Flexible edge detection and its enhancement by smell bees optimization algorithm

Edge detection still nowadays a complex challenge since the intrinsic proprieties of an image vary from one case to another. Thus, capturing the semantic content of an image relies only on the human interpretation. In this paper, a novel edge detection algorithm is proposed. Compared to usual edge d...

Full description

Saved in:
Bibliographic Details
Published in:Neural computing & applications 2021-08, Vol.33 (16), p.10021-10041
Main Author: Mohamed Ben Ali, Yamina
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Data Mining and Knowledge Discovery
Detectors
Edge detection
Image Processing and Computer Vision
Optimization
Original Article
Probability and Statistics in Computer Science
Smell
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Edge detection still nowadays a complex challenge since the intrinsic proprieties of an image vary from one case to another. Thus, capturing the semantic content of an image relies only on the human interpretation. In this paper, a novel edge detection algorithm is proposed. Compared to usual edge detectors based on derivative filters, the idea behind the proposed algorithm is to extract edges by exploiting only information present in the image itself without need of any extra information. The used detection process is composed of two main phases, smoothing the image and extracting edges. Besides the simplicity of its implementation, the detection algorithm CMAX is doted to more flexibility enabling us to decide on the degree of details embedded in each region of the image independently. Also, as a complementary phase, the quality of detection can be improved by using an optimization approach based on the nature-inspired algorithm smell bees optimization. The quantitative evaluation results of CMAX before and after enhancement and their comparison with others well-known detectors are done by using the benchmark of Berkeley images.
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-021-05769-2