Algorithm Based on Texture for the Recognition of Vehicles` Model


The KIPS Transactions:PartB , Vol. 12, No. 3, pp. 257-264, Jun. 2005
10.3745/KIPSTB.2005.12.3.257,   PDF Download:

Abstract

The number of vehicles are rapidly increased as our society is developed. The vehicle recognition has been studied for a while because many people acknowledged it has critical functions to solve the problems of traffic control or vehicle-related crimes. In this paper a novel method is proposed to recognize vehicle models corresponding makers. Vehicles'' models are recognized based on the texture parameters from segmented radiator region above a number plate. A three-layer neural network was built and trained with the texture features for recognition. The proposed method shows 93.7% of recognition rate and 99.7% of specificity for vehicles'' model.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
H. J. Lee, "Algorithm Based on Texture for the Recognition of Vehicles` Model," The KIPS Transactions:PartB , vol. 12, no. 3, pp. 257-264, 2005. DOI: 10.3745/KIPSTB.2005.12.3.257.

[ACM Style]
Hyo Jong Lee. 2005. Algorithm Based on Texture for the Recognition of Vehicles` Model. The KIPS Transactions:PartB , 12, 3, (2005), 257-264. DOI: 10.3745/KIPSTB.2005.12.3.257.