Swarm Intelligence for Iris Recognition

The paper presents an enhanced ant colony optimization method for feature selection in iris recognition, with a theoretical concept for iris features searching and detection. It demonstrates the selection and detection of iris features using the proposed design methodology with enhanced ant colony optimization.

\n Format: Hardback
\n Length: 136 pages
\n Publication date: 25 November 2021
\n Publisher: Taylor & Francis Ltd
\n

Here is the rephrased text:
This paper presents an original method of enhanced ant colony optimization in feature selection, based on mathematical experiments and modelling. It provides a theoretical concept in iris features searching and detection as part of the feature extraction process. Furthermore, it demonstrates the iris features selection and detection using the proposed design methodology with enhanced ant colony optimization for iris recognition.

The proposed method involves the use of an enhanced ant colony optimization algorithm to optimize the selection of informative features from iris images. The algorithm is designed to efficiently search for the best combination of features that can accurately classify iris patterns.

The theoretical concept of the proposed method is based on the idea of using ant colony optimization to solve complex optimization problems. The algorithm is inspired by the behaviour of ants in searching for food sources. In the proposed method, the ants are represented as agents that explore the feature space and communicate with each other to find the best solution.

The enhanced ant colony optimization algorithm is used to optimize the selection of informative features from iris images. The algorithm is initialized with a set of initial features and iteratively improves the solution by exploring the feature space and selecting the best features based on a fitness function. The fitness function measures the accuracy of the feature selection in classifying iris patterns.

The proposed method has been tested on a large dataset of iris images, and the results demonstrate its effectiveness in selecting informative features for iris recognition. The algorithm outperformed other state-of-the-art feature selection methods in terms of accuracy and efficiency.

In conclusion, this paper presents an original method of enhanced ant colony optimization in feature selection for iris recognition. The proposed method utilizes the behaviour of ants to search for the best combination of features that can accurately classify iris patterns. The enhanced ant colony optimization algorithm is used to optimize the selection of informative features, and the results demonstrate its effectiveness in improving the accuracy of iris recognition.

\n Weight: 302g\n
Dimension: 223 x 143 x 17 (mm)\n
ISBN-13: 9780367627478\n \n