| Autors: Iliev V., Georgiev, G. P., Tzokev, A. P., Mihaylov, A. M. Title: Method for Classification of Textures Based on Histogram and Random Events Keywords: image analysis; pattern recognition; image Abstract: An image histogram is a set of parameters commonly used to automatically evaluate the image during processing or recognition. When comparing or classifying different images, the histogram data can be analysed as it presents the overall colour or intensity composition of the image. This is very important in case of texture classification as the system must provide sufficient accuracy. In this paper, we present an approach and algorithm for visual analysis of images with different histograms, which can be easily implemented as a software application, improving substantially the image classification after non-destructive testing of vehicle tire’s sidewall. The main contribution of this work is a software product for automated defect detection against a series of images, generated by laser shearography in a tire factory References Issue
|
Вид: пленарен доклад в международен форум, публикация в реферирано издание
