Object detection in the images in industrial process control systems based on salient points of wavelet transform analysis

Abstract

The article considers the task of object detection on the images in industrial process control systems. The task is solved in two stages: image segmentation and matching the images of the segments with the template values. A new method based on wavelet transform salient points detection is proposed for image segmentation. Salient point descriptors are used for image matching; the new method of descriptor construction based on wavelet transform is proposed. The unified mathematical tool of the wavelet transform used for image segmentation and image matching decreases computational load for objects enabling detection tasks solving.