Abstract
Günümüz teknolojisinde gelişen bilgisayarlar hayatın her alanında aktif olarak kullanmaktadır. İş, eğitim, sosyal vb. alanlarda işlerimizi kolaylaştırmamıza yardımcı olan bu sistemler geliştikçe işlem yapabilmek ya da problem çözmek daha da kolay hale geldiği anlaşılmaktadır. Bu alanların hemen hemen hepsinin içerisinde yer alan görüntü ya da resim niteliği bulunan dosya veya dosyalar üzerinde ihtiyaca göre bir takım morfolojik işlemler gerçekleştirilebilir. Bu çalışmanın amacı herhangi bir araç görüntüsü alınarak aracın renginin tespit edilmesidir. Tespit edilen renk ihtiyaca göre kullanıldığı alanlar farklılık gösterebilir. Örneğin bir plaka okuma sisteminde araç bilgisi eşleştirmek için renk bulgusu önemli bir faktördür. Buna benzer birçok alanda ihtiyaç duyulan araç renk bilgisi için birçok farklı uygulama alanları ve yöntemleri mevcuttur. Bu tarz uygulama alanlarında kullanılmak üzere karmaşıklığı minimum düzeyde olan bir algoritma tasarlanmıştır. Sistem, python programlama dili kullanılarak tasarlanmıştır. Doğruluk oranı resmin piksel kalitesi ile direkt olarak doğru orantılıdır.
References
- [1] Q. Zhang, L. Zhuo, J. Li, J. Zhang, H. Zhang, and X. Li, “Vehicle color recognition using Multiple-Layer Feature Representations of lightweight convolutional neural network,” Signal Processing, vol. 147, pp. 146–153, 2018, doi: 10.1016/j.sigpro.2018.01.021.
- [2] H. Fu, H. Ma, G. Wang, X. Zhang, and Y. Zhang, “MCFF-CNN: Multiscale comprehensive feature fusion convolutional neural network for vehicle color recognition based on residual learning,” Neurocomputing, vol. 395, pp. 178–187, 2020, doi: 10.1016/j.neucom.2018.02.111.
- [3] K. J. Kim et al., “Vehicle Color Recognition via Representative Color Region Extraction and Convolutional Neural Network,” Int. Conf. Ubiquitous Futur. Networks, ICUFN, vol. 2018-July, pp. 89–94, 2018, doi: 10.1109/ICUFN.2018.8436710.
- [4] Y. Artan, B. Alkan, B. Balci, A. E. L. İ. H. O. Ş, and A. Ş. Havelsan, “Plaka Tanima Kamera Görüntülerİ Nde Derİ N Ö Ğ Renme Tabanli Araç Marka , Model Ve Renk Siniflandirma Yöntemİ Deep Learning Based Vehicle Make , Model and Color Recognition Using License Plate Recognition Camera Images,” pp. 22–25.
- [5] M. Yang, G. Han, X. Li, X. Zhu, and L. Li, “Vehicle color recognition using monocular camera,” 2011 Int. Conf. Wirel. Commun. Signal Process. WCSP 2011, pp. 0–4, 2011, doi: 10.1109/WCSP.2011.6096902.
- [6] X. Li, G. Zhang, J. Fang, J. Wu, and Z. Cui, “Vehicle color recognition using vector matching of template,” 3rd Int. Symp. Electron. Commer. Secur. ISECS 2010, no. c, pp. 189–193, 2010, doi: 10.1109/ISECS.2010.50.
- [7] Y. Dong, M. Pei, and X. Qin, “Vehicle color recognition based on license plate color,” Proc. - 2014 10th Int. Conf. Comput. Intell. Secur. CIS 2014, pp. 264–267, 2015, doi: 10.1109/CIS.2014.63.
- [8] T. Wang, C. Xiu, and Y. Cheng, “Vehicle recognition based on saliency detection and color histogram,” Proc. 2015 27th Chinese Control Decis. Conf. CCDC 2015, pp. 2532–2535, 2015, doi: 10.1109/CCDC.2015.7162347.
- [9] B. Huval et al., “An Empirical Evaluation of Deep Learning on Highway Driving,” pp. 1–7, 2015, [Online]. Available: http://arxiv.org/abs/1504.01716.
- [10] F. Wang, L. Man, B. Wang, Y. Xiao, W. Pan, and X. Lu, “Fuzzy-based algorithm for color recognition of license plates,” Pattern Recognit. Lett., vol. 29, no. 7, pp. 1007–1020, 2008, doi: 10.1016/j.patrec.2008.01.026.
- [11] B. Huval et al., “An Empirical Evaluation of Deep Learning on Highway Driving,” pp. 1–7, 2015.
- [12] E. Osaba, “Benchmark dataset for the Asymmetric and Clustered Vehicle Routing Problem with Simultaneous Pickup and Deliveries, Variable Costs and Forbidden Paths,” Data Br., vol. 29, p. 105142, 2020, doi: 10.1016/j.dib.2020.105142.
