A New Image Edge Detection Method using Quality-based Clustering

Neupane, Bijay; Aung, Zeyar; Woon, Wei Lee

doi:10.2316/p.2012.782-053

Cited by 8 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Along these lines, the conclusive outcome is gotten by shifting the pictures by the Butterworth channel and afterward applying the shrewd edge identification administrator. Neupane et al 41 rationale. 43,44 The steganography technique 45 conceals the secret message using the LSB and extracts the confidential data using an artificial neural network.…”

Section: Related Workmentioning

confidence: 99%

High‐quality steganography scheme using hybrid edge detector and Vernam algorithm based on hybrid fuzzy neural network

Dhawan

Gupta

2021

Concurrency and Computation

View full text Add to dashboard Cite

There has been a developing extension in the utilization of steganography, because of the advancement in utilizing web innovation and interactive media innovation. Subsequently, these days, the data are not made sure about adequately while transmitting it over the system. Data are the most significant resource for the current electronic communication framework. Thus the data security has played a significant job to give protection from unapproved people. Steganography is the technique that provides the solution for this challenge. This article proposes a novel type of steganography strategy in which it uses the hybrid algorithm for higher security and a hybrid fuzzy neural network is utilized for the good quality of stego images. For higher security, this article utilizes the Sobel and Kirsch edge identifier and then the Vernam algorithm utilized for encrypting the secret image. Thereafter this article utilizes the combination of fuzzy logic and neural network for enhancing the quality of stego images. There are various advantages of this technique that it can be utilized in various areas, for example, confidential data communication in the defense sector, medical, electronic governance, banking, communication, and so on. K E Y W O R D Sfuzzy logic, KL divergence, mean square error, neural network, PSNR, Sobel and Kirsch edge detector, structural similarity index, Vernam algorithm tors, which depend on the least significant bit (LSB). 8 The edges of the image show less effect while concealing mystery information, so relying

show abstract

Section: Related Workmentioning

confidence: 99%

High‐quality steganography scheme using hybrid edge detector and Vernam algorithm based on hybrid fuzzy neural network

Dhawan

Gupta

2021

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Other proposals only use expressions related to intensity mean as heuristic information ( [2], [17]). In our work, variance is also included because a pixel with high variance is candidate to be and edge [16].…”

Section: A Initialization Phasementioning

confidence: 99%

New ACO algorithm for image edge detection

Martínez¹,

Buemi²

2014

6th Chilean Conference on Pattern Recognition (CCPR)

View full text Add to dashboard Cite

Ant Colony Optimization (ACO) is a metaheuristic based on real behavior of ants to solve optimization problems. Edge detection plays an important role in image processing. It consists in detecting edges or contours in images which allows to extract information from them. An ACO algorithm to edge detection is proposed. Using heuristic and knowledge information and applying an improvement operator, binary images including edges detected are obtained. The algorithm was tested with several images (real and synthetic, with and without presence of noise). The results reached were competitive in terms of quality of images and required computational time.

show abstract

“…In [11], the authors proposed an edge detection method that uses K-means clustering and different properties of image pixels as features. The qualities of the different clustering results obtained using different number of clusters were analyzed using silhouette indexes in order to choose the best number of clusters.…”

Section: Introductionmentioning

confidence: 99%

Intelligent edge detector based on multiple edge maps

Qasim¹,

Woon²,

Aung³

et al. 2012

2012 International Conference on Computer Systems and Industrial Informatics

Self Cite

View full text Add to dashboard Cite

An intelligent edge detection method is proposed. The method is based on the use of pattern recognition and machine learning techniques to combine the outputs of multiple edge detection algorithms. In this way, the limitations of the individual edge detectors can be overcome and performance enhancement is achieved. Two widely used classification algorithms, the Naive Bayes Classifier and the Multi-layer Perceptron, were selected for the learning task. The proposed system was evaluated on artificial and real images. A simple class labeling system based on the output of all edge detectors is suggested to provide controllability between detection sensitivity and noise resistance. Principal Component Analysis was performed to reduce computational burden and improve detection accuracy. The method is shown to achieve a practical compromise between detection sensitivity, computational complexity, and noise immunity.

show abstract

A New Image Edge Detection Method using Quality-based Clustering

Cited by 8 publications

References 8 publications

High‐quality steganography scheme using hybrid edge detector and Vernam algorithm based on hybrid fuzzy neural network

High‐quality steganography scheme using hybrid edge detector and Vernam algorithm based on hybrid fuzzy neural network

New ACO algorithm for image edge detection

Intelligent edge detector based on multiple edge maps

Contact Info

Product

Resources

About