Software Framework for Face Recognition System Using Amazon Rekognition

This study presents the development and implementation of a software framework for a face recognition system using Amazon Rekognition, a cloud-based image and video analysis service provided by Amazon Web Services (AWS). The face recognition system is designed to offer a scalable, accurate, and efficient solution for identity verification and authentication, primarily targeting applications in security, access control, and user authentication systems. The framework integrates various AWS services, including Amazon S3 for image storage, Amazon Lambda for serverless computation, Amazon DynamoDB for database management, and API Gateway for interaction between the front-end application and backend services. During the implementation, Pycharm Integrated Development Environment (IDE) was used to develop user interface. The methodology employed in this study includes the collection of a dataset comprising 500 images for training and 200 images for testing. Images were gathered from primary and secondary sources, and preprocessing techniques such as face detection, normalization, and augmentation were applied to ensure the quality and consistency of the dataset. During the training phase, Amazon Rekognition’s IndexFaces API was used to extract unique facial features and store them for subsequent comparisons. In the testing phase, the SearchFacesByImage API was used to evaluate the system’s performance in identifying and verifying faces. The proposed framework was evaluated for performance metrics such as scalability, processing time, and accuracy, and compared with other face recognition models to determine its competitive advantages. By leveraging cloud-based technologies and serverless architectures, the system exhibits high scalability, minimal latency, and costefficiency, making it ideal for real-time, large-scale deployments. Additionally, the framework is flexible and can be integrated into various application domains, such as security systems, smart homes, financial institutions, and educational environments. This study concludes that Amazon Rekognition offers a robust solution for face recognition, providing a foundation for further research and innovation in this field. The framework’s ability to integrate seamlessly with AWS services enables organizations to implement face recognition solutions without the need for extensive hardware or infrastructure investment. Future work could explore enhancements in system robustness, support for larger datasets, and improvements in handling challenging conditions, such as occlusions or facial expressions, to further boost accuracy and reliability.

Authors

Institutions

Publication Details

Journal
INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY E-ISSN
Published
2026-11-13
DOI
https://doi.org/10.56201/ijcsmt.v10.no5.2024.pg135.154
Primary Topic
Face recognition and analysis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Software Framework for Face Recognition System Using Amazon Rekognition

John Bille URBANUS
3 links
INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY E-ISSN
Face recognition and analysis
article

Software Framework for Face Recognition System Using Amazon Rekognition

John Bille URBANUS
article en

Abstract

This study presents the development and implementation of a software framework for a face recognition system using Amazon Rekognition, a cloud-based image and video analysis service provided by Amazon Web Services (AWS). The face recognition system is designed to offer a scalable, accurate, and efficient solution for identity verification and authentication, primarily targeting applications in security, access control, and user authentication systems. The framework integrates various AWS services, including Amazon S3 for image storage, Amazon Lambda for serverless computation, Amazon DynamoDB for database management, and API Gateway for interaction between the front-end application and backend services. During the implementation, Pycharm Integrated Development Environment (IDE) was used to develop user interface. The methodology employed in this study includes the collection of a dataset comprising 500 images for training and 200 images for testing. Images were gathered from primary and secondary sources, and preprocessing techniques such as face detection, normalization, and augmentation were applied to ensure the quality and consistency of the dataset. During the training phase, Amazon Rekognition’s IndexFaces API was used to extract unique facial features and store them for subsequent comparisons. In the testing phase, the SearchFacesByImage API was used to evaluate the system’s performance in identifying and verifying faces. The proposed framework was evaluated for performance metrics such as scalability, processing time, and accuracy, and compared with other face recognition models to determine its competitive advantages. By leveraging cloud-based technologies and serverless architectures, the system exhibits high scalability, minimal latency, and costefficiency, making it ideal for real-time, large-scale deployments. Additionally, the framework is flexible and can be integrated into various application domains, such as security systems, smart homes, financial institutions, and educational environments. This study concludes that Amazon Rekognition offers a robust solution for face recognition, providing a foundation for further research and innovation in this field. The framework’s ability to integrate seamlessly with AWS services enables organizations to implement face recognition solutions without the need for extensive hardware or infrastructure investment. Future work could explore enhancements in system robustness, support for larger datasets, and improvements in handling challenging conditions, such as occlusions or facial expressions, to further boost accuracy and reliability.

INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY E-ISSN
Modibbo Adama University of Technology (NG)
Face recognition and analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon