![Open Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltextgreen.png)
![Restricted Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltextred.png)
![Open Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltextgreen.png)
![Open Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltext_open_medium.gif)
![Restricted Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltextred.png)
![Restricted Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltext_restricted_medium.gif)
Attendance System Based on Face Recognition using Recurrent Neural Network
Subscribe/Renew Journal
Background---Face recognition within the classrooms in the challenging task in the field of Face detection system. Event of the certain detection process represents the various parameters such as, skin color, pixel range. The proposed work implies the tracking of the students which is followed by the automatic attendance system that implies in the automatic attendance using the face recognition technique. More images can be analyzed using the deep learning methods which yield the presence of student and automatic attendance can be registered. This can lead towards change in automatic attendance system with the accurate prediction.
Method---The face recognition depends upon the basic image processing techniques. The image acquisition stage involves the collection of database as in the video format or in the live data stream. The pre-processing stage is carried out using the background subtraction technique using the binary conversion technique. Histogram optical flow and Local Binary pattern is carried out for the segmentation of face images. Features are extracted and stored from the segmentation process. Training process is carried out using Convolutional Neural Network (CNN) classifier.
Results---The trained and the tested phase of the proposed work maintains the accuracy rate of 87.63% with the reduction in the sensitivity and the specificity range of 72.5 and 86.2% . The experimental results is carried out using the MATLAB domain which use the OS generic platform that yields the lesser error rate and higher accuracy of classification.
Keywords
![](https://i-scholar.in/public/site/images/abstractview.png)
Abstract Views: 189
![](https://i-scholar.in/public/site/images/pdfview.png)
PDF Views: 1