Journal Article

IrisSeg-drunk: enhanced iris segmentation and classification of drunk individuals using Modified Circle Hough Transform

Bellary, Sreepathi, Jayadev, Puneeth Guddhur

2024

Overview

The field of biometrics has become increasingly intriguing due to the significant amount of research being conducted on Iris Recognition (IR) in recent years. It has been observed that alcohol consumption can cause deformation in the iris pattern, resulting from the dilation or constriction of the pupil, which can potentially impact the performance of IR. To address these issues, this paper proposes an efficient iris segmentation model that incorporates a Modified Circle Hough Transform (MCHT) for clustering individuals under the influence of alcohol. The proposed model consists of several steps, namely noise reduction, iris segmentation, pupil segmentation, and clustering of individuals into drinker and non-drinker categories. Initially, input images are obtained from a database. To reduce noise in the images, a Median Filtering (MF) technique is employed. The Canny mathematical morphology (CMM) algorithm is then utilized to segment the iris region from the noise-free image. Subsequently, the MCHT algorithm is applied to perform pupil segmentation based on the segmented iris image. This modification enhances the accuracy and robustness of the system. Finally, the Matrix-Based Clustering (MBC) technique clusters individuals into the drunk and non-drunk categories. The experimental results of the proposed method show that it performs better than other state-of-the-art models, indicating its superior performance. In conclusion, this paper introduces an effective iris segmentation model incorporating the Modified Circle Hough Transform (MCHT) for clustering individuals based on their alcohol consumption. The proposed approach demonstrates enhanced accuracy and robustness compared to existing models, as evidenced by the experimental outcomes.

• Publisher: Springer International Publishing,Springer Nature B.V
• Subject: Accuracy / Algorithms / Artificial Intelligence / Biometric recognition systems / Circles (geometry) / Clustering / Computer Science / Computer Systems Organization and Communication Networks / Data Structures and Information Theory / Hough transformation / Image filters / Image segmentation / Mathematical morphology / Mathematics of Computing / Noise reduction / Pupils / Robustness / Software Engineering/Programming and Operating Systems / Theory of Computation