Abstract
The main weakness of the k-Nearest Neighbor algorithm in face recognition is calculating the distance and sort all training data on each prediction which can be slow if there are a large number of training instances. This problem can be solved by utilizing the priority k-d tree search to speed up the process of k-NN classification. This paper proposes a method for student attendance systems in the classroom using facial recognition techniques by combining three levels of Discrete Wavelet Transforms (DWT) and Principal Component Analysis (PCA) to extract facial features followed by applying the priority of k-d tree search to speed up the process of facial classification using k-Nearest Neighbor. The proposed algorithm is tested on two datasets that are Honda/UCSD video dataset and our dataset (AtmafaceDB dataset). This research looks for the best value of k to get the right facial recognition using k-fold cross-validation. 10-fold cross-validation at level 3 DWT-PCA shows that face recognition using k-Nearest Neighbor on our dataset is 95.56% with k = 5, whereas in the Honda / UCSD dataset it is only 82% with k = 3. The proposed method gives computational recognition time on our dataset 40 milliseconds.
Highlights
Facial recognition performance is influenced by several variables, including pose, expression, lighting, and occlusion [1].Many educational institutions in Indonesia continue to use attendance sheets, allowing students to cheat by asking friends to sign their names
We propose a combination of face recognition methods using three levels of Discrete Wavelet Transforms (DWT) and Principal Component Analysis (PCA) to extract facial features followed by applying k-d tree to accelerate the process of facial classification using k-nearest neighbor (k-NN)
The combination of methods for student attendance systems in the classroom was proposed by [11] using facial recognition techniques by incorporating Discrete Wavelet Transforms (DWT) and Discrete Cosine Transform (DCT) to extract the facial features of students followed by applying Radial Basis Function (RBF) to classify face objects
Summary
Facial recognition performance is influenced by several variables, including pose, expression, lighting, and occlusion (namely, glasses, mustaches, beards, headgear, etc.) [1]. The use of attendance sheets has proven to be time-consuming, unreliable, inaccurate, and inefficient. Based on this issue, we propose a combination of face recognition methods using three levels of Discrete Wavelet Transforms (DWT) and Principal Component Analysis (PCA) to extract facial features followed by applying k-d tree to accelerate the process of facial classification using k-NN. The k-NN process with Euclidean distance is used to identify students’ presence through pictures or video of a student’s face By using this approach, it is possible that automatically integrated systems between IP camera and pc or notebooks will determine whether each student is present or absent and will be recognized in the group of courses followed. The paper is structured as follows: Section 2 consists of related research discussions, Section 3 consists of the proposed research method, Section 4 presents the results of research and analysis, and Section 5 offers some conclusions
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call