Kennedy O. Okokpujie

An Improved Iris Segmentation Technique Using Circular Hough Transform

It is quite easy to spoof an automated iris recognition system using fake iris such as paper print and artificial lens. False Rejection Rate (FRR) and False Acceptance Rate (FAR) of a specific approach can be as a result of noise introduced in the segmentation process. Special attention has not been paid to a modified system in which a more accurate segmentation process is applied to an already existing efficient algorithm thereby increasing the overall reliability and accuracy of iris recognition. In this work an improvement of the already existing wavelet packet decomposition for iris recognition with a Correct Classification Rate (CCR) of 98.375% is proposed. It involves changing the segmentation technique used for this implementation from the integro-differential operator approach (John Daugman’s model) to the Hough transform (Wilde’s model). This research extensively compared the two segmentation techniques to show which is better in the implementation of the wavelet packet decomposition. Implementation of the integro-differential approach to segmentation showed an accuracy of 91.39% while the Hough Transform approach showed an accuracy of 93.06%. This result indicates that the integration of the Hough Transform into any open source iris recognition module can offer as much as a 1.67% improved accuracy due to improvement in its preprocessing stage. The improved iris segmentation technique using Hough Transform has an overall CCR of 100%.

Comparative Analysis of Fingerprint Preprocessing Algorithms for Electronic Voting Processes

Fingerprints have been used for a long time as a very adequate method of distinguishing people. Matching fingerprints can be very difficult without a good algorithm for the scanners. Complexities especially during the verification phase can arise from problems with the algorithm scanners use. In elections and other forms of voting, security and proof of individuality remain some of the biggest obstacles to be surmounted. This paper proposes an ideal algorithm which could solve these challenges. The Zhan-Suen Thinning Algorithm and the Guo-Hall Parallel Thinning Algorithm were compared using standard parameters from the perspective of fingerprint technology and electoral requirements to deduce the better algorithm. MATLAB® was used for the comparative performance analysis of the two algorithms. The time taken to complete iterations, quality of output produced and reliability were the parameters used to carry out the comparative performance analysis of the two algorithms. The better algorithm, Guo-Hall’s was recommended for implementation on e-voting systems. Guo-Hall’s algorithm is very effective and has the capacity to curb electoral fraud when adopted in e-voting process.

Automatic home appliance switching using speech recognition software and embedded system

In most homes, electrical appliances are controlled and operated manually, this could be difficult and challenging to do when tiredness, handicap, morphological variations (height, aging etc.) and inadequate skill stands in the way as impediment. This study aims to implement a better and more flexible means of controlling home appliances by means of an automated switching mechanism using speech recognition technique. Acoustic signals picked by a microphone controlled by a speech recognition application generate digital signals that are passed to a microcontroller, which in turn dispatches commands that operate the relays to which the appliances in the home are connected. The goal of using speech command to automate the switching of home appliances was achieved and proved to be a more convenient means of switching home appliances.

Development of a facial recognition system with email identification message relay mechanism

Attendance records play a vital role in the educational sector. It is so vital that students are not allowed to sit for examinations if they do not meet the class attendance benchmark. But students, instead of making sure they attend classes regularly, devise cunny ways of committing attendance fraud. This unpleasant trend has made it necessary to develop systems that can take accurate class attendance records and minimize fraud. The use of biometrics to develop attendance taking systems is becoming quite popular. One of such biometrics is The Face. In this paper, a facial recognition algorithm known as Fisherfaces or Fisher Discriminant Analysis (FDA) which is not sensitive to substantial variation in facial look and illumination is used to develop the facial recognition attendance taking system. The system implemented has a training database of Ten (10) students. Ten (10) facial images of each student are taken with different composures, looks and under different levels of illumination. Tests on nine (9) students in the database yielded accuracies of as low as 70% and as high as 90%. This validates the proof that the more the number of training facial image in the database, the higher the accuracy of Fisherfaces approach. The simple mail transfer protocol (SMTP) was interfaced with the database to send identification messages (name of student identified with time and date of identification) to the email address of the administrator (in this case the lecturer) in real-time to effectively monitor the attendance. The result was found capable of eliminating attendance fraud.

Integration of Iris Biometrics in Automated Teller Machines for Enhanced User Authentication

The ubiquitous Automatic Teller Machine that revolutionized the way monetary transactions are carried out the world over is currently riddled with several security challenges. Top on the list of these challenges are the thefts and frauds associated with the ever popular Personal Identification Number based automatic teller machines. A lot of suggestions and proposals have been made in recent times, on how to combat the menace of automatic teller machine frauds. Biometrics is one of the most promising tools that have the capacity to put the nefarious activities around automatic teller machines in check. This paper proposes a cheap and economic iris biometric based automatic teller machine, built around a microcontroller, iris scanner and a robust database. The designed and implemented prototype is capable of checkmating automatic teller machine fraud and it is also easy to implement in developing nations.

Fingerprint Biometric Authentication Based Point of Sale Terminal

Retail businesses that are not transacted online still represent a substantial amount of retail deals that are closed on a daily basis. Retail business owners and customers continue to explore other means of ensuring payments made with Point of Sale (POS) devices are done securely. This paper proposes the incorporation of fingerprint biometric recognition as an additional layer of protection to the customary pin and password requirements to gain permission to pay for goods purchased and services rendered using point of sale devices. The proposed fingerprint biometric recognition point of sale device has zero false match and false non-match rate. This strengthens the present authentication process that makes use of pins and passwords that are prone to fraud and solidifies the trust and confidence users place on point of sale devices.

Development of an Electronic Fare Collection System Using Stationary Tap-Out Devices

The peculiar nature of emerging economies means that established technology must be developed with the constraints and limitations of these locations in view. This paper presents the development of an Electronic Fare Collection system using Contactless smart cards. Electronic fare collection system are commonly integrated with public transit networks such as the bus Rapid Transit (BRT) and Light Rail Transit (LRT) services in major cities worldwide. However, in deploying such systems in an emerging economy like Nigeria, unique consideration has to be given with regards to power management, robustness and availability. The system developed consists of a mobile tap-in device connected to a bus, a stationary tap-out device to be situated at a specific bus stop and a web server on the cloud for coordination and off site monitoring. The stationary tap-out device used consists of a proximity card reader (or an RFID reader) connected to a computing unit linked with a display, outdoor power provision (source) and data transmission capability. A program was developed to capture data from randomly applied proximity cards (or RFID cards) and to transmit same periodically to a remote location for use by the system. The system developed is able to sustain itself for a long period of time from available power supply, it also proves robust enough from a software and hardware perspective. Lastly its availability is proven even when data transmission capability proves erratic.