Revolutionising document security: OCR-based signature verification

Text detection & localization plays an essential role in finding the textual information from natural scene images that can be used in robot navigation, license plate detection, and wearable applications. In this work, we present text detection and localization approach based upon a novel text awareness model that encompasses an improved fast edge preserving and smoothing Maximum Stable Extremal Region (FEPS-MSER) algorithm which uses the fast guided filter to separate the interconnected characters efficiently by removing the mixed pixels around the edges of blurred images. The fast guided filter takes less execution time as compared to other edge-smoothing filters. The combination of five independent and class determining facets namely stroke width deviation, 8-histogram of edge gradients, color variation, occupation ratio, and occupy rate convex area is proposed to differentiate between text and non-text components. The probability of a component to be text is based on Text Awareness Score (TAS) that is calculated by fusing these facets in Naive Bayes using the observation possibility and prior probability of text & non-text components. Naive Bayes classifier helps in accurate and fast determination of the text awareness score and thus helps in the classification of text & non-text components with the help of graph cut algorithm. The text components have been grouped by using the mean-shift clustering algorithm which is a non-parametric technique and does not require the initial knowledge of clusters. The proposed method achieves improved results concerning precision, recall, and f-measure on the ICDAR benchmark datasets for natural scene images.

Signatures are commonly used as a unique way of identifying and verifying a person’s identity. Legal documents like bank cheques and transactions, government documents, and affidavits require signature-based verification to identify the authenticity of the person. The signature identification and verification system help to distinguish whether an input signature is honest or a fake. For very long years, this was considered to be a challenging mission when the offline mode was taken into consideration. The offline mode uses scanned signature images, where the online mode of signing process isn't existing. To overcome the signature verification challenge, an application of deep learning techniques to identify feature representations from signature images can be leveraged. In this paper, we have demonstrated how to identify valid and invalid signatures by building a signature verification and identification system that uses deep convolution neural network (ConvNet).KeywordsDeep learningConvolution neural network (ConvNet)Signature verification

In the evolving landscape of financial transactions, ensuring the security and authenticity of signature verification on bank cheques is vital to prevent fraud. This paper presents a survey of techniques used in signature verification, covering traditional image processing methods such as feature extraction, edge detection, and shape analysis, alongside modern deep learning approaches like Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and hybrid models. The survey explores key challenges, including handwriting variations, image noise, and the need for reliable real-world systems. Solutions such as pre-processing techniques, data augmentation, and transfer learning are discussed to improve accuracy. Commonly used datasets for training and evaluating models are reviewed, highlighting their features and limitations. The paper also considers ethical concerns such as fairness, transparency, and the broader implications of deploying such systems in financial institutions. By integrating insights from both traditional and advanced methods, this survey provides a valuable reference for researchers and practitioners aiming to enhance the accuracy, robustness, and reliability of signature verification systems. Strengthening these systems contributes to the overall integrity and trust in digital financial transactions. Key words: Bank Cheques, CNN, OCR, Line Sweeping.

Character recognition has been an active area of research and, due to its diverse applicable environment, it continues to be a challenging research topic. The data entry form is a convenient and successful tool for collection of information by filling the sheets with handwritten characters. For many purposes, such as documenting and archiving, extracting the handwritten characters is important. One of the most important fields in these forms is the data-filled boxes. The extraction process is important in processes of handwritten recognition techniques. Feature extraction plays an important role in different classification-based problems, such as face recognition, signature verification, optical character recognition (OCR), etc. The performance of OCR highly depends on the proper selection and extraction of a feature set. Different feature extraction methods are designed for different representations of the characters. The holistic approach is focused on feature extraction of the entire image and recognition using a neural network. This work proposes a subspace approach that regularizes and extracts Eigen features from handwritten numerals. Extracted Eigen features are recognized using a neural network. The proposed algorithm has been successfully implemented and has the added advantage of obtaining the extraction and recognition result at the same time.

