Plaka tanıma sistemi için farklı bir yaklaşım
Yükleniyor...
Dosyalar
Tarih
2009-06-26
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
IEEE
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Bu bildiride, bilgisayarlı görü ve örüntü tanıma alanlarında çok popüler olan plaka tanıma sistemi için farklı bir yakla¸sım sunuyoruz. Plaka tanıma sistemi genellikle üç ana bölüme ayrılır: plakanın yerinin saptanması, karakter bölütleme ve karakter tanıma. Plaka tanıma sisteminin en önemli bölümü olan plaka yerinin saptanmasında, yatay tarama ile arama alanını daralttıktan sonra, Türk plakalarında yer alan TR işaretini kullanan yeni ve özgün bir algoritma öneriyoruz. Yeri saptanan plakanın karakterlerinin bölütlenmesi için ikili imge üzerinde morfolojik işlemler uyguluyoruz. Son olarak, karakter tanıma işleminde ise, harf ve sayı yapay sinir ağlarını ayırarak hata oranını en küçültmeyi hedefliyoruz.
In this paper, we present a different approach for license plate recognition system which is a very popular subject in computer vision and pattern recognition fields. Generally, license plate recognition system is divided into three main parts: locating the license plate, character segmentation and character recognition. In locating the license plate phase which is the most important part of the license plate recognition system, we propose a new and original algorithm which uses the TR sign of the Turkish license plates after making horizontal scan for narrowing the search area. For segmenting the located license plate's characters, we apply morphological operations to the binary image. At last, in the character recognition phase, we aim to minimize the error rate by separating the letter and number neural networks.
In this paper, we present a different approach for license plate recognition system which is a very popular subject in computer vision and pattern recognition fields. Generally, license plate recognition system is divided into three main parts: locating the license plate, character segmentation and character recognition. In locating the license plate phase which is the most important part of the license plate recognition system, we propose a new and original algorithm which uses the TR sign of the Turkish license plates after making horizontal scan for narrowing the search area. For segmenting the located license plate's characters, we apply morphological operations to the binary image. At last, in the character recognition phase, we aim to minimize the error rate by separating the letter and number neural networks.
Açıklama
Anahtar Kelimeler
Character recognition, Character segmentation, Computer vision, Error analysis, Error rate, Horizontal scan, Image segmentation, License plate recognition system, License plate, License plate recognition systems, License plates (automobile), Licenses, Mathematical morphology, Morphological operations, Neural networks, Optical character recognition, Original algorithms, Pattern recognition, Pattern recognition systems, Plate location, Search area, Signal processing, Turkey, Turkishs
Kaynak
2009 IEEE 17th Signal Processing and Communications Applications Conference
WoS Q Değeri
N/A
Scopus Q Değeri
N/A
Cilt
Sayı
Künye
Tamer, E., & Cizmeci, B. (2009). A different approach for license plate recognition system. Paper presented at the 2009 IEEE 17th Signal Processing and Communications Applications Conference, 357-360. doi:10.1109/SIU.2009.5136406
