Design and Implementation of Crime Investigation Using Biometric Approach

1.1 Introduction

Biometrics refers to the automated recognition of individuals based on their unique behavioral and biological characteristics, such as fingerprints, facial features, iris patterns, and voice traits (NCBI Bookshelf, 2024). In the context of crime investigation, biometric systems use these measurable human traits to identify and verify individuals involved in criminal activities with greater precision than traditional manual methods. Crime investigation itself is the scientific and systematic process of collecting, analyzing and interpreting evidence in order to establish what happened during a crime and link perpetrators to criminal acts. Traditionally, this process relied heavily on manual documentation, witness testimony, and physical evidence analysis, which is often time intensive, prone to error and subject to limitations in accuracy and traceability.

As a prelude to other parts of this study, this chapter will discuss the background upon which this study was initiated, the statement of problems that led to this study, the Aim and Objectives of the study. Others are Significance of the study, Scope of work, Limitation of the study and Definition of technical terms.

1.2 Background of Study

Crime investigation plays a crucial role in maintaining public safety, facilitating justice, and deterring criminal behaviour in modern societies. Traditional investigative processes historically relied on manual record keeping, witness statements, and physical evidence analysis to identify suspects and establish links to criminal activities. According to Jain, Ross, and Nandakumar (2025), traditional identification systems are often hampered by human error, poor record integrity, and delays in retrieving critical information, which can result in prolonged investigations and challenges in securing convictions. As criminal activities continue to evolve with increased sophistication and complexity, law enforcement agencies worldwide have sought more advanced technologies capable of improving the accuracy and efficiency of investigative processes (Jain, Ross, and Nandakumar, 2025).

Biometric technology has emerged as a promising solution to many of the shortcomings observed in conventional investigative approaches. Biometric systems use individuals' unique physical or behavioural traits such as fingerprints, facial structure, iris patterns, and gait; to perform identification and verification tasks. According to Maltoni, Maio, Jain, and Prabhakar (2024), biometric recognition systems offer advantages over traditional approaches because they rely on inherent, measurable traits that are difficult to forge or duplicate. This reduces the risk of identity fraud and enhances the reliability of suspect identification. For example, Automated Fingerprint Identification Systems (AFIS) have transformed the way law enforcement matches latent prints recovered from crime scenes against national or regional databases.

Smith & Lee (2025) reported that AFIS has helped reduce the backlog of fingerprint comparisons in many jurisdictions, significantly speeding up investigative timelines while preserving evidentiary integrity (Smith & Lee, 2025). Beyond fingerprints, facial recognition technologies have gained broader application in public safety and surveillance systems. According to Zhao, Chellappa, Phillips, and Rosenfeld (2026), facial recognition algorithms using deep learning models have shown improved accuracy rates under various environmental conditions, enabling investigators to cross-reference surveillance footage with watchlists and criminal databases. However, while these developments show promise, they also raise critical concerns about data privacy, algorithmic bias, and ethical governance.

The growing volume of digital evidence and the need for cross jurisdictional collaboration further complicate the landscape of crime investigation. According to Peters and Ahmed (2025), interoperable biometric databases that connect local, national, and international systems are key to tracking repeat offenders and solving complex, multi region crimes. However, challenges related to data standardization, privacy regulations, and legal agreements between agencies often delay effective implementation of such integrated systems.

Chen & Williams (2025) affirmed that without uniform standards and secure data sharing policies, the promise of interconnected biometric systems remains constrained by bureaucratic and legal hurdles (Chen & Williams, 2025). In addition to operational challenges, biometric systems must be continually updated to address issues of fairness and inclusivity. Studies have shown that some biometric algorithms perform unevenly across different demographic groups due to biased training data or design flaws.

According to Garcia and Patel (2026), facial recognition systems, in particular, have exhibited higher error rates for individuals of certain ages, genders, or ethnic backgrounds, raising concerns about equitable treatment within criminal justice processes. This highlights the need for robust algorithm training on diverse datasets and ongoing evaluation to minimize bias and ensure that biometric approaches serve all populations fairly. This study is set against the backdrop of increasing crime rates, challenges in traditional investigative methods, and the urgent need for technologically advanced systems that improve the accuracy, efficiency, and reliability of crime investigation in law enforcement agencies.

