Modified Circular Fuzzy Segmentor and Local Circular Encoder to Iris Segmentation and Recognition
Journal Title: International Journal of Intelligent Engineering and Systems - Year 2017, Vol 10, Issue 2
Abstract
Currently a lot of biometric procedures are being developed based on different features and algorithms. Nevertheless, it is known that, from all of these techniques, iris recognition is one of the most promising for high security applications. In this paper, a novel scheme is proposed to iris segmentation and recognition in iris based biometric system. In the new scheme, we use the modified circular fuzzy segmentor (MCFS) model to segment the pupil and iris inner boundary. After that, a binary encoder based feature extraction scheme named as LCE is proposed to extract the significant features to do the iris recognition process. Once feature extraction scheme is done by the LCE operator, the iris recognition is done through fuzzy logic classifier. We use three datasets from widely used iris databases (CASIA, MMU and UBIRIS) to analyze the increase of the error rates when the iris is inaccurately segmented. We selected 780 images of the CASIA, MMU and UBIRIS databases that the used segmentation algorithm can accurately segment. From the experimentation results, the proposed method of MCFS+LCE is outperformed than the existing methods.
Authors and Affiliations
Emmanvel Chirchi
Keywords
Related Articles
- EP ID EP229422
- DOI 10.22266/ijies2017.0430.20
- Views 84
- Downloads 0
Test Case Generation for Real-Time System Software Using Specification Diagram
Software testing of the real-time system (RTS) software based on specification diagram has a necessary sequence of parallel events for generation of test cases. In the model-based test case generation for RTS both automa...
Grey Fuzzy Neural Network-Based Hybrid Model for Missing Data Imputation in Mixed Database
Nowadays, the missing data imputation is the novel paradigm to replace with the imputed value of the missing attribute. The missing data occurs due to bias information, non-response of the system. In the medical domain,...
Optimal Decision Tree Based Unsupervised Learning Method for Data Clustering
Clustering is an investigative data analysis task. It aims to find the intrinsic structure of data by organizing data objects into similarity groups or clusters. Our investigation using a pattern based clustering on nume...
Fuzzy Sliding Mode Controller of DFIG for Wind Energy Conversion
Wind turbine based on Doubly-Fed Induction Generator (DFIG) is gaining in the growing wind market. This paper describes a design method for the fight control of doubly-fed induction generator (DFIG) based on fuzzy slidin...
Multi Agent Based Diabetes Diagnosing and Classification with the Aid of Hybrid Firefly-Neural Network
A multi agent distributed data mining system for diagnosing diabetes and classification is proposed. Here we are introducing four agents namely user agent, connection agent, updation agent, and security agent. In which e...