Open Access Open Access  Restricted Access Subscription or Fee Access

Automatic Face Tracking and Attendance System Using Machine Learning Techniques

Ranjan Rufus Rozario S, Manjunatha Hiremath


The human face is the most significant part of our identity. It plays a very important role in daily communication, interaction and other routine habits in our lives. The main advantage of facial detection over many other biometric systems is the uniqueness of the subject. The human face has a very high rate of variability and hence this makes its detection and/or tracking a difficult problem in computer vision. Hence, face detection and tracking algorithms are necessary for human computer interaction, intrusion detection (Security), etc. Extensive research is being done in this field. In this research work, the face detection and recognition is experimented with improved Viola Jones and FLD algorithms. Further, this detection is extended to tracking in real-time video using an improved KLT algorithm. The experimental results shows 98.63% recognition and tracking accuracy. To show the real time performance of these enhanced algorithms, the automatic attendance system is considered as an application. Attendance is provided to the students present in the image captured and processed using the proposed algorithms. Since the use of machine learning has been widely accepted, the proposed recognition algorithm uses machine learning techniques to train the system and recognise the students present in the image. The proposed approach uses the technique of increasing the efficiency at every level of the system. Efficiency is increased at the face detection, face recognition and the face tracking phase of the system. Hence, this substantially increases the overall performance of the system.


Face Detection, Face recognition, Face Tracking, Attendance system, Viola Jones, KLT, FLD, Machine learning.

Full Text:


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.