This paper presents a novel color texture-based method for
object detection in images. To demonstrate our technique, a vehicle
license plate (LP) localization system is developed. A support vector
machine (SVM) is used to analyze the color textural properties of LPs.
No external feature extraction module is used, rather the color values of
the raw pixels that make up the color textural pattern are fed directly to
the SVM, which works well even in high-dimensional spaces. Next, LP
regions are identified by applying a continuously adaptive meanshift
algorithm (CAMShift) to the results of the color texture analysis. The
combination of CAMShift and SVMs produces not only robust and but
also efficient LP detection as time-consuming color texture analyses for
less relevant pixels are restricted, leaving only a small part of the input
image to be analyzed.