- [13] https://github.com/burakaggul/vehicle_color_recognition/blob/main/vehicle_color_recognition.py
Abstract
Computers developed in today's technology are actively used in all areas of life. Business, education, social, etc. It is understood that as these systems, which help us facilitate our work in the fields, it becomes easier to act or solve problems. A number of morphological operations can be performed on the files or files that have image or picture quality in almost all of these areas. The purpose of this study is to determine the color of the vehicle by taking any vehicle image. The areas where the detected color is used may differ depending on the need. Color indication is an important factor in matching vehicle information, for example in a license plate reading system. There are many different application areas and methods for vehicle color information needed in many similar areas. An algorithm with minimal complexity has been designed to be used in such application areas. The system is designed using the python programming language. The accuracy rate is directly proportional to the pixel quality of the picture.
References
- [1] Q. Zhang, L. Zhuo, J. Li, J. Zhang, H. Zhang, and X. Li, “Vehicle color recognition using Multiple-Layer Feature Representations of lightweight convolutional neural network,” Signal Processing, vol. 147, pp. 146–153, 2018, doi: 10.1016/j.sigpro.2018.01.021.
- [2] H. Fu, H. Ma, G. Wang, X. Zhang, and Y. Zhang, “MCFF-CNN: Multiscale comprehensive feature fusion convolutional neural network for vehicle color recognition based on residual learning,” Neurocomputing, vol. 395, pp. 178–187, 2020, doi: 10.1016/j.neucom.2018.02.111.
- [3] K. J. Kim et al., “Vehicle Color Recognition via Representative Color Region Extraction and Convolutional Neural Network,” Int. Conf. Ubiquitous Futur. Networks, ICUFN, vol. 2018-July, pp. 89–94, 2018, doi: 10.1109/ICUFN.2018.8436710.
- [4] Y. Artan, B. Alkan, B. Balci, A. E. L. İ. H. O. Ş, and A. Ş. Havelsan, “Plaka Tanima Kamera Görüntülerİ Nde Derİ N Ö Ğ Renme Tabanli Araç Marka , Model Ve Renk Siniflandirma Yöntemİ Deep Learning Based Vehicle Make , Model and Color Recognition Using License Plate Recognition Camera Images,” pp. 22–25.
- [5] M. Yang, G. Han, X. Li, X. Zhu, and L. Li, “Vehicle color recognition using monocular camera,” 2011 Int. Conf. Wirel. Commun. Signal Process. WCSP 2011, pp. 0–4, 2011, doi: 10.1109/WCSP.2011.6096902.
- [6] X. Li, G. Zhang, J. Fang, J. Wu, and Z. Cui, “Vehicle color recognition using vector matching of template,” 3rd Int. Symp. Electron. Commer. Secur. ISECS 2010, no. c, pp. 189–193, 2010, doi: 10.1109/ISECS.2010.50.
- [7] Y. Dong, M. Pei, and X. Qin, “Vehicle color recognition based on license plate color,” Proc. - 2014 10th Int. Conf. Comput. Intell. Secur. CIS 2014, pp. 264–267, 2015, doi: 10.1109/CIS.2014.63.
- [8] T. Wang, C. Xiu, and Y. Cheng, “Vehicle recognition based on saliency detection and color histogram,” Proc. 2015 27th Chinese Control Decis. Conf. CCDC 2015, pp. 2532–2535, 2015, doi: 10.1109/CCDC.2015.7162347.
- [9] B. Huval et al., “An Empirical Evaluation of Deep Learning on Highway Driving,” pp. 1–7, 2015, [Online]. Available: http://arxiv.org/abs/1504.01716.
- [10] F. Wang, L. Man, B. Wang, Y. Xiao, W. Pan, and X. Lu, “Fuzzy-based algorithm for color recognition of license plates,” Pattern Recognit. Lett., vol. 29, no. 7, pp. 1007–1020, 2008, doi: 10.1016/j.patrec.2008.01.026.
- [11] B. Huval et al., “An Empirical Evaluation of Deep Learning on Highway Driving,” pp. 1–7, 2015.
- [12] E. Osaba, “Benchmark dataset for the Asymmetric and Clustered Vehicle Routing Problem with Simultaneous Pickup and Deliveries, Variable Costs and Forbidden Paths,” Data Br., vol. 29, p. 105142, 2020, doi: 10.1016/j.dib.2020.105142.
- [13] https://github.com/burakaggul/vehicle_color_recognition/blob/main/vehicle_color_recognition.py
Details
| Primary Language | Turkish |
|---|---|
| Subjects | Engineering |
| Journal Section | Articles |
| Authors | |
| Publication Date | April 30, 2021 |
| Submission Date | February 14, 2021 |
| Acceptance Date | March 3, 2021 |
| Published in Issue | Year 2021 Volume: 3 Issue: 1 |
Cited By
Development of a Counterfeit Vehicle License Plate Detection System by Using Deep Learning
Balkan Journal of Electrical and Computer Engineering
https://doi.org/10.17694/bajece.1093158
This work is licensed under Creative Commons Attribution 4.0 International License.