Panjab University Swami Sarvanand Giri Regional Centre, Hoshiarpur

Technological advancements and image processing software have made document fraud more prevalent, aided by the availability of inexpensive scanners and printers that facilitate document alteration. Document forensics addresses this issue through active and passive techniques for detecting forgeries. Active methods, like using extrinsic fingerprints and signatures, help in straightforward document authentication. In contrast, passive methods require more sophisticated verification techniques. This review article explores various strategies for identifying the source printers of digital documents and the authors of scanned handwritten documents. It examines a range of methodologies, including machine learning and deep learning approaches, relevant to document forensics. Additionally, the article reviews research on detecting different types and models of printers using textual detection and noise analysis. It also discusses classification and feature extraction techniques, providing a comprehensive overview of the current state-of-the-art methods and tools in the field of document forensics.

Fruit consumption has become a necessity nowadays because maintaining a healthy lifestyle and a nutritionally balanced diet is crucial, given the high-stress lifestyle adopted universally. Fruits are rich in various nutrients, containing multiple vitamins, minerals, and dietary fiber. Thus, fruits have a high demand in markets, and to fulfill that demand, some sellers tend to use artificial ripening agents to ripen climacteric fruits, which have various harmful effects on the human body. Artificially ripened fruits are a primary concern for the Indian fruit industry and a major hindrance to its growth globally and for consumers. This paper explores various non-destructive artificial intelligence (AI) techniques to classify artificially ripened fruits, enabling us to maintain fruit quality and consumer health. These AI techniques are simple, accurate, cost-effective, and scalable compared with the traditionally used methods. This paper will work as a database to help future researchers explore all AI techniques in one place. The analysis suggests using spectral data, specifically hyperspectral imaging with machine learning models, for detecting artificially ripened fruits, which needs further exploration. This approach would be advantageous for accessing complex properties, such as surface and internal changes, and would improve detection accuracy.

In a period marked by swift technological progress, the task of identifying writers through handwriting holds significant importance across various domains, including forensic investigation, plagiarism detection, and historical research. The importance of this endeavor has been further magnified by the widespread influence of digitalization. This study employs a hybrid approach that integrates cutting-edge deep learning techniques, specifically Convolutional Neural Networks (CNNs), with traditional machine learning methodologies, such as Support Vector Machines (SVM) and Random Forest (RF). Deep learning techniques are particularly valuable for analyzing extensive handwriting samples because they can automatically discern complex features and patterns from large datasets. In this research, we synthesize predictions from deep learning models and employ machine learning classification for writer identification based on handwriting analysis. Central to our study is a comprehensive dataset of Devanagari characters, collected from 220 unique writers. This dataset has been thoughtfully curated to validate the methodology we have employed. Our hybrid classification approach, combining CNN with SVM and CNN with RF, achieves remarkable accuracy rates of 91.49

The theme of ‘Human Security’ was first articulated by Mahbub-ul-Haq in the United Nations Development Programme’s Human Development Report in 1994. Freedom from fear and freedom from want are the two cardinal principles of human security. Human Security puts individual as the prime referral point in its exposition and analysis. Since, there is a lot of emphasis upon gender-specific discourses in the last three decades this article seeks to bring into limelight the critical perspectives of the interfaces between gender and human security, with special reference to India. This article raises some fundamental and pertinent questions. What impact does gender have on human security? What are the different dimensions of Human Security? To what extent we have been able to establish a gender-specific human security discourse in India? This article tries to answer all these substantive questions and establish a gendered-human security discourse in contemporary India.

Identification of a person on the basis of different characteristics is a prevailing area of research. Both behavioral biometrics and physical biometrics are used as measures to recognize a person’s identity. Physical biometrics includes fingerprints and IRIS patterns; whereas behavioral biometrics includes some sort of pattern in human activities like handwriting. Handwriting, like other biometrics, is one of the best attributes for implicitly identifying a person. Every person has a different style of handwriting. Gender prediction on the basis of handwriting styles in different Indian and non-Indian scripts offers a vast area for research and is an effective strategy for biometrics. This paper's major goal is to give an in-depth analysis of gender prediction using handwriting in non-Indic and Indic scripts. The intention is to provide a variety of feature extraction methods, datasets available, and a taxonomy of conventional and machine learning-based tools for gender prediction on the basis of handwriting. This article discusses the context, survey protocol, methodology, and various datasets used by the various researchers. The compiled study used for feature extraction and classification methods, along with a critical analysis of the work done, is also elaborated in this manuscript.