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




Abstract:
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.

CITATION:

IEEE format

H. Stefanović, R. Veselinović, G. Bjelobaba, A. Savić, “An Adaptive Car Number Plate Image Segmentation Using K-Means Clustering,” in Sinteza 2018 - International Scientific Conference on Information Technology and Data Related Research, Belgrade, Singidunum University, Serbia, 2018, pp. 74-78. doi:10.15308/Sinteza-2018-74-78

APA format

Stefanović, H., Veselinović, R., Bjelobaba, G., Savić, A. (2018). An Adaptive Car Number Plate Image Segmentation Using K-Means Clustering. Paper presented at Sinteza 2018 - International Scientific Conference on Information Technology and Data Related Research. doi:10.15308/Sinteza-2018-74-78

BibTeX format
Download

RefWorks Tagged format
Download