Canny optimisation of the dynamic image colour automatic segmentation algorithm
by Li Song
International Journal of Computer Applications in Technology (IJCAT), Vol. 69, No. 3, 2022

Abstract: Aiming at the current dynamic image colour automatic segmentation algorithm in image segmentation, there are problems of missing image edge information, poor clarity, large impact noise, and low-image segmentation accuracy. A Canny-optimised automatic colour segmentation algorithm for dynamic image is proposed. Noise in dynamic images is filtered by a switch-type median filter using a Laplacian operator test. Three primary colour features of the dynamic image edge were extracted by the compensation algorithm, and the edge dynamic image weighted fusion was completed based on the primary colour feature. The Canny operator is used to optimise the concave research method, analyse the dynamic image gradient amplitude histogram, select the adaptive double threshold value as the best threshold according to the image characteristics, and realise the automatic dynamic image colour segmentation based on the best segmentation threshold. The results show that the proposed algorithm has complete image edge information and good segmentation effect, and can effectively filter out impact noise and improve the accuracy of image segmentation.

Online publication date: Mon, 19-Dec-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computer Applications in Technology (IJCAT):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com