Real time smart car lock security system using face detection and recognition

Padmapriya, S.; KalaJames, Esther Annlin

doi:10.1109/iccci.2012.6158802

Cited by 23 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Advancements in facial emotion recognition have surged in recent years, with such technology finding diverse applications, including emergency response and security [1,2], video surveillance and law enforcement [3,4], as well as access management and control [5]. However, the performance of emotion recognition systems is often challenged by variations in pose, illuminations, facial expressions, and noise interference.…”

Section: Introductionmentioning

confidence: 99%

Performance Enhancement in Facial Emotion Classification Through Noise-Injected FERCNN Model: A Comparative Analysis

Anji Reddy,

Regula,

Sharmila

et al. 2023

ISI

View full text Add to dashboard Cite

The human face serves as a potent biological medium for expressing emotions, and the capability to interpret these expressions has been fundamental to human interaction since time immemorial. Consequently, the extraction of emotions from facial expressions in images, using machine learning, presents an intriguing yet challenging avenue. Over the past few years, advancements in artificial intelligence have significantly contributed to the field, replicating aspects of human intelligence. This paper proposes a Facial Emotion Recognition Convolutional Neural Network (FERCNN) model, addressing the limitations in accurately processing raw input images, as evidenced in the literature. A notable improvement in performance is observed when the input image is injected with noise prior to training and validation. Gaussian, Poisson, Speckle, and Salt & Pepper noise types are utilized in this noise injection process. The proposed model exhibits superior results compared to well-established CNN architectures, including VGG16, VGG19, Xception, and Resnet50. Not only does the proposed model demonstrate greater performance, but it also reduces training costs compared to models trained without noise injection at the input level. The FER2013 and JAFFE datasets, comprising seven different emotions (happy, angry, neutral, fear, disgust, sad, and surprise) and totaling 39,387 images, are used for training and testing. All experimental procedures are conducted via the Kaggle cloud infrastructure. When Gaussian, Poisson, and Speckle noise are introduced at the input level, the suggested CNN model yields evaluation accuracies of 92.17%, 95.07%, and 92.41%, respectively. In contrast, the highest accuracies achieved by existing models such as VGG16, VGG19, and Resnet 50 are 45.97%, 63.97%, and 54.52%, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Performance Enhancement in Facial Emotion Classification Through Noise-Injected FERCNN Model: A Comparative Analysis

Anji Reddy,

Regula,

Sharmila

et al. 2023

ISI

View full text Add to dashboard Cite

show abstract

“…Therefore, FR is gradually becoming the most satisfactory and secure solution because it is impractical to embezzle a face and steal it on the spot to gain control of a car. Research continues to bring the technology of FR closer to the human level to develop robust security systems [8,9]. Some of these systems are already helping many people to secure their cars.…”

Section: Introductionmentioning

confidence: 99%

Cost Efficient Automobile Security Using Face Recognition and GSM Module

Gulzar

Qadeer

Aamir

et al. 2022

JCBI

View full text Add to dashboard Cite

Face detection is one of the most important modern computer vision topics. The importance of face recognition (FR) is increasing in our society for identification purposes. In this paper, we practically demonstrated the authenticity of an automatic security system for automobiles using face recognition technology. Our proposed system is not only a facial recognition system, but also supports authentication via a GSM module for remote monitoring and permission/control by a specific remote security code. The system was implemented and tested using a Raspberry Pi 3 board, Python and OpenCV to program the different modules for face recognition. The implementation results confirm the applicability of the proposed system as it offers the advantages of robustness, high accuracy, reliability and security at the lowest cost. This paper defines a combination of fail-safe algorithms for the GPS/GSM module in addition to face recognition algorithms, which are more suitable in dynamic environments where high uncertainties are expected and require high accuracy and reasonable speed. In future, we aim to develop an intelligent smart home application to meet the upcoming needs.

show abstract

“…According to the Society of Automotive Engineers (SAE), driving automation is regarded in six separate levels [10], ranging from no to some to full automation. In particular, smaller systems are being developed separately, such as systems for vision-guided automatic parking [12], context-awareness [30], [29], turn signaling [4], security using face detection and recognition [11], [21], speed control and steering [35].…”

Section: Introductionmentioning

confidence: 99%