Face Recognition Using Fisherface Method

Anggo, Mustamin; Arapu, La

doi:10.1088/1742-6596/1028/1/012119

Cited by 61 publications

(24 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Adobe Photoshop Cs4 program is used for preprocessing of image. The results claims, 93% of accuracy on 73 test image with the indication of the reasons of failure as scaling factor and pose [5].…”

Section: Literature Review On Different Approaches Of Face Recognmentioning

confidence: 89%

Transition from Holistic to Deep learning Face Recognition Methods

Sabeenian*¹,

Harirajkumar²,

Cruz³

2019

IJRTE

View full text Add to dashboard Cite

Face recognition, the fastest growing biometric technology of computer vision, made a breakthrough in the field of security, healthcare, access control and marketing etc. This technology helps in automatically discern and identify the faces for authentication by comparing available digital image of faces. Various algorithms have been developed for enhancing the performance of face recognition system. The face authentication system entails three major steps, face detection, feature extraction and face recognition. This paper provides some of the major milestones of face representation for recognition like holistic learning approach, feature based approach, hybrid approach and deep learning approach. The various techniques under these categories are reviewed. Finally, implemented face recognition using convolution neural network (CNN). In this method, the image is captured through webcam for the dataset preparation. The detection is carried out by CNN cascade, followed by face landmark and face embedding by FaceNet CNN. Recognition of face is performed after training the network. Implemented faces recognition successfully and accurately for smaller dataset.

show abstract

Section: Literature Review On Different Approaches Of Face Recognmentioning

confidence: 89%

Transition from Holistic to Deep learning Face Recognition Methods

Sabeenian*¹,

Harirajkumar²,

Cruz³

2019

IJRTE

View full text Add to dashboard Cite

show abstract

“…In the future, other facial recognition algorithms can be tried, since the LBPH algorithm cannot achieve very high confidence (higher than 80%) and is sensitive to the light condition, although the LBPH algorithm can meet the needs of smart home design. For example, the FisherFace algorithm based on Linear Discriminant Analysis (LDA) is also a popular method of facial recognition [12]. It is also included in the OpenCV package.…”

Section: B Surveillance Systemmentioning

confidence: 99%

IoT Enabled Smart Security Framework for 3D Printed Smart Home

Ansari

Abdulghani

et al. 2020

2020 IEEE International Conference on Smart Internet of Things (SmartIoT)

View full text Add to dashboard Cite

Recently, smart home design using Internet of Things (IoT) technology has become a growing industry. Since security is the most important element of the smart home design, the project aims to design a 3D printed smart home with a focus on the security features that would meet the security design of futuristic real homes. The surveillance system of traditional smart home is separated from the door lock system. This project innovatively integrates and coordinates them through the facial recognition algorithms, which forms the entry system of this design. The overall system can be divided into two subsystems (parts), which are the sensing and actuation system (PART I) and the entry system (PART II). PART I includes various sensors and actuators to ensure the security of home, including combustible gas sensor, air quality sensor and temperature & humidity sensor. When anomalies are detected by sensors, actuators such as ventilator, buzzer and LEDs start to work. In PART II, the PIR motion sensor is utilized to detect the person to activate the facial recognition step. Facial recognition algorithm (LBPH algorithm) is implemented for person classification, which is used in selecting the duration of recording for the surveillance system. The surveillance system could select not to record for the occupants or different levels of recording for each occupant based on the confidence of recognition. The project outcomes a 3D printed smart home with a door lock system, a surveillance system, and a sensing & actuation network, which accomplishes the security features in perception and network layer of IoT system design.

show abstract

“…Another Fisherface experiment was completed by Mustamin Anggo and La Arapu (Anggo, 2018). Following the algorithm proposed by Belhumeur, they created their own version of the Fisherface classifier.…”

Section: Fisher In the Article The Use Of Multiple Measurements In Tamentioning

confidence: 99%

“…This version followed the original structure of the Fisherface algorithm very closely. After running the algorithm through their dataset, they arrived at an accuracy of 93% (Anggo, 2018). This experiment provided an additional source of results from a different face database.…”

Section: Fisher In the Article The Use Of Multiple Measurements In Tamentioning

confidence: 99%