Document Image Analysis

—The current document blur/quality estimation algorithms rely on the OCR accuracy to measure their success. A sharp document image, however, at times may yield lower OCR accuracy owing to factors independent of blur or quality of capture. The necessity to rely on OCR is mainly due to the difficulty in quantifying the quality otherwise. In this work, we overcome this limitation by proposing a novel dataset for document blur estimation, for which we physically quantify the blur using a capture setup which computationally varies the focal distance of the camera. We also present a selective search mechanism to improve upon the recently successful patch-based learning approaches (using codebooks or convolutional neural networks). We present a thorough analysis of the improved blur estimation pipeline using correlation with OCR accuracy as well as the actual amount of blur. Our experiments demonstrate that our method outperforms the current state-of-the-art by a significant margin.

The current Document Image Quality Assessment (DIQA) algorithms directly relate the Optical Character Recognition (OCR) accuracies with the quality of the document to build supervised learning frameworks. This direct correlation has two major limitations: (a) OCR may be affected by factors independent of the quality of the capture and (b) it cannot account for blur variations within an image. An alternate possibility is to quantify the quality of capture using human judgement, however, it is subjective and prone to error. In this work, we build upon the idea of Spatial Frequency Response (SFR) to reliably quantify the quality of a document image. We present through quantitative and qualitative experiments that the proposed metric leads to significant improvement in document quality prediction in contrast to using OCR as ground truth.

A multi-font, multi-size Optical Character Recognizer (OCR) of Tamil Script is developed. The input image to the system is binary and is assumed to contain only text. The skew angle of the document is estimated using a combination of Hough transform and Principal Component Analysis. A multi-rate-signal-processing based algorithm is devised to achieve distortion-free rotation of the binary image during skew correction. Text segmentation is noise-tolerant. The statistics of the line height and the character gap are used to segment the text lines and the words. The images of the words are subjected to morphological closing followed by connected component-based segmentation to separate out the individual symbols. Each segmented symbol is resized to a pre-fixed size and thinned before it is fed to the classifier. A three-level, tree-structured classifier for Tamil script is designed. The net classification accuracy is 99.0%.

Ink analysis provides significant information to forensic document examiners to
determine the authenticity of the questioned documents. Ink mismatch detection
potentially leads to determination of forgery, backdating and fraud. In this work a nondestructive automated document examination system using hyperspectral imaging and deep learning is presented, which successfully discriminates between different inks mixtures that are visually similar in appearance. Automated ink mismatch detection approach is used on hyperspectral datasets comprising of different mixing proportions of various blue and black inks notes taken from Writing Ink Hyperspectral Image Database. The state-of-the-art Convolutional Neural Network (CNN) method is used to learn optimum features directly from the ink samples in the database. The trained CNN is used to classify ink pixels in an input image. Some real data inks mixture experiments are presented to demonstrate the efficacy of this proposed approach. We expect that these finding will further encourage the use of hyperspectral imaging along with deep learning in document analysis, particularly for automated questioned document examination.

Document image classification is an important step in Office Automation, Digital Libraries, and other document image analysis applications. There is great diversity in document image classifiers: they differ in the problems they solve, in the use of training data to construct class models, and in the choice of document features and classification algorithms. We survey this diverse literature using three components: the problem statement, the classifier architecture, and performance evaluation. This brings to light important issues in designing a document classifier, including the definition of document classes, the choice of document features and feature representation, and the choice of classification algorithm and learning mechanism. We emphasize techniques that classify single-page typeset document images without using OCR results. Developing a general, adaptable, high-performance classifier is challenging due to the great variety of documents, the diverse criteria used to define document classes, and the ambiguity that arises due to ill-defined or fuzzy document classes.

