Tej Kaur

Background: The human nose is a prominent facial feature whose morphoscopic traits offer valuable insights into an individual's ancestry, sex, and personal identification. The study aims to evaluate the nasal morphological features to explore sexual dimorphism and ethnic differences among the two North Indian population groups using three machine learning models: Random Forest Classifier (RFC), CatBoost (CB), and Support Vector Machine (SVM). Results: Snapshots of the noses of 500 participants (18–35 years) from frontal, basal, and lateral profiles belonging to two genetically distinct endogamous populations (i.e., Rajputs and Brahmins ) from North India, were collected. A total of eighteen morphoscopic parameters such as nose size, nasal bridge profile, etc. were considered and evaluated through standard procedures. Data were pre-processed and underwent a single train-test split into 80:20 ratio along with a fivefold cross-validation method. Customised machine learning models predicted sex and ethnicity, with SHAP (SHapley Additive exPlanations) used for interpretability, while intra-observer reliability was assessed to ensure data consistency. Support Vector Machine performed slightly best for sex estimation (69%), followed by Random Forest (68%) and CatBoost (62%). For ethnicity, Random Forest performed slightly better, achieving 75% accuracy, followed by CatBoost (72%) and Support Vector Machine (70%). SHAP analysis revealed nasal root height and nose size as consistent sex predictors, whereas ethnicity classification relied on a more variable traits across models. Moreover, fivefold cross-validation results provided an assessment of model performance stability. Conclusion: Nasal morphoscopic parameters show greater ethnicity than sex, underscoring their forensic utility in sex and ethnicity estimation.

Background: Fingerprint analysis constitutes a fundamental component of forensic investigation. Friction skin ridges are highly reliable for human identification because they are distinctive and permanent, making them helpful in criminal investigations for identifying suspects and victims. The present study aims to evaluate sexual dimorphism on the basis of fingerprint ridge density (FPRD) and study its variability in the radial, ulnar and proximal areas of fingerprints of both left and right hands in males and females. Methods: The fingerprints were obtained from all the 10 fingers of 113 individuals from North Indian population (56 males and 57 females) between the ages of 18 and 30 years. Following the fingerprint collection process, the data was manually inspected by counting the ridges in three topological regions of the skin i.e. radial, ulnar, and proximal areas using a linen tester. Subsequently, statistical analysis was employed. The student t-test (parametric) and Mann-Whitney U test (non-parametric) were used to statistically assess the fingerprint ridge density between the sexes in the three topological regions. Further, Bonferroni correction was applied to control for Type I error due to multiple comparisons, and Cohen’s d and Cliff’s delta were calculated to assess the magnitude of sexual dimorphism between males and females. Results and conclusions: Females exhibited higher ridge density values than males across all regions. After Bonferroni correction (α = 0.00167), only strongly significant variables remained. Cohen’s d and Cliff’s delta indicated moderate to large sexual dimorphism in several regions, with the large effect size observed in RMR (Right Middle Radial), RMP (Right Middle Proximal), LTR (Left Thumb Radial), LTU (Left Thumb Ulnar), LIU (Left Index Ulnar), LMU (Left Middle Ulnar), LRR (Left Ring Radial), LRU (Left Ring Ulnar) and LLR (Left Little Radial) areas. The assessment of sexual dimorphism from fingerprint ridge density may allow the investigating officer to narrow down the forensic investigation based on either sex.

Facial recognition technology is an artificial intelligence-based biometric technology that stands at the forefront of global forensic investigations as a leading and widely adopted biometric modality. In comparison to alternative parameters such as voice, fingerprint, iris, retina, eye scan, gait, ear, and hand geometry; facial recognition emerges as the most popular and effective tool for personal identification and verification. Beyond its role in research, access control, user authentication, and border security, the technology plays a dynamic role in law enforcement and surveillance. Despite its extensive applications, the technology sparks privacy and ethical debates. Contemporary concerns revolve around its potential to implicate innocent individuals, raising issues of civil liberties, human rights, and privacy infringement. In light of these considerations, this article critically examines the reliability and consistency of facial recognition technology and incorporates case studies highlighting instances of wrongful detentions. It also explores the principles and functioning of facial recognition technology. The face recognition outcomes rely heavily on features that are extracted to reflect the face pattern and classification techniques used to distinguish between faces. However, there are a few limitations associated with the facial recognition technology. This is prone to errors in detecting some facial features and skin tones, which raises potential risks and consequences for innocent persons and communities. Therefore, these mistaken identity cases emphasize the urgent need for robust oversight, transparency and safeguards to ensure fairness, preventing misuse and upholding the dignity and privacy of individuals in the growing era of artificial intelligence. The present communication concludes with actionable recommendations to address the ethical and privacy challenges associated with facial recognition in the forensic context.

