Modified Bird swarm algorithm for edge detection in noisy images using fuzzy reasoning

ABSTRACT

A new bio-inspired edge detection approach is proposed to deal with the noisy images using a combination of bird swarm algorithm (BSA) and fuzzy reasoning. BSA is based on the behaviour of the birds. The birds fly through each pixel while they forage for the food and detect the edge pixels and noisy pixels that fall in their path. The direction in which the birds fly is found using fuzzy rule-based system. The pixels are classified as edge and non-edge pixels using the concept of thresholding. The noisy pixels are removed by the birds using fuzzy impulse noise detection and reduction method. The technique has been evaluated on two standard image datasets for quantitative and qualitative analysis. The results clearly indicate significant improvement over the other bio-inspired approaches, namely, Genetic Algorithm (GA), Particle Swarm Optimisation (PSO), Ant Colony Optimisation (ACO), Bacterial Foraging Algorithm (BFO), Deep Learning approach, fuzzy with BFO for noisy images, Neuro-fuzzy approach and PSO particularly for images having impulse noise in terms of Entropy, Kappa Value, Pratt’s Figure of Merit (FoM) and Structural Similarity Index Measure (SSIM). The proposed approach works well to detect the continuous, thin and smooth edges in the presence of 5–40% noise density.

KEYWORDS:

• Bird swarm algorithm
• edge detection
• impulse noise
• fuzzy reasoning

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Notes on contributors

Jyotika Pruthi

Jyotika Pruthi received her B.Tech degree in Computer Science and Engineering from Maharshi Dayanand University, Rohtak, India in 2011, M.Tech degree in Computer Science from Banasthali University, Rajasthan, India in 2013 and is pursuing PhD from The NorthCap University, Gurgaon, India. She has over 5 years of teaching and research experience. Her research interests include image processing, artificial intelligence and machine learning. She has published more than 15 papers in various conferences of international repute. She has won best paper award in a conference held at JNU, New Delhi and has been awarded thrice for being the best presenter by IET, UK.

Shaveta Arora

Dr. Shaveta Arora received her BTech degree in Instrumentation and Control Engineering with Hons. from Kurukshetra University, Haryana, India in 2001, M.Tech degree from Punjab Technical University, Punjab, India in 2007 and PhD degree from The Northcap University, Gurgaon, India, in 2017. She has over 16 years of teaching and research experience at undergraduate, postgraduate and doctoral level in NBA accredited programs. Her research interests include signal and image processing, fuzzy sets and information sets. She has published more than 20 research papers in various journals and conferences of international and national repute.

Kavita Khanna

Dr Kavita Khanna is, at present, an associate professor and head of Computer Science & Engineering Department with The NorthCap University, Gurgaon, Haryana. She has 18 years of teaching experience during which she has published more than 30 research papers and guided 21 M.Tech students in their research work. Her research areas include artificial neural networks, computer graphics, digital image processing, and design and analysis of algorithms. She has done her PhD from Guru Gobind Singh Indraprastha University, Delhi Apart from that she is working as a Radio Jockey with All India Radio FM Gold.