Application of Chaos Cuckoo Search Algorithm in computer vision technology
Image segmentation is an essential phase in image analysis and computer vision. In computer vision, image processing denotes the analysis and handling of digital images to enhance their quality. Image processing becomes more challenging because of many complexes, noisy images from various sources in...
Saved in:
Published in: | Soft computing (Berlin, Germany) Vol. 25; no. 18; pp. 12373 - 12387 |
---|---|
Main Authors: | , , , |
Format: | Journal Article |
Language: | English |
Published: |
Berlin/Heidelberg
Springer Berlin Heidelberg
01-09-2021
|
Subjects: | |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | Image segmentation is an essential phase in image analysis and computer vision. In computer vision, image processing denotes the analysis and handling of digital images to enhance their quality. Image processing becomes more challenging because of many complexes, noisy images from various sources in selecting applications, requiring minimal computational time/cost procedures and higher accuracy. Hence, in this paper, Chaos Cuckoo Search Algorithm (CCSA) has been suggested to resolve image segmentation and improve image accuracy. An un-deterministic problem is the challenge of unsure pixel detection and rim formulation for picture segmentation. The use of CV and optimization approaches has reduced the uncertainty about restricted picture characteristics. Ergodicity and stochasticity are formulated in this proposal which fulfill certain pixel and edge detection. Heterogeneous picture patterns solve the insecurity with chaotic maps and an Algorithm of Cuckoo Search. Unlike ordinary cuckoo searches, the chaotic mapping fuses deterministic search and stochastic validations. Chaos belongs to a characteristic of nonlinear models. Chaotic motion ensures homogeneity within a certain range since it has obsessed ergodicity, uncertainty, and stochasticity. The proposed model automates algorithms' settings and delivers optimal parameters for computer vision applications and image segmentation. Furthermore, a local search approach is utilized to enhance the outcomes in the cuckoo search algorithm. The experimental results show that the proposed CCSA model enhances accuracy and reduces uncertainty compared to other existing approaches. |
---|---|
ISSN: | 1432-7643 1433-7479 |
DOI: | 10.1007/s00500-021-05950-8 |