Face Recognition for Missing/Criminal Person Detection and Alerting

Abstract

Crimes are at rise and becoming difficult for police to identify and rescue the Missing Persons. Our Proposed System will use Face Recognition Algorithms to detect Missing Persons. Face Recognition begins with extracting the coordinates of features such as width of mouth, width of eyes, pupil, and compare the result with the measurements stored in the database and return the closest record (facial metrics). Nowadays, there are a lot of face recognition techniques and algorithms found and developed around the world. Facial recognition becomes an interesting research topic. It is proven by numerous numbers of published papers related with facial recognition including facial feature extraction, facial algorithm improvements, and facial recognition implementations. We will be using advance algorithms like LBPH for our system and also compare to other older algorithms to prove higher accuracy of our system.

Introduction

Overview

Traditional methods of locating missing persons or criminals are slow and often ineffective, especially with limited data. Facial recognition technology is proposed as a more efficient and accurate alternative. It identifies individuals by analyzing distinct facial features and matching them with entries in a database.

Technology Used

• Local Binary Patterns Histogram (LBPH) is the core algorithm due to its simplicity, efficiency, and robustness in real-world conditions.

• The system also uses Haar Cascade classifiers for face detection before applying LBPH.

Literature Review

1. Nurul Azma Abdullah: Used PCA for quick and simple facial recognition, ideal for limited-resource environments.

2. Apoorva and Impana: Utilized Haar-like features and cascade classifiers for real-time detection in dynamic environments.

3. Kavushica Rasanayagam: Combined CNNs and AWS cloud infrastructure for scalable, deep-learning-based recognition.

4. Liping Chang: Proposed a hybrid model using deep learning and handcrafted features to improve performance in poor image conditions.

Existing Systems – Limitations

• Use older methods like SVM, k-NN, PCA, and Eigenfaces.

• Work well in controlled environments but fail under real-world conditions.

• Suffer from low accuracy, rigidity, lack of adaptability, and high complexity.

Proposed System

A more robust and user-friendly system using LBPH for facial recognition:

• Components:

  1. Image acquisition via webcam or surveillance.

  2. Image preprocessing.

  3. Face detection (Haar Cascade).

  4. Feature extraction (LBPH).

  5. Classification and recognition.

  6. Results displayed via GUI.

• Advantages:

  • Simple GUI for broad accessibility.

  • Faster and more accurate than general neural networks.

  • Recognizes both criminals and missing persons.

  • Can recognize faces from different angles.

  • Effective even with variations in lighting or expression.

LBPH Algorithm Details

• Analyzes local pixel neighborhoods to create binary patterns.

• Converts these into histograms representing different image sections.

• Key Parameters:

  1. Radius – neighborhood size.

  2. Neighbours – points sampled per pixel.

  3. Grid X/Y – horizontal/vertical divisions for detailed spatial representation.

• Distance metrics (e.g., Euclidean) used for comparison during recognition.

Conclusion

We developed a facial recognition system capable of identifying both missing and criminal individuals through real-time image capture using surveillance cameras. Once a match is detected, the system is designed to immediately alert the nearest police station by triggering a siren or notification signal. The core of the system utilizes the Local Binary Pattern Histogram (LBPH) algorithm, which enables accurate recognition even when facial profiles are captured from either side. This enhances the system’s robustness in practical scenarios where full frontal facial views may not always be available. The entire system was implemented, integrated with a notification mechanism, and evaluated across a variety of test cases. The results demonstrated that all key functionalities — including detection, recognition, and alert generation — performed reliably under the given conditions. Based on the successful validation, it can be concluded that such a system holds strong potential for real-world deployment in public spaces, transportation hubs, or other high-security areas. With further refinement and integration into existing law enforcement infrastructure, it could significantly aid in identifying and recovering missing individuals and apprehending wanted suspects.

References

[1] N. A. Abdullah, “PCA-Based Automated Facial Recognition System,” International Journal of Computer Applications, vol. 975, no. 8887, pp. 1–6, 2020. [2] Apoorva and Impana, “Haar Classifier for Robust Face Recognition,” International Research Journal of Engineering and Technology (IRJET), vol. 7, no. 6, pp. 2184–2187, Jun. 2020. [3] K. Rasanayagam, “Deep Learning and Cloud-Based Face Recognition,” International Journal of Engineering and Advanced Technology (IJEAT), vol. 9, no. 3, pp. 123–128, Feb. 2020. [4] L. Chang, “Hybrid Feature Extraction Framework for Facial Recognition using SCAE, SRC, and LBP,” Pattern Recognition Letters, vol. 139, pp. 104–111, May 2021. [5] O. M. Parkhi, A. Vedaldi, and A. Zisserman, “Deep Face Recognition,” British Machine Vision Conference (BMVC), pp. 1–12, 2015. [6] F. Schroff, D. Kalenichenko, and J. Philbin, “FaceNet: A Unified Embedding for Face Recognition and Clustering,” Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 815–823, 2015. [7] Y. Taigman, M. Yang, M. Ranzato, and L. Wolf, “DeepFace: Closing the Gap to Human-Level Performance in Face [8] S. Zhang, X. Wang, H. Qi, and Y. Wang, “Face Detection Based on Deep Learning: An Overview,” IEEE Access, vol. 7, pp. 78254–78273, 2019. [9] Z. Cao, Q. Yin, X. Tang, and J. Sun, “Face Recognition with Learning-Based Descriptor,” Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2707–2714, 2010. [10] A. Kumar and A. Passi, “Comparison and Evaluation of Face Recognition Algorithms and Their Performance Metrics,” International Journal of Computer Applications, vol. 82, no. 14, pp. 35–41, Nov. 2013. [11] H. Wang and D. Zhang, “Face Recognition Using SVM with Gabor Features,” International Journal of Pattern Recognition and Artificial Intelligence, vol. 21, no. 06, pp. 1123–1136, 2007. [12] R. Chellappa, C. L. Wilson, and S. Sirohey, “Human and Machine Recognition of Faces: A Survey,” Proceedings of the IEEE, vol. 83, no. 5, pp. 705–740, May 1995.

Copyright

Copyright © 2025 Konda Deekshitha, Dr. V. Uma Rani. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.