Morfolojik Görüntü İşleme Tekniği ile Yapay Sinir Ağlarında Görüntü Tahribat Analizi

Yıl 2016, Cilt: 4 Sayı: 1, 0 - 0, 15.01.2016

Gökhan Atalı Sinan Serdar Özkan Durmuş Karayel

https://doi.org/10.21541/apjes.27271

Cited By: 3

Öz

Teknolojinin gelişmesine paralel olarak kamera sistemlerinde yüksek düzeyde kaliteyi öngören lensler tasarlanmıştır. Ancak bu lensler yapısal olarak her ne kadar görüntü kalitesinde başarılı olsalar da üzerinde tahribat meydana gelmiş görüntülerin ayırt edilmesinde herhangi bir ek özellik mevcut değildir. Esasen bu tür tahribatların giderilmesi için yapay zeka teknikleri kullanmak mümkündür. Bu çalışmada, yapay sinir ağları kullanarak üzerinde tahribat meydana gelmiş görüntülerin morfolojik görüntü işleme teknikleri ile birleştirilerek tahribatın derecesine göre orijinal görüntüye yakınsaması ele alınmıştır. Ayrıca bu amaca ulaşmak ve kullanımı kolaylaştırmak amacıyla geliştirilen arayüz sayesinde eğitim ve test verilerinin yanı sıra ağı oluşturmak için kullanılacak parametrelerin kolaylıkla hazırlanan algoritmaya entegrasyonu sağlanmaktadır.

 

Anahtar Kelimeler: Yapay Sinir Ağları, Karakter Tespiti, Morfolojik Görüntü İşleme

Image Damage Analysis With Morphological Image Processing Technique Using Artificial Neural Networks

Öz

The lenses providing high quality for camera systems are designed as parallel with developing technologies. These lenses do not have any additional functionality to distinguish damaged images while they are successful with regard to image quality. Essentially, artificial intelligence techniques can be used to eliminate such damaged cases. In this study, convergence to original image of the damaged images according to the degree of damage using together artificial neural networks and morphological image processing techniques are discussed. Also, it is provided to be integrated training and test data with used algorithm thanks to developed interfaces to achieve goal and to facilitate use. In addition, this interface is used to be entered the training parameters to the system.

 

Keywords: Artificial Neural Networks (ANN), Character detection, Morphological image processing

Kaynakça

• Barroso, J., Rafael, A., Dagless, E. L., Bulas-Cruz, J., Number plate reading using computer vision, IEEE – International Symposium on Industrial Electronics ISIE’97, Universidade do Minho, Guimarães, 1997.
• Morphological Segmentation for Textures and Particles, Published as Chapter 2 of Digital Image Processing Methods, E. Dougherty, Editor, Marcel-Dekker, New York, 1994, Pages 43--102.
• B. Hongliang and L. Changping. A hybrid license plate extraction method based on edge statistics and morphology.17th International Conference On Pattern Recognition(ICPR’04), 2:831–834, 2004.
• M. Sarfraz, M. J. Ahmed, and S. A. Ghazi. Saudi arabian license plate recognition system. Proceedings of the 2003 International Conference on Geometric Modeling and Graphics(GMAG’03), pages 36–41, 2003.
• V. Kamat and S. Ganesan. An efficient implementation of hough transform for detecting vehicle license plate using dsp’s. 1st IEEE Real-Time Technology and Applications Symposium, pages 58–59, 1995.
• V. Shapiro, D. Dimov, S. Bonchev, V. Velichkov, and G. Gluhchev. Adaptive license plate image extraction. International Conference on Computer Systems and Technologies, 2003.
• F. Mart´ın, M. Garc´ıa, and J. L. Alba. New methods for automatic reading of vlps (vehicle license plates). Signal Processing Patten Recognition and Application, 2002.
• Kahraman F., Gökmen M. “GABOR Süzgeçler Kullanılarak Taşıt Plakalarının Yerinin Saptanması”, 11. sinyal İşleme ve İletişim Uygulamaları Kurultayı, İstanbul, 2003.
• F.Kahraman, B.Kurt, M.Gökmen "Aktif Görünüm Modeline Dayalı Yüz Tanıma" Signal Processing and Communications Applications Conference, 2005. Proceedings of the IEEE 13th, May 2005, Pages 483-486, Print ISBN: 0-7803-9239-6
• C.Tu, B.J van Wyk, Y. Hamam, K. Djouani, Shengzhi Du "Vehicle Position Monitoring Using Hough Transform" IERI Procedia Volume 4, 2013, Pages 316–322 2013 International Conference on Electronic Engineering and Computer Science (EECS 2013)
• C.Lopez-Molina, B. De Baets, H. Bustince "Quantitative error measures for edge detection" Pattern Recognition Volume 46, Issue 4, April 2013, Pages 1125–1139
• P. Ponce, S. S. Wang, D. L. Wang, “License Plate Recognition-Final Report”, Department of Electrical and Computer Engineering, Carnegie Mellon University, 2000.
• M. Yu and Y. D. Kim, ``An Approach to Korean License Plate Recognition Based on Vertical Edge Matching", IEEE International Conference, vol. 4, 2975-2980, 2000
• J.R. Parker, P. Federl, ``An Approach To Licence Plate Recognition", The Laboratory For Computer Vision, University of Calgary, 1996.
• Cui Y., Huang Q., Extracting Characters of License Plates from Video Sequences, Machine Vision and Applications 10, 308-320, 1998.
• Naito, T., Tsukada, T., Yamada, Yamamoto, S., Robust License-Plate Recognition Method for Passing Vehicles under Outside Environment, IEEE Trans. Vehicular Technology 49, 2309-2319, 2000.
• Nishiyama, K., Kato, K., Hinenoya, T.: Image processing system for traffic measurement, Proceedings of International Conference on Industrial Electronics, Control and Instrumentation Kobe, Japan, (1991) 1725–1729.
• Lu, Y., Machine printed character segmenation, Pattern Recognition, vol. 28, n. 1, 67-80, Elsevier Science Ltd, UK, 1995