AI-Driven Fraud Detection in Financial Transactions -Using Machine Learning and Deep Learning to Detect Anomalies and Fraudulent Activities in Banking and E-Commerce Transactions

This is an image text detection and extraction project with OpenCV and Optical Character Recognition (OCR) methods. Preprocessing of images is performed with OpenCV, such as grayscale, noise removal, resizing, and thresholding, to improve the quality of images. Tesseract OCR is utilized to detect and extract text and convert it into a machine-readable text. The system is also able to automatically identify Regions of Interest (ROIs) in which text is likely to reside, thus streamlining text recognition. It renders it appropriate for document digitization, text extraction from signs or license plates, and text searching within images. By automating document processing and data entry, the system minimizes manual work, raising efficiency and accuracy. It also minimizes accessibility barriers for the blind by transforming written content into accessible formats. Companies can utilize it for invoices and receipts processing, researchers for reading from historic documents, and AI programs for automated text recognition. The project is scalable since it can be able to deal with various categories of images and real-world applications. The project is applicable to data mining, archiving, and use cases where AI employs fast and effective text retrieval. It is cost-effective and effective when utilized for the processing of large volumes of text through the combination of OpenCV and OCR. Because of its capability to handle intricate images, the system is applicable in fields of automation, accessibility, and improving productivity in different fields. Keywords: Text Detection, Optical Character Recognition (OCR), OpenCV, Image Processing, Feature Extraction, Tesseract, Machine Learning, Deep Learning, Preprocessing, Computer Vision.

The increasing integration of telecommunications with financial services has brought about significant advancements in the accessibility and efficiency of financial transactions. However, this convergence has also led to a rise in fraudulent activities, posing substantial risks to both service providers and users. The application of machine learning (ML) in detecting fraud within telecommunication-based financial transactions offers a promising solution to these challenges. This abstract explores the potential of ML techniques to enhance the detection and prevention of fraud in this domain. Machine learning algorithms, particularly those specializing in anomaly detection, pattern recognition, and predictive modeling, are well-suited to identifying fraudulent activities in real-time. These algorithms can analyze vast amounts of transaction data to detect irregularities that may indicate fraud, such as unusual transaction patterns, deviations from normal behavior, and other red flags that traditional rule-based systems might overlook. By continuously learning from new data, ML models can adapt to emerging fraud tactics, making them highly effective in a rapidly evolving threat landscape. Furthermore, the integration of ML with big data analytics allows for the processing and analysis of large-scale transactional data, enhancing the accuracy and speed of fraud detection. Techniques such as supervised learning, unsupervised learning, and reinforcement learning are particularly effective in categorizing transaction types and identifying potential frauds with minimal human intervention. The use of ML also enables the automation of fraud detection processes, reducing operational costs and increasing the efficiency of fraud management systems. This abstract highlights the critical role of machine learning in enhancing the security of telecommunication-based financial transactions. The ability of ML to detect and prevent fraud in real-time not only mitigates risks but also improves trust and reliability in telecommunication financial services. As fraudsters continue to develop sophisticated methods, the ongoing refinement of ML algorithms will be essential in maintaining robust defenses against financial fraud in the telecommunication sector. Keywords: ML, Detecting, Fraud, Telecommunication-Based, Financial Transactions.

Text recognition in the wild is a challenging task in the field of computer vision and machine learning. Existing optical character recognition engines cannot perform well in the natural scene. In this context, deep learning models have emerged as a powerful state-of-the-art technique in the classification and recognition process. This study proposes a new Convolutional Neural Network based system for scene text reading. We investigate how to combine the character recognition module followed by the word recognition module to achieve the overall system goal. The first module analyzes characters within multi-scale images by relaying on the power of the convolutional network and the fully connected network for character recognition. The second module relies on the Viterbi search to find the closest word to a given characters sequence. For the sake of more precision, a bigram based linguistic module is applied. The proposed system achieves the state-of-the-art performance on three standard scene text recognition benchmarks: chars74k, ICDAR 2003 and ICDAR 2013. In particular, this performance is proven on both of character and word recognition accuracy as well as speed aspects via a comparative study between different deep learning architectures.