1.3 Statement of Problems

Based on the investigation conducted, the implemented system encounters a number of challenges, with some of the most significant issues outlined below:

1. The existing crime investigation systems in many law enforcement agencies rely heavily on manual documentation and conventional record-keeping methods, which are prone to errors, misplacement of files, and delays in suspect identification.
2. Fingerprint records, case files, and physical evidence are often stored in non-digitized formats, making retrieval time-consuming and inefficient.
3. The traditional databases are often fragmented, lack interoperability, and do not support multi-modal biometric verification, resulting in incomplete or inaccurate suspect identification.
4. In the old system, there is reliance on outdated identification methods, such as manual fingerprint comparison, increases the risk of human error, slows down investigations, and limits the capacity of law enforcement to respond to growing crime rates.
5. Furthermore, current systems lack robust security measures to protect sensitive criminal data, which exposes information to potential tampering, loss, or unauthorized access.
6. Lastly, existing systems do not provide automated tools for analyzing biometric data from multiple sources, which restricts timely cross-referencing and affects the speed of case resolution.

1.4 Aim and Objectives of Study

The aim of this study is to design and implement a reliable biometric-based crime investigation system that will enhance the accuracy, efficiency, and security of suspect identification and evidence management in law enforcement operations. In achieving this aim, the following specific objectives were set out as follows:

1. To develop a biometric system capable of capturing and storing unique identifiers such as fingerprints, facial features, and iris patterns for criminal investigations.
2. To reduce delays in suspect identification by automating the cross-referencing of biometric data with existing criminal databases.
3. To improve the integrity and security of criminal records by implementing secure storage and controlled access mechanisms for biometric data.
4. To evaluate the effectiveness of the implemented system in enhancing investigative accuracy and reducing human errors compared to existing manual methods.
5. To provide a scalable framework for integrating the biometric system into local, national, and regional law enforcement networks to strengthen coordinated crime investigation efforts.

1.5 Significance of Study

The deployment of the proposed system will hold significant relevance in the following ways:

1. The developed biometric crime investigation system will provide law enforcement agencies with an automated platform to accurately identify suspects using fingerprints, facial recognition, and iris scans.
2. The system will reduce delays in investigations by enabling faster cross-referencing of evidence with existing criminal databases.
3. The new system will enhance the security and integrity of criminal records by preventing data loss, tampering, or unauthorized access.
4. The project will support judicial processes by providing verifiable and tamper-proof evidence, which will strengthen conviction rates.
5. Lastly, the system will offer a scalable model that can be integrated into regional and national law enforcement networks, improving coordinated responses to crime and repeat offenders.

1.6 Scope of Study

The study focuses on the design and implementation of a biometric-based crime investigation system tailored for law enforcement agencies in Lagos State, Nigeria. It covers the use of fingerprints, facial recognition, and iris scans to accurately identify suspects and manage criminal records.

1.7 Limitations of the Study

During the course of this study, many things militated against its completion, some of which are:

1. Time Constraint: The time frame given to accomplish this project was very short due to school academic calendar and it was carried out under pressure which made the researcher not to implement some necessary features.
2. Establishment Policies: Establishment policies posed a serious limitation as most staffs are not ready to release information needed for this project work. There were lots of information needed from the staffs of this institution to enhance the study which took them time to release or they did not release at all for security purposes, hence the scope was reduced.
3. Financial Constraint: Insufficient fund tends to impede the efficiency of the researcher in sourcing for the relevant materials, literature or information and in the process of data collection (internet).

1.8 Definition of Terms

Biometrics:

Biometrics refers to the automated identification and verification of individuals based on their unique biological or behavioral characteristics, such as fingerprints, facial features, iris patterns, and voice traits. According to Jain, Ross, and Nandakumar (2025), biometrics is increasingly used in law enforcement to improve the accuracy of suspect identification and strengthen investigative outcomes.

Crime Investigation:

Crime investigation is the systematic process of collecting, analyzing, and interpreting evidence to establish facts, identify suspects, and support the judicial process. Fletcher and Murphy (2024) reported that effective crime investigation requires both physical evidence and reliable methods to link perpetrators to criminal acts.

Fingerprint Recognition:

Fingerprint recognition is a biometric method that involves capturing and comparing the unique patterns of ridges and valleys on an individual's fingers. Maltoni, Maio, Jain, and Prabhakar (2024) asserted that fingerprint identification is one of the oldest and most reliable biometric approaches used in forensic investigations.

Facial Recognition:

Facial recognition is the process of identifying or verifying an individual by analyzing and comparing facial features from images or video. Zhao, Chellappa, Phillips, and Rosenfeld (2026) stated that advances in machine learning have significantly improved the accuracy of facial recognition systems in law enforcement applications.

Iris Recognition:

Iris recognition is a biometric technique that uses the unique patterns of the colored part of the eye to identify individuals. Reported that iris recognition provides a high level of accuracy and is stable over time, making it suitable for secure identification in crime investigations (Nguyen, Smith, & Ahmed, 2025).