Over the past three decades, significant developments have been made in hyperspectral imaging due to which it has emerged as an effective tool in numerous civil, environmental, and military applications. Modern sensor technologies are capable of covering large surfaces of earth with exceptional spatial, spectral, and temporal resolutions. Due to these features, hyperspectral imaging has been effectively used in numerous remote sensing applications requiring estimation of physical parameters of many complex surfaces and identification of visually similar materials having fine spectral signatures. In the recent years, ground based hyperspectral imaging has gained immense interest in the research on electronic imaging for food inspection, forensic science, medical surgery and diagnosis, and military applications. This review focuses on the fundamentals of hyperspectral image analysis and its modern applications such as food quality and safety assessment, medical diagnosis and image guided surgery, forensic document examination, defense and homeland security, remote sensing applications such as precision agriculture and water resource management and material identification and mapping of artworks. Moreover, recent research on the use of hyperspectral imaging for examination of forgery detection in questioned documents, aided by deep learning, is also presented. This review can be a useful baseline for future research in hyperspectral image analysis.

The thesis concentrates on computational methods pertaining to ancient ostraca - ink on clay inscriptions, written in Hebrew. These texts originate from the biblical kingdoms of Israel and Judah, and dated to the late First Temple period (8th – early 6th centuries BCE). The ostraca are almost the sole remaining epigraphic evidence from the First Temple period and are therefore important for archaeological, historical, linguistic, and religious studies of this era. This “noisy” material offers a fertile ground for the development of various “robust” image analysis, image processing, computer vision and machine learning methods, dealing with the challenging domain of ancient documents’ analysis. The common procedures of modern epigraphers involve manual and labor-intensive steps, facing the risk of unintentionally mixing documentation with interpretation. Therefore, the main goal of this study is establishing a computerized paleographic framework for handling First Temple period epigraphic material. The major research questions, addressed in this thesis are: quality evaluation of manual facsimiles; quality evaluation of ostraca images; automatic binarization of the documents and its subsequent refinement; quality evaluation of binarizations on global and local levels; identification of different writers between inscriptions (two distinct methods are proposed); image segmentation (with improvements over the classical Chan-Vese algorithm); and letters’ shape prior estimation. The developed methods were tested on real-world archaeological and modern data and their results are found to be favorable.

Data mining and knowledge discovery in databases have been attracting a significant amount of research, industry, and media attention of late. There is an urgent need for a new generation of computational theories and tools to assist researchers in extracting useful information from the rapidly growing volumes of digital data

—Due to the rapid increase of different digitized documents, the development of a system to automatically retrieve document images from a large collection of structured and unstructured document images is in high demand. Many techniques have been developed to provide an efficient and effective way for retrieving and organizing these document images in the literature. This paper provides an overview of the methods which have been applied for document image retrieval over recent years. It has been found that from a textual perspective, more attention has been paid to the feature extraction methods without using OCR.

Handwriting is one of the most common types of questioned writing encountered and frequently attracts the attention in litigation. Contrary to the physiological characteristics, handwriting is a behavioral characteristic thus no two individuals with mature handwriting are exactly alike or an individual cannot produce the others writing exactly. Writing behavior and individualities are examined for similarities for both specimen and questioned document, thus, it is very efficient and effective strategy for biometrics. In this paper, we present a comprehensive review of writer identification methods and intend to provide taxonomy of dataset, feature extraction methods, as well as classification (conventional and deep learning based) for writer identification. For ease of reader, we grouped the discussion into English, Arabic, Western and Other languages from script prospective, whereas, from algorithm and methods perspective, we grouped the discussion with respect to implementation steps sequence. In the end, we highlighted the challenges and open research issues in the field of writer identification. Finally, we also suggest future direction.

Comics are complex documents whose reception engages cognitive processes such as scene perception, language processing, and narrative understanding. Possibly because of their complexity , they have rarely been studied in cognitive science. Modeling the stimulus ideally requires a formal description, which can be provided by feature descriptors from computer vision and computational linguistics. With a focus on document analysis, here we review work on the computational modeling of comics. We argue that the development of modern feature descriptors based on deep learning techniques has made sufficient progress to allow the investigation of complex material such as comics for reception studies, including experimentation and computational modeling of cognitive processes.