The integration of machine learning (ML) in supply chain management (SCM) is revolutionizing the way financial transactions are processed, monitored, and optimized. Traditional financial transaction systems within supply chains often suffer from inefficiencies, latency, fraud vulnerabilities, and limited scalability. This paper explores various machine learning approaches that enhance financial transactions in SCM by improving accuracy, speed, security, and decision-making. Specifically, the study examines supervised learning techniques such as regression and classification for credit risk assessment and payment forecasting, as well as unsupervised learning for anomaly detection and fraud prevention in transactional data. Reinforcement learning is also discussed in the context of dynamic pricing, payment scheduling, and financial risk optimization across supplier networks. Deep learning models, particularly those using neural networks, are highlighted for their capabilities in real-time financial transaction processing and predictive analytics in complex, multi-tiered supply chains. Case studies from leading industries demonstrate the effectiveness of ML in enhancing transparency, reducing transaction costs, and increasing trust between supply chain partners. Furthermore, the paper addresses challenges such as data quality, interpretability of models, regulatory compliance, and the need for robust infrastructure to support ML implementation. The research also outlines best practices for integrating ML into existing financial systems and supply chain platforms, emphasizing the importance of cross-functional collaboration among IT, finance, and operations teams. The study concludes that the adoption of ML-driven solutions can significantly elevate the performance of financial transaction systems in SCM, resulting in improved cash flow management, better supplier relationships, and more resilient supply networks. These findings offer valuable insights for businesses seeking to leverage machine learning for strategic financial and supply chain innovation. Keywords: Machine Learning, Financial Transactions, Supply Chain Management, Predictive Analytics, Anomaly Detection, Reinforcement Learning, Credit Risk Assessment, Fraud Prevention, Dynamic Pricing, Transaction Optimization.

The characters in the text image or video is having more information for recovery and indexing applications. The recognition of characters from the video text images is a difficult task due to the complex backgrounds, grey-scale values, illuminations, and sizes. Hence, various text detection algorithms like feature extracting algorithms including texture and region-based, machine learning, and deep learning approaches are implemented. Optical Character Recognition (OCR) is implemented in detecting the characters from the text frames and gives the text information including the location of the frame for text in the video. The Natural Language Processing (NLP) technique results in high performance in detecting the different text languages from the video frames. Convolutional Neural Network (CNN) algorithms are used in the feature selection process for efficient recognition of text characters from the images. The deep learning algorithms are used in textual regions in the frames of the video for detecting the text. The LSTM combined CNN networks are also implemented for extracting the features from the image for efficient and high-quality output text.

The signature recognition (SR) and verification technique is used to appreciate and confirm character’s handwritten signature. Nowadays handwritten signature is among the most commonly permitted personal attributes for identification verification. Signature verification provides authorization in financial and business transaction. Signature verification finds its application within the area of internet banking, passport verification approach, provides authentication to candidates in public examination from their signatures, credit cards, bank cheques, etc. Due to the growing amount of handwritten signatures, it is vitally fundamental that a person offline handwritten signature to be identified uniquely. A signature is a behavioral biometric characterized by way of behavioral trait that a creator learns and acquires over a period of time and turns into his specific identification. Keywords: Image, signature recognition, template matching, neural networks, support vector machine Cite this Article Priyanka Chauhan, Nirupma Tiwari. A Survey Paper on Offline Signature Recognition with Various Techniques. Journal of Artificial Intelligence Research & Advances . 2017; 4(2): 19–29p.

Financial fraud continues to threaten the integrity of digital financial systems, with traditional rule-based detection methods increasingly ineffective against evolving tactics. Recent advances suggest that integrating Machine Learning (ML) and Blockchain Technology may provide a robust solution. This study explores how this hybrid approach can improve fraud detection in financial transactions by enhancing accuracy, transparency, and response efficiency. The study adopted a quantitative research design using a publicly available dataset of over 2,500 financial transactions. Features included transaction amounts, account behavior, login attempts, and timestamps. Supervised machine learning models—Random Forest and Support Vector Machine (SVM)—were applied to classify transactions as fraudulent or legitimate. The models were trained, optimized, and evaluated using metrics such as accuracy, precision, recall, and F1-score. Descriptive analysis revealed fraud accounted for only 6.8% of transactions, confirming significant class imbalance. The Random Forest model outperformed the SVM, achieving 99.9% accuracy, precision, recall, and F1-score. TransactionAmount, TransactionDuration, and CustomerOccupation were found to be the most influential predictors. The integration of blockchain was identified as vital for secure, immutable data storage, enabling real-time auditability and enhancing the trustworthiness of the machine learning process. The combination of machine learning’s predictive power with blockchain’s immutable ledger creates a highly effective fraud detection framework. Random Forest was identified as the superior model in terms of both performance and reliability for this application. Financial institutions should adopt integrated ML-blockchain systems to strengthen fraud prevention, ensure transaction transparency, and support regulatory compliance. This study contributes to the advancement of intelligent and secure financial systems by offering empirical evidence of the value of this hybrid approach. Keywords: Fraud Detection, Machine Learning, Blockchain, Random Forest, Financial Transactions, Cybersecurity, Anomaly Detection.

