Wulandari, T. Barasaruddin, and D. Yanti, “Enhancing CNN with preprocessing stage in automatic emotion enhancing CNN with preprocessing stage in automatic emotion recognition recognition,” in Procedia computer science, 2017, pp. 523–529.
[5] S. Walczak and N. Cerpa, “Artificial Neural Networks,” in Encyclopedia of Physical Science and Technology (Third Edition), Third Edition., R. A. Meyers, Ed., New York: Academic Press, 2003, pp. 631–645. doi: https://doi.org/10.1016/B0-12-227410-5/00837-1.
[6] H. K. Jeong et al., “Image Quality Assessment Using Convolutional Neural Network in Clinical Skin Images,” JID Innov., vol. 4, no. 4, p. 100285, 2024, doi: https://doi.org/10.1016/j.xjidi.2024.100285.
[7] I. Kandel and M. Castelli, “The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset,” ICT Express, vol. 6, no. 4, pp. 312–315, 2020, doi: https://doi.org/10.1016/j.icte.2020.04.010.
[8] K. Tong and Y. Wu, “Deep learning-based detection from the perspective of small or tiny objects: A survey,” Image Vis. Comput., vol. 123, p. 104471, 2022, doi: https://doi.org/10.1016/j.imavis.2022.104471.
[9] M. Vakili, M. Ghamsari, and M. Rezaei, “Performance analysis and comparison of machine and deep learning algorithms for IoT data classification,” arXiv Prepr. arXiv2001.09636, 2020.
[10] O. Kembuan, G. Caren Rorimpandey, and S. Milian Tompunu Tengker, “Convolutional Neural Network (CNN) for Image Classification of Indonesia Sign Language Using Tensorflow,” in 2020 2nd International Conference on Cybernetics and Intelligent System (ICORIS), 2020, pp. 1–5. doi: 10.1109/ICORIS50180.2020.9320810.
