DSpace JSPUI
DSpace preserves and enables easy and open access to all types of digital content including text, images, moving images, mpegs and data sets
Learn More
Please use this identifier to cite or link to this item:
http://repository.potensi-utama.ac.id/jspui/jspui/handle/123456789/5624Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Rosnelly, Rika | - |
| dc.date.accessioned | 2023-04-27T14:44:02Z | - |
| dc.date.available | 2023-04-27T14:44:02Z | - |
| dc.date.issued | 2020-10-24 | - |
| dc.identifier.uri | http://repository.potensi-utama.ac.id/jspui/jspui/handle/123456789/5624 | - |
| dc.description | The development of science and technology related to data and statistical analysis of biological data (biometrics) is growing rapidly. Much electronic equipment can help relieve human tasks. Refers to biometrics technology, the technology aims to measure and analyze human characteristics such as face patterns mainly used for face recognition processes. A person reading face characteristics needs reader equipment, as a database capable of storing face pattern data and software that analysis such data[1]. Face recognition system as identity verification has been developed and produced various algorithms for digital imagery process, and then it takes algorithms that can recognize faces. Research on face recognition was conducted using Principal Component Analysis (PCA) with a successful percentage of face recognition processes of 82.81%. Some of the factors that influence the success of recognition are exposure to the face, the distance of the face with the webcam, the number of images of people's faces stored, and the performance of the computer used [2]. Other research on face recognition using the eigenface algorithm yielded an average match percentage of 88% when the database contained 10 face data, results, while at the time the database amounted to 20 face data, the average match percentage result reached 52%. The cause of the difference in results is due to exposure factors, distance, face shape, and the amount of data available [3]. Other research on face recognition using the Hidden Markov Model (HMM) and Fast Fourier Transform (FFT) methods with test results by recalling the accuracy rate is 41%, and overall testing is 36%. Accuracy depends heavily on clustering capabilities [4]. Other research on face recognition uses the deep neural networks method Convolutional Neural Networks (CNN) as real-time face recognition that has proven to be highly efficient in face classification[5]. The results of the trial using the construction of the Convolutional Neural Networks model into 7 layers with inputs from extended local binary pattern extraction results with a radius of 1 and neighbor 15 showed face recognition performance achieved an average accuracy rate of more than 89% in ∓ 2 frames per second [6]. Research on face recognition algorithms is quite numerous and varied, but they all have the same three basic stages the face detection, test face feature extraction, and face recognition[4]. A biometric verification system has two kinds of errors, namely errors in receiving a false acceptance rate (FAR) and errors in rejecting a false rejection rate (FRR). FAR and FRR are functions of the threshold value (t) [7]. In general, face recognition systems are divided into two types, namely feature-based systems and image-based systems [8]. In the feature-based system, features are used to extract from face imagery components such as the eyes, nose, mouth, etc. [9], which are then geometrically modeled on the relationship between them. In contrast, the image-based system uses raw information from image pixels, which is then represented in the Principal Component Analysis (PCA) method or wavelet transformation[10]. Based on research and consideration of the causative factors of differences in previous match results, the authors conducted research on face recognition using the eigenface algorithm [11]. The eigenface algorithm is a collection of eigenvectors used for face recognition using the help of laptop cameras[12]. | en_US |
| dc.description.abstract | The eigenface algorithm is a collection of eigenvectors used for face recognition through computers. The face recognition system is part of image processing that recognizes faces based on imagery that is stamped and stored in an image file in JPEG format. Face recognition problems can be solved through the implementation of an algorithm. The algorithm used in this study is the eigenface algorithm. The input image is stamped through a laptop camera with a size of 320 pixels x 240 pixels and reduced to 100 pixels x 100 pixels to be saved as a master file of the face with various facial expressions is a forward-facing position without a smile, facing forward a thin smile, facing forward with a big smile, head tilted to the left, and head tilted to the right. The purpose of this research is to build face recognition software using eigenface algorithms. The results showed that faces could be recognized using the eigenface algorithm with an average accuracy rate of 85% | en_US |
| dc.publisher | CITSM2020 | en_US |
| dc.subject | Camera, Image, Eigenface, Pixel, Face | en_US |
| dc.title | Face Recognition Using Eigenface Algorithm On Laptop Camera | en_US |
| dc.type | Other | en_US |
| Appears in Collections: | A Paper | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 22. Face Recognition Using Eigenface Algorithm on Laptop Camera 2020.pdf | 1.01 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.