Abstract
In this paper, we present a new method based on the use of information provided by the gradient methods for determining the geometric parameters of objects with high accuracy. The algorithm is based on the use of data obtained after image processing by gradient filters. Also, it reacts to the slightest change in the contours of objects of the dynamic image scenes. Repeated experiments using more than 5000 real images were processed to improve the theory. Given a high refresh rate of modern systems, a position of the Center Of Gravity (COG) in the dynamic images is changing gradually even for rapid motion. Using this feature, COG for each frame of a training sample is defined under various threshold values by means of an algorithm. A number of elements (frames) in the training sample are selected depending on the type of the dynamic object, a task set and on the initial conditions. The suggested method is recommended for further use by the expert system, in parallel with its own operation, with a goal to maintain a threshold value on the optimal level in case of dynamic perturbing factors. After the research, we found that the prediction accuracy increased that essentially improved results. A number of experiments demonstrated increasing the accuracy of determination of the center of blurred objects. Also, we have eliminated the human factor. All of the calculations are done automatically. These data are very useful and important for all areas of science where high accuracy of the results is necessary.
Highlights
In computer vision, image segmentation is the process of partitioning a digital image into multiple segments
For simulation of the method, the integrated software development environment Delphi Code Gear RAD Studio by Borland Corporation is used, because it offers the widest possibilities for producing software products for most platforms
The program can determine a maximal range for threshold values
Summary
Image segmentation is the process of partitioning a digital image into multiple segments. Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.) in images. Image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain characteristics. Parameters of the whole system depend on the accuracy and rate of selecting a necessary threshold value. This problems has a special significance today, because modern systems tend to process huge arrays of information in real time while preserving high accuracy [3,4,5,6]. The inadequacy of classic methods [7] for efficient threshold determination is related to the diversity of image types and, sometimes, their low contrast, and selection of a threshold value by an operator significantly decreases the system performance, accuracy, stability and independence
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