Background and objective: Scientific methods and technologies are growing rapidly in the 21st century. However, natural catastrophes, mass disasters and criminal activities continue to persist in human society. In these situations, identification of the deceased proves to be a challenging task for medico-legal professionals, as in many such cases, dead bodies are highly fragmented, mutilated, and are not in a situation of being identified by facial and external body features. If adequate ante-mortem (AM) and post-mortem (PM) data are available, the techniques of forensic odontology may contribute greatly to the identification of the deceased. The present narrative review highlights the importance of digital methods over conventional methods used in forensic odontology and the importance of dental remains in personal identification. Main body: Exploring this application, literature was searched from “PubMed”, “PubMed Central”, “Scopus” and “Web of Science” using relevant keywords. The relevant publications were further scrutinized and included in the present review. Traditional methods of dental data collection have a number of inherent issues, including poor and incomplete documentation of dental charting, written dental records, and dental profiles, the use of local language in recording the dental profile, and the use of different or non-standardized terminology that may be difficult for a forensic anthropologist or odontologist to understand. These issues may pose a significant challenge in understanding the AM data available at the time of comparison, ultimately delaying the identification process. The digital techniques and artificial intelligence have the potential to substantially enhance the quality of forensic examination by improving the efficiency, accessibility, and interoperability of records. In mass disaster cases with high casualties, digital techniques facilitate the rapid and seamless cross-border transfer of victim data that greatly accelerates the identification process. Conclusion: The practical application of advances in artificial intelligence (AI) is playing an important role in improving the analysis of digital dental evidence, resulting in greater accuracy, efficiency, and reliability in forensic investigations. Digital techniques such as 2D and 3D superimposition methods, digital radiographs, and 3D surface scans, may solve the problems of conventional methods.

Although India gained independence in 1947, its laws, namely the Indian Penal Code (IPC) of 1860, the Code of Criminal Procedure (CrPC) of 1973 and the Indian Evidence Act (IEA) of 1872, were still in use. These criminal laws were primarily inherited from the statutes that were established during the colonial period. These laws were framed according to the crimes and legal needs of that time. Moreover, the 21st century is an era of artificial intelligence, thus the emergence of digital/cybercrimes. Therefore, many of these laws become outdated and ineffective in addressing and solving the contemporary challenges and crimes. Consequently, there was an immediate need to reform the criminal laws in India to address the contemporary challenges and social values that can stand with technological advancements. Addressing these issues in the Indian justice system, the Government of India implemented the three new laws on 1 ^st July 2024, namely the Bharatiya Nyaya Sanhita (replaces the IPC) ; the Bharatiya Nagrik Suraksha Sanhita (replaces the CrPC) and the Bharatiya Sakshya Adhiniyam (replaces the IEA). The primary aim of these laws is to modernize and streamline the Indian criminal justice system with scientific, forensic and technological advancements and align with the laws of developed countries. The communication explores the objective, application and associated potential challenges of these new laws. It also seeks to explore the provisions of the new laws to find out their possible impact on the Criminal Justice System of India.

Signature authentication refers to the verification whether the signature is legitimate or forged and is executed by the person who is claiming to have signed it. The main objective of the present research was to customize a deep learning-based convolutional neural network (CNN) model trained on a primary dataset for signature authentication. The model was trained, validated, and tested on the dataset of the 1400 signature images (700 genuine and 700 forged) primarily obtained from the study participants. The signature samples were equally divided into a train (1000 samples comprising 500 forged and 500 genuine signatures) and a test dataset (400 samples comprising 200 forged and 200 genuine signatures) as per the requirements of the model's training and testing procedure. The model's architecture was optimized with different hyperparameters to achieve a higher accuracy rate. The results show that the proposed model attains the training, validation and testing accuracy of 97.32%, 97.92%, and 84.5% respectively. Furthermore, other evaluation matrices were also computed, including precision, recall (sensitivity), F1-score, and specificity with the values of 85%, 84%, 84%, and 90%, respectively. The accuracy matrices provide better performance over the other existing methods. This customized CNN architecture can be trained on larger datasets and directly deployed in the field of forensic science for signature examination. The study has wide-ranging applications in the banking sector, forensic document examination, courtrooms, and beyond.