Further optimization of the CNN model

Oct 13, 2025 by magicalceylontours.com 12 views

Implementation of Building Door Security Systems with a Face Recognition Approach Using IoT-Based Convolutional Neural Network (CNN)

Introduction

In today's digital era, technology-based security systems are increasingly needed to increase protection of important buildings and facilities. One of the rapidly developing technologies is face recognition. This technology is used to identify or verify a person's identity through his facial features analysis. This study aims to improve building safety by ensuring that only registered people can access the door, thereby reducing the risk of security violations that come from the use of physical keys or access cards.

The Importance of Face Recognition Technology in Building Security

Face recognition technology has become a crucial aspect of modern security systems. It provides a secure and efficient way to identify individuals, reducing the risk of unauthorized access to buildings and facilities. With the increasing use of physical keys and access cards, the risk of security breaches is high. Face recognition technology eliminates this risk by verifying a person's identity through their facial features analysis.

Research Methodology

This study involved several stages, including literature studies to understand the basic concepts of facial recognition, internet of things (IoT), and Convolutional Neural Networks (CNN). Dataset collection was also carried out, including the process of labeling, training, testing, and evaluating. From the data that has been tested, the values of results, such as accuracy, precision, recall, and F1-Score values.

Dataset Collection and Evaluation

The dataset used in this study consisted of images of individuals with varying facial expressions and lighting conditions. The dataset was labeled and divided into training and testing sets. The training set was used to train the CNN model, while the testing set was used to evaluate the model's performance. The evaluation metrics used were accuracy, precision, recall, and F1-Score values.

Test Results

The test results show that face recognition technology with CNN algorithms can reach accuracy of 72.7%, precision 50%, recall 75%, and F1-Score value 60%. This shows that the system is able to recognize the face well in optimal lighting conditions. However, system performance tends to decrease when lighting is inadequate.

Analysis of Results

The accuracy of 72.7% shows that the system has a fairly good level of reliability, although there is still room for improvement. The precision value that only reaches 50% indicates the existence of challenges in avoiding positive mistakes, where the system may identify individuals who are not registered as legitimate users. Conversely, the recall value that reaches 75% shows that the system is good enough in identifying registered individuals, although there is a possibility that some users are not detected.

The increase in the F1-Score value at 60% reflects the balance between precision and recall, but still shows the need for further optimization so that it can be relied upon in various lighting situations. Decrease in performance under the unworthy lighting conditions emphasize the importance of creating additional solutions, such as the use of artificial light sources or the development of more sophisticated algorithms that can adjust to lighting variations.

Challenges and Limitations

Despite the promising results, there are several challenges and limitations that need to be addressed. The system's performance decreases in inadequate lighting conditions, which highlights the need for additional solutions to improve the system's reliability. Furthermore, the system's ability to recognize individuals with varying facial expressions and lighting conditions is limited, which requires further optimization.

Conclusion

The implementation of building door security systems with a CNN-based face recognition approach shows great potential in increasing security. Although the initial results provide positive indications, further research is needed to overcome the challenges that exist, especially in terms of accuracy and performance in varied lighting conditions. The development and integration of better technology will be the key in creating a more reliable and effective security system in the future.

Future Directions

Future research directions include the development of more sophisticated algorithms that can adjust to lighting variations, the use of artificial light sources to improve the system's performance, and the integration of additional biometric features, such as iris recognition or fingerprint recognition, to improve the system's reliability.

Recommendations

Based on the findings of this study, the following recommendations are made:

Further optimization of the CNN model: The CNN model needs to be further optimized to improve its performance in varied lighting conditions.
Use of artificial light sources: The use of artificial light sources can improve the system's performance in inadequate lighting conditions.
Integration of additional biometric features: The integration of additional biometric features, such as iris recognition or fingerprint recognition, can improve the system's reliability.

Conclusion

In conclusion, the implementation of building door security systems with a CNN-based face recognition approach shows great potential in increasing security. Although the initial results provide positive indications, further research is needed to overcome the challenges that exist, especially in terms of accuracy and performance in varied lighting conditions. The development and integration of better technology will be the key in creating a more reliable and effective security system in the future.
Frequently Asked Questions (FAQs) on Implementation of Building Door Security Systems with a Face Recognition Approach Using IoT-Based Convolutional Neural Network (CNN)

Q: What is the main objective of this study?

A: The main objective of this study is to improve building safety by ensuring that only registered people can access the door, thereby reducing the risk of security violations that come from the use of physical keys or access cards.

Q: What is face recognition technology?

A: Face recognition technology is a type of biometric technology that uses facial features analysis to identify or verify a person's identity.

Q: How does the CNN model work?

A: The CNN model works by analyzing the facial features of an individual and comparing them to a database of registered individuals. The model uses a series of algorithms to identify the individual and verify their identity.

Q: What are the advantages of using face recognition technology in building security?

A: The advantages of using face recognition technology in building security include:

Improved security: Face recognition technology provides a secure and efficient way to identify individuals, reducing the risk of unauthorized access to buildings and facilities.
Reduced risk of security breaches: Face recognition technology eliminates the risk of security breaches that come from the use of physical keys or access cards.
Increased convenience: Face recognition technology provides a convenient and efficient way to access buildings and facilities.

Q: What are the challenges and limitations of using face recognition technology in building security?

A: The challenges and limitations of using face recognition technology in building security include:

Decreased performance in inadequate lighting conditions
Limited ability to recognize individuals with varying facial expressions and lighting conditions
Need for further optimization to improve the system's reliability

Q: What are the future directions for this study?

A: The future directions for this study include:

Development of more sophisticated algorithms that can adjust to lighting variations
Use of artificial light sources to improve the system's performance
Integration of additional biometric features, such as iris recognition or fingerprint recognition, to improve the system's reliability

Q: What are the recommendations for implementing face recognition technology in building security?

A: The recommendations for implementing face recognition technology in building security include:

Further optimization of the CNN model
Use of artificial light sources to improve the system's performance
Integration of additional biometric features, such as iris recognition or fingerprint recognition, to improve the system's reliability

Q: What are the potential applications of this study?

A: The potential applications of this study include:

Building security: Face recognition technology can be used to improve building security by ensuring that only registered people can access the door.
Access control: Face recognition technology can be used to control access to buildings and facilities.
Identity verification: Face recognition technology can be used to verify an individual's identity.

Q: What are the potential benefits of this study?

A: The potential benefits of this study include:

Improved security: Face recognition technology provides a secure and efficient way to identify individuals, reducing the risk of unauthorized access to buildings and facilities.
Increased convenience: Face recognition technology provides a convenient and efficient way to access buildings and facilities.
Reduced risk of security breaches: Face recognition technology eliminates the risk of security breaches that come from the use of physical keys or access cards.