A Novel Hybrid Metaheuristic Approach to Perceive the Gender Based Identification System

Background: Gender recognition is one of the most challenging perceptible tasks, which is gaining attention in the increasing digital data era as the requirement of a personalized, reliable and ethical system inevitable. A problem that we address in this paper greatly deals with the gender based identification system. We are motivated by this problem as many recent social interactions and existing services rely on the gender of an individual, and also in forensic identification, the gender information provides the feasibility for easy and quick investigation. Objective: The paper primarily focused on the gender based identification problem and culminated a robust gender based recognition system with a higher accuracy rate. We attempted to perceive the gender of an individual through the multimodal biometric system by integrating the three prominent biometric traits namely: fingerprint, palm-print and hand in a specific manner. The proposed multimodal biometric for gender recognition system provides a better accuracy rate improvement with the optimal feature set which is generated from available high dimensional features set. Methods: Aiming for the objective to reduce the search space, a hybrid meta-heuristic approach GSA-Firefly (GFF) is introduced in this paper. The optimization approach GFF is proposed to retrieve the optimal number of features from the high dimensional features generated by fusing the texture features of all the three considered biometric traits along with the fingerprint minutiae features. Furthermore, the decision tree classifier is used to classify the gender of an individual. Results: The feasibility of the proposed approach is measured with different qualitative performance parameters. In light of achieving the accuracy rate of 99.2%, it shows that its performance is comparatively better against other techniques reported in the literature with the different sets of the classifier. Conclusion: The hybridization technique that effectively integrates meta-heuristic approaches, GSA and firefly, outperforms other similar approaches with respect to obtaining the optimal features of multimodal biometric for the gender based identification system. Furthermore, the novel technique enhances the overall performance of the system by reducing the search space over time and space.