Parergon. A documentary hermeneutic in contemporary art: the situation of Land Art
This work focuses on how artworks that are not sufficient in themselves can be defined. We here refer to artworks needing to be completed by recordings or documents – such as sculptures from contemporary art or Land Art. Although tangible, these artworks are uneasy to exhibit because they cannot be removed from the remote areas where they stand. Therefore, the documents matching the artworks allow the institution to realize their form. We call parergon, from Ancient Greek (“accessory”), a recording of the artwork’s form. That kind of document leads the viewer to the path of aesthetic reception. Here is the paradox: this aesthetic experience is not allowed by the artwork itself, but by a beside work. In order to justify the use of this antic word in a contemporary context, this work first studies its old uses, to bring out the fact that the parergon can only be found in some misunderstanding between what is essential and what is accessory in an artwork. In that case, the confusion can only be cleared up by interpretation. This problem is philosophically continued by the question of the artwork’s limits: where does a piece of art coming in many different forms begin or end? This study shows that before initiating Land Art practices, a deconstruction of the instant presence of artworks in museums was required. However, photography is not only the sculpture’s extension in the institution. It is also for the artwork, a way to appear only as a location elected by the artist as worthy to be artificially exhibited. Finally, the analysis of specific examples helps to show that the parergon does not only lie in sculptures’ photographs, but is also a documentary way to make a photographic work of art.

Keywords: parergon, artwork, Land Art, deconstruction, photography, interpretation, document

D. Stutzmann, « Intelligence artificielle et humanités numériques : déchiffrement des écritures médiévales, analyse des écritures et étude des sources en SHS», La lettre de l'InSHS, n° 54, juillet 2018 [http://www.cnrs.fr/inshs/Lettres-information-INSHS/lettre_infoinshs54hd.pdf]

Forensic applications have great importance in the digital era, for the investigation of different types of crimes. The forensic analysis includes Deoxyribonucleic Acid (DNA) test, crime scene video and images, forged documents analysis, computer-based data recovery, fingerprint identification, handwritten signature verification and facial recognition. The signatures are divided into two types i.e. genuine and forgery. The forgery signature can lead to the huge amount of financial losses and create other legal issues as well. The process of forensic investigation for the verification of genuine signature and detection of forgery signatures in law related departments has been manual and the same can be automated using digital image processing techniques, and automated forensic signature verification applications. The signatures represent any person's authority so the forged signatures may also be used in a crime. Research has been done to automate the forensic investigation process, but due to the internal variations of signatures, the automation of signature verification still remained a challenging problem for researchers. In this paper, we have further extended previous research carried out in [1-2] and proposed a Forensic signature verification model based on two classifiers i.e. Multilayer Perceptron (MLP) and Random Forest for the classification of genuine and forgery signatures.

Document Image processing and Optical Character Recognition (OCR) have been a frontline research area in the field of human-machine interface for the last few decades. Recognition of Indian language characters has been a topic of interest for quite some time. The earlier contributions were reported in [1] and [2]. A more recent work is reported in [3] and [9]. The need for efficient and robust algorithms and systems for recognition is being felt in India, especially in the post and telegraph department where OCR can assist the staff in sorting mail. Character recognition can also form a part in applications like intelligent scanning machines, text to speech converters, and automatic language-to-language translators.

8
th International Conference on Data Mining (DaMi 2022) Conference provides a forum for
researchers who address this issue and to present their work in a peer-reviewed forum.
Authors are solicited to contribute to the conference by submitting articles that illustrate research
results, projects, surveying works and industrial experiences that describe significant advances in
the following areas, but are not limited to.

Page 1. A Two-Step Dewarping of Camera Document Images ... Abstract Dewarping of camera document images has attracted a lot of interest over the last few years since warping not only reduces the document readability but also affects the accuracy of an OCR application. ...

