Abstract
Yapay Zeka veya Yapay Zeka, genellikle insan zekası gerektiren görevleri yerine getirebilen bilgisayar sistemlerinin ve algoritmaların geliştirilmesini ifade eder. Bu görevler arasında problem çözme, öğrenme, doğal dili anlama, kalıpları tanıma ve karar verme yer alır. Yapay zeka sistemleri, insanın bilişsel işlevlerini taklit edecek veya simüle edecek şekilde tasarlanmış olup, onların büyük miktarlarda veriyi işlemesine ve analiz etmesine, değişen koşullara uyum sağlamasına ve geleneksel olarak insanlara özel olan görevleri yerine getirmesine olanak tanır. Bu çalışmada, yüzleri tanımak ve duyguları sınıflandırmak için yapay zeka teknolojileri, özellikle de derin öğrenme, önceden eğitilmiş modeller kullanılmıştır. AlexNet, VGGNet, ResNet, Inception gibi popüler mimariler farklı veri setleri üzerinde eğitilerek performansları karşılaştırılmıştır. Elde edilen sonuçlar, derin evrişimli sinir ağları ile görüntü sınıflandırma performansında önemli bir iyileşme olduğunu göstermektedir. Özellikle daha derin ve karmaşık mimariye sahip ağlar daha iyi performans gösterme eğilimindedir. Ancak aşırı uyum riskini azaltmak için uygun düzenleme tekniklerinin kullanılması çok önemlidir.
References
- 1. Manuel, Castells (1996). The information age: economy, society and culture. Oxford: Blackwell. ISBN 978-0631215943. OCLC 43092627.
- 2. Emotion Recognition based on Texture Analysis of Facial Expression (Authors: Gyanendra K. Verma, Bhupesh Kumar Singh) (Date: November 2011)
- 3. Discriminatory Analysis. Nonparametric Discrimination: Consistency Properties (Authors: Evelyn Fix and Joseph L. Hodges) (Date: 1951)
- 4. Nearest Neighbor Pattern Classification (Authors: T. M. Cover and P. E. Hart) (Date: January 1967) (Publisher: IEEE)
- 5. Choice Of Neighbor Order In Nearest-Neighbor Classification (Authors: Peter Hall, Byeong U. Park and Richard J. Samworth) (Date: 2008) (Publisher: The Annals of Statistics)
- 6. A novel kNN algorithm with data-driven k parameter computation (Authors: Shichao Zhanga , Debo Cheng, , Zhenyun Denga, Ming Zongc and Xuelian Deng) (Date: July 2018) (Pattern Recognition Letters)
- 7. A training algorithm for optimal margin classifiers (Authors: Bernhard E. Boser, Isabelle M. Guyon and Vladimir N. Vapnik) (Date: 1992)
- 8. Support Vector Clustering (Authors: Asa Ben-Hur, David Horn, Hava T. Siegelmann and Vladimir Vapnik) (Date: June 2008) (Journal of Machine Learning Research)
- 9. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097-1105).
- 10. Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
- 11. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778)
- 12. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2818-2826)
- 13. Viola, P., And Jones, M., 'Rapid Object Detection Using A Boosted Cascade Of Simple Features,'Accepted Conference On Computer Vısıon And Pattern Recognıtıon 2001
- 14. Dwivedi, D. (2018). Face detection for beginners. Retrieved from https://towardsdatascience.com
- 15. Training Invariant Support Vector Machines (Authors: Dennis Decoste and Bernhard Schölkopf) (Date: January 2002) (Machine Learning) (Kluwer Academic Publishers)
- 16. Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified,real-time object detection. In: CVPR (2016)
Abstract
AI or Artificial Intelligence, refers to the development of computer systems and algorithms that can perform tasks that typically require human intelligence. These tasks include problem-solving, learning, understanding natural language, recognizing patterns, and making decisions. AI systems are designed to mimic or simulate human cognitive functions, enabling them to process and analyze large amounts of data, adapt to changing circumstances, and perform tasks that were traditionally exclusive to humans. In this study AI technologies specifically deep learning pre trained models are utilized to recognize faces and classify emotions. Popular architectures such as AlexNet, VGGNet, ResNet, and Inception have been trained on different datasets, and their performances are compared. The results obtained indicate a significant improvement in image classification performance with deep convolutional neural networks. Particularly, networks with deeper and more complex architectures tend to perform better. However, it is crucial to employ appropriate regularization techniques to mitigate the risk of overfitting.
Keywords
Artificial Intelligence AI Image Processing Face Detection Emotion Recognition Haar Cascade k-NN YOLO SSD CNN
References
- 1. Manuel, Castells (1996). The information age: economy, society and culture. Oxford: Blackwell. ISBN 978-0631215943. OCLC 43092627.
- 2. Emotion Recognition based on Texture Analysis of Facial Expression (Authors: Gyanendra K. Verma, Bhupesh Kumar Singh) (Date: November 2011)
- 3. Discriminatory Analysis. Nonparametric Discrimination: Consistency Properties (Authors: Evelyn Fix and Joseph L. Hodges) (Date: 1951)
- 4. Nearest Neighbor Pattern Classification (Authors: T. M. Cover and P. E. Hart) (Date: January 1967) (Publisher: IEEE)
- 5. Choice Of Neighbor Order In Nearest-Neighbor Classification (Authors: Peter Hall, Byeong U. Park and Richard J. Samworth) (Date: 2008) (Publisher: The Annals of Statistics)
- 6. A novel kNN algorithm with data-driven k parameter computation (Authors: Shichao Zhanga , Debo Cheng, , Zhenyun Denga, Ming Zongc and Xuelian Deng) (Date: July 2018) (Pattern Recognition Letters)
- 7. A training algorithm for optimal margin classifiers (Authors: Bernhard E. Boser, Isabelle M. Guyon and Vladimir N. Vapnik) (Date: 1992)
- 8. Support Vector Clustering (Authors: Asa Ben-Hur, David Horn, Hava T. Siegelmann and Vladimir Vapnik) (Date: June 2008) (Journal of Machine Learning Research)
- 9. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097-1105).
- 10. Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
- 11. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778)
- 12. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2818-2826)
- 13. Viola, P., And Jones, M., 'Rapid Object Detection Using A Boosted Cascade Of Simple Features,'Accepted Conference On Computer Vısıon And Pattern Recognıtıon 2001
- 14. Dwivedi, D. (2018). Face detection for beginners. Retrieved from https://towardsdatascience.com
- 15. Training Invariant Support Vector Machines (Authors: Dennis Decoste and Bernhard Schölkopf) (Date: January 2002) (Machine Learning) (Kluwer Academic Publishers)
- 16. Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified,real-time object detection. In: CVPR (2016)
Details
| Primary Language | Turkish |
|---|---|
| Subjects | Software and Application Security |
| Journal Section | Research Articles |
| Authors | |
| Publication Date | August 26, 2025 |
| Submission Date | July 18, 2024 |
| Acceptance Date | August 23, 2024 |
| Published in Issue | Year 2025 Volume: 8 Issue: 1 |
