An Adaptive Car Number Plate Image Segmentation Using K-Means Clustering

Izdanje: Sinteza 2018 International Scientific Conference on Information Technology and Data Related Research

DOI: 10.15308/Sinteza-2018-74-78

Oblast: Internet and Cloud Computing

Stranice: 74-78

Apstrakt:
This paper provides an implementation of K-means clustering algorithm in order to segment a car number plate digital image into regions. Some spatial information from a histogram-based windowing process are used, while the user specifies the number of clusters in a dataset and a distance metric to quantify how close two objects in digital image are to each other. Some examples on image segmentation and plate localization for different number of clusters, are illustrated and used in plate characters recognition process.
Ključne reči: cluster, data partitions, digital image, K-means algorithm, edge detector.
Priložene datoteke:
  • 74-78 ( veličina: 1001,24 KB, broj pregleda: 581 )

Preuzimanje citata:

BibTeX format
@article{article,
  author  = {H. Stefanović, R. Veselinović, G. Bjelobaba and A. Savić}, 
  title   = {An Adaptive Car Number Plate Image Segmentation Using K-Means Clustering},
  journal = {Sinteza 2018 International Scientific Conference on Information Technology and Data Related Research},
  year    = 2018,
  pages   = {74-78},
  doi     = {10.15308/Sinteza-2018-74-78}
}
RefWorks Tagged format
RT Conference Proceedings
A1 Hana Stefanović
A1 Radosav Veselinović
A1 Goran Bjelobaba
A1 Ana Savić
T1 An Adaptive Car Number Plate Image Segmentation Using K-Means Clustering
AD Univerzitet Singidunum, Beograd, Beograd, Srbija
YR 2018
NO doi: 10.15308/Sinteza-2018-74-78
Unapred formatirani prikaz citata
H. Stefanović, R. Veselinović, G. Bjelobaba and A. Savić, An Adaptive Car Number Plate Image Segmentation Using K-Means Clustering, Univerzitet Singidunum, Beograd, 2018, doi:10.15308/Sinteza-2018-74-78