This paper describes the information properties of museum specimen labels and machine learning tools to automatically extract Darwin Core (DwC) and other metadata from these labels processed through Optical Character Recognition (OCR). The DwC is a metadata profile describing the core set of access points for search and retrieval of natural history collections and observation databases. Using the HERBIS Learning System (HLS) we extract 74 independent elements from these labels. The automated text extraction tools are provided as a web service so that users can reference digital images of specimens and receive back an extended Darwin Core XML representation of the content of the label. This automated extraction task is made more difficult by the high variability of museum label formats, OCR errors and the open class nature of some elements. In this paper we introduce our overall system architecture, and variability robust solutions including, the application of Hidden Markov and Naïve Bayes machine learning models, data cleaning, use of field element identifiers, and specialist learning models. The techniques developed here could be adapted to any metadata extraction situation with noisy text and weakly ordered elements.

OCR2SEQ represents an innovative advancement in Optical Character Recognition (OCR) technology, leveraging a multi-modal generative augmentation strategy to overcome traditional limitations in OCR systems. This paper introduces OCR2SEQ’s unique approach, tailored to enhance data quality for sequence-to-sequence models, especially in scenarios characterized by sparse character sets and specialized vocabularies. At the heart of OCR2SEQ lies a set of novel augmentation techniques designed to simulate realistic text extraction errors. These techniques are adept at generating diverse and challenging data scenarios, thereby substantially improving the training efficacy and accuracy of text-to-text transformers. The application of OCR2SEQ has shown notable improvements in data processing accuracy, particularly in sectors heavily dependent on OCR technologies such as healthcare and library sciences. This paper demonstrates the capability of OCR2SEQ to transform OCR systems by enriching them with augmented, domain-specific data, paving the way for more sophisticated and reliable machine learning interpretations. This advancement in OCR technology, as presented in the study, not only enhances the accuracy and reliability of data processing but also sets a new benchmark in the integration of augmented data for refining OCR capabilities.

Everything becomes smart in the modern era, for everything we need a better plan or arrangements. In the olden days, essential information was noted as a document with the help of paper and pen or printed texts. But the intelligent world needs a paperless environment by converting handwritten or printed text documents into software copies. This can be achieved by the electronic data conversion concept called Optical Character Recognition (OCR). OCR of some documents is complex because of different writing styles and quality of scanned image issues, which can be solved by adopting a deep learning technique for better accuracy. We employed Long Short Term Memory (LSTM) for English Optical Character Recognition for paperless and effortless data storage and fast access in this work. Still, the records may contain the entities like names, contact details, drug details, diseases, educational qualifications, dates, etc. These entities cannot be separated by employing OCR alone; we need an entity recognition framework for deeper and faster data analysis. For efficient Named Entity Recognition, we utilize the Adaptive Fuzzy Inference System (ANFIS) powered by the algorithms CRF and BERT to automatically label each entity by training the vast amount of unlabeled text data. The ANFIS model is equipped with both linguistic and numerical knowledge. It is more accurate than the ANN when it comes to identifying patterns and classification data. Also, it is more transparent to the user. Our proposed framework aims to improve the performance of the character recognition system by using a feed-forward network. One of the main issues that have been identified in the development of this system is noise. Through this network, we can provide a single input and one output layer. The main components of the system are the training and recognition sections. These two sections are mainly focused on image acquisition and feature extraction. Besides these, they also include training and simulation of the classifier. The first step in the process of image recognition is to extract the features from the normalized image matrix. We then train the network using a proposed training algorithm. Experimentation on medical records attains a higher accuracy value of 0.9637, recall value of 0.9627, and f1 score of 0.9627, respectively.