Multispectral imaging allows for analysis of images in multiple spectral bands. Over the past three decades, airborne and satellite multispectral imaging have been the focus of extensive research in remote sensing. In the recent years, ground based multispectral imaging has gained an immense amount of interest in the fields ranging from computer vision and medical imaging to art, archaeology and computational forensics. The rich information content in multispectral images allows forensic experts to examine the chemical composition of forensic traces. Due to its rapid, non-contact and non-destructive characteristics, multispectral imaging is an effective tool for visualization, age estimation, detection and identification of forensic traces in document images. Ink mismatch is a key indicator of forgery in a document. Inks of different materials exhibit different spectral signature even if they have the same color. Multispectral analysis of questioned documents images allows identification and discrimination of visually similar inks. In this paper, an efficient automatic ink mismatch detection technique is proposed which uses Fuzzy C-Means Clustering to divide the spectral responses of ink pixels in handwritten notes into different clusters which relate to the unique inks used in the document. Sauvola's local thresholding technique is employed to efficiently segment foreground text from the document image. Furthermore, feature selection is used to optimize the performance of the proposed method. The presented method provides better ink discrimination results than state-of-the-art methods when tested on publicly available UWA Writing Inks Dataset.

Objectives: A framework for character recognition is essential used to convert a digital image of character into machine
coded format character. This fundamental trademark can be used to determine numerous real life applications. Methods/
Statistical Analysis: To classify hand-written documents, either offline or online, the recognition of character is
tremendously influenced by variety of styles of same writer on various circumstances and even different writers. Distortion
and noise included during digitization is additionally a noteworthy issue in recognition of character that influences the
recognition/classification accuracy adversely. Findings: It has been get to know that recognition of hand-written Gurmukhi
characters is an exceptionally troublesome task. There are enormous difficulties in handwritten character recognition
because of various writing style of scholars. This paper presents various techniques presented by different researchers for
Punjabi character recognition work. It has been also noticed that recognition accuracy depends upon volume of training
dataset and testing dataset and may be improved by using various optimized feature selection techniques. Application/
Improvements: A lot of research papers have been surveyed and it is seen that work on different strategies have been
attempted.

In this article, we present a novel set of features for detection of text in images of natural scenes using a multi-layer perceptron (MLP) classifier. An estimate of the uniformity in stroke thickness is one of our features and we obtain the same using only a subset of the distance transform values of the concerned region. Estimation of the uniformity in stroke thickness on the basis of sparse sampling of the distance transform values is a novel approach. Another feature is the distance between the foreground and background colors computed in a perceptually uniform and illumination-invariant color space. Remaining features include two ratios of anti-parallel edge gradient orientations, a regularity measure between the skeletal representation and Canny edgemap of the object, average edge gradient magnitude, variation in the foreground gray levels and five others. Here, we present the results of the proposed approach on the ICDAR 2003 database and another database of scene images consisting of text of Indian scripts.

In this thesis, realistic looking isolated character images indistinguishable from a writer’s individualistic writing were pseudo randomly generated by using a statistical model which learns that writer’s characteristic handwriting style. Hitherto research focus had been on modeling the human writing process or analyzing dynamic handwriting data, neither of which are viable approaches for widespread application in the growing human computer interaction technology. A writer specific statistical model of the most influential handwriting features was trained from multiple samples of each letter written by that writer from an optimal handwriting sampling text passage. Each sample letter was analyzed and new letters synthesized as a sequence of connected sub-strokes, using control-point extraction and clustering by correspondence search of multiple samples, followed by stroke curve synthesis using spline interpolation functions.

Several significant algorithms were tested for each stage of the synthesis procedure to find the techniques optimal for static handwriting data: entropy based threshold for character image extraction; Kuwahara filter for de-noising; Zhang-Suen algorithm for skeletonization; distance transform for control-point selection; shape-context descriptor for control-point correspondence search; thin plate splines for control-point transformation; and interpolating splines for generating stroke curves. Empirical results indicate that the novel combination of handwriting specific algorithms in this thesis can generate realistic synthetic handwriting in a given writer’s unique style, of satisfactory quality.