A Comparative Study of Face Recognition Algorithms under Facial Expression and Illumination

Shinwari, Ali Rehman; Balooch, Asadullah Jalali; Alariki, Ala Abdulhakim; Abdulhak, Sami Abduljalil

doi:10.23919/icact.2019.8702002

Cited by 7 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, on face samples with lighting variation, techniques were proposed that compliment both the traditional and deep learning FR methods reporting improved performance [26,15]. The approaches include pre-processing of the facial samples to normalise any variation, before feeding it to the face recognition algorithm [33,17,50,34,35].…”

Section: Related Workmentioning

confidence: 99%

“…A consideration of the effects of facial pose and other external factors is left to future studies. Specifically for the lighting variation, numerous image pre-processing methods exist to improve the performance of the FR model [35,50,34], but studies exploring the tuning or training of FR models to be robust to lighting variations are relatively rare [5,21].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards End-to-End Neural Face Authentication in the Wild -- Quantifying and Compensating for Directional Lighting Effects

Varkarakis,

Yao,

Corcoran

2021

Preprint

View full text Add to dashboard Cite

The recent availability of low-power neural accelerator hardware, combined with improvements in end-to-end neural facial recognition algorithms provides enabling technology for on-device facial authentication. The present research work examines the effects of directional lighting on a State-of-Art (SoA) neural face recognizer. A synthetic re-lighting technique is used to augment data samples due to the lack of public data-sets with sufficient directional lighting variations. Top lighting and its variants (top-left, topright) are found to have minimal effect on accuracy, while bottom-left or bottom-right directional lighting have the most pronounced effects. Following the fine-tuning of network weights, the face recognition model is shown to achieve close to the original Receiver Operating Characteristic curve (ROC) performance across all lighting conditions, and demonstrates an ability to generalize beyond the lighting augmentations used in the fine-tuning dataset. This work shows that a SoA neural face recognition models can be tuned to compensate for directional lighting effects, removing the need for a pre-processing step prior to applying facial recognition.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Towards End-to-End Neural Face Authentication in the Wild -- Quantifying and Compensating for Directional Lighting Effects

Varkarakis,

Yao,

Corcoran

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Many people get confused between kinship and face recognition systems as they depend on facial image analysis. Face recognition refers to whether two persons are the same or not by individual’s photograph comparison with album photograph ( Shinwari et al, 2019 ; Wei & Li, 2017 ; Schroff, Kalenichenko & Philbin, 2015 ). A face recognition system can perform either facial verification or identification.…”

Section: Introductionmentioning

confidence: 99%

“…This score can be used for the recognition process that can be in the mode of identification or verification ( Wei & Li, 2017 ). Facial recognition systems can also be used in many applications, advertisements, healthcare, security, and criminal recognition ( Shinwari et al, 2019 ). As the face recognition system is used as a security system that can secure our homes, offices, the face recognition system needs to be more secure.…”

Section: Introductionmentioning

confidence: 99%

Kinship verification and recognition based on handcrafted and deep learning feature-based techniques

Nader

El-Gamal

El–Sappagh

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

Background and Objectives Kinship verification and recognition (KVR) is the machine’s ability to identify the genetic and blood relationship and its degree between humans’ facial images. The face is used because it is one of the most significant ways to recognize each other. Automatic KVR is an interesting area for investigation. It greatly affects real-world applications, such as searching for lost family members, forensics, and historical and genealogical studies. This paper presents a comprehensive survey that describes KVR applications and kinship types. It presents a literature review of current studies starting from handcrafted passing through shallow metric learning and ending with deep learning feature-based techniques. Furthermore, kinship mostly used datasets are discussed that in turn open the way for future directions for the research in this field. Also, the KVR limitations are discussed, such as insufficient illumination, noise, occlusion, and age variations problems. Finally, future research directions are presented, such as age and gender variation problems. Methods We applied a literature survey methodology to retrieve data from academic databases. An inclusion and exclusion criteria were set. Three stages were followed to select articles. Finally, the main KVR stages, along with the main methods in each stage, were presented. We believe that surveys can help researchers easily to detect areas that require more development and investigation. Results It was found that handcrafted, metric learning, and deep learning were widely utilized in kinship verification and recognition problem using facial images. Conclusions Despite the scientific efforts that aim to address this hot research topic, many future research areas require investigation, such as age and gender variation. In the end, the presented survey makes it easier for researchers to identify the new areas that require more investigation and research.

show abstract

“…A gender recognition using neural network was implemented by Mittal [4]. Various face recognition algorithms involving video surveillance have been studied and compared in [5] and [6]. In [7], an AI-based trajectory analysis has been proposed to automatically gather and analyze the transfer and change behavior of passengers at transportation nodes within the public transport system.…”

Section: Introductionmentioning

confidence: 99%

An AI-based web surveillance system using raspberry Pi

2019

J. adv. tec. eng. res.

View full text Add to dashboard Cite

We present details of a project to build an inexpensive AI-based home surveillance system using Raspberry Pi. We used a Raspberry Pi and a USB webcam to record a live environment and take photos when motion is detected. The proposed security system allows multiple cameras and users. Users have access to a control center where they can login and select the appropriate camera. The website interface encrypts the user's account information and stores them in a database. Further, an improved setup using Pi-based camera is shown and discussed. The proposed system uses IBM's Internet of Things software library to implement several features via node-red lows. Two lows are created. The irst low triggers the camera to take pictures when motion is detected. The picture is then sent to visual recognition node for processing. If there are people detected, an email is sent with the link to the streaming. If people are not detected, there is no further action. The second low is used to analyze the picture with AI-based visual recognition node. The picture is passed to the visual recognizer for analysis. Then the result is sent to a template node for display as a table.

show abstract

A Comparative Study of Face Recognition Algorithms under Facial Expression and Illumination

Cited by 7 publications

References 12 publications

Towards End-to-End Neural Face Authentication in the Wild -- Quantifying and Compensating for Directional Lighting Effects

Towards End-to-End Neural Face Authentication in the Wild -- Quantifying and Compensating for Directional Lighting Effects

Kinship verification and recognition based on handcrafted and deep learning feature-based techniques

An AI-based web surveillance system using raspberry Pi

Contact Info

Product

Resources

About