A Robust Hybrid Biometric Face Recognition Payment System 
Yashasvi Mutteneni1, Shirisha Kasireddy2, Anurag Achanta3
1Yashasvi Mutteneni*, Department of Computer Science and Engineering, JNT University, Hyderabad, India.
2Shirisha Kasireddy, Department of Computer Science and Engineering, JNT University, Hyderabad, India.
3Anurag Achanta, Department of Computer Science and Engineering, JNT University, Hyderabad, India.
Manuscript received on February 28, 2020. | Revised Manuscript received on March 22, 2020. | Manuscript published on March 30, 2020. | PP: 5586-5591 | Volume-8 Issue-6, March 2020. | Retrieval Number: F9771038620/2020©BEIESP | DOI: 10.35940/ijrte.F9771.038620
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Modern civilization has always been endeavoring to achieve a cashless and digital society. The emergence of payment methods like cards, net banking, and digital wallets have enabled the possibility of cashless and cardless online and offline payments. However, these payment methods are at the risk of theft and sometimes may require users to memorize different passwords. Biometric Payments may seem like a viable option but, the fingerprints can be spoofed and dirt particles may damage the fragile sensors. Face recognition payments are more frictionless than the present card, mobile and biometric payment systems as they do not require a device to carry out the transaction. It is also reliable, secure and efficient. Hence, saving time for both the customer and retailer. The previous system used Eigenfaces and Euclidean Distance for face recognition payment. Our proposed system uses Haar Cascades for face detection and Local Binary Patterns Histogram(LBPH) for face recognition. Our proposed approach is more efficient with respect to parameters such as noise reduction, threshold, training time, confidence and accuracy as it achieves a higher noise reduction and accuracy with a lower threshold, training time and confidence.
Keywords: Cardless Payment, Face Detection, Face Recognition, Haar Cascades, Local Binary Pattern Histogram, Open CV.
Scope of the Article: Image Processing and Pattern Recognition.