scholarly journals Evolution maps and applications

2016 ◽  
Vol 2 ◽  
pp. e39 ◽  
Author(s):  
Ofer Biller ◽  
Irina Rabaev ◽  
Klara Kedem ◽  
Its’hak Dinstein ◽  
Jihad J. El-Sana

Common tasks in document analysis, such as binarization, line extraction etc., are still considered difficult for highly degraded text documents. Having reliable fundamental information regarding the characters of the document, such as the distribution of character dimensions and stroke width, can significantly improve the performance of these tasks. We introduce a novel perspective of the image data which maps the evolution of connected components along the change in gray scale threshold. The maps reveal significant information about the sets of elements in the document, such as characters, noise, stains, and words. The information is further employed to improve state of the art binarization algorithm, and achieve automatically character size estimation, line extraction, stroke width estimation, and feature distribution analysis, all of which are hard tasks for highly degraded documents.

2021 ◽  
Vol 9 (2) ◽  
pp. 855-866
Author(s):  
Amir Rajaei, Khadijeh Seimari

With the exciting development of Internet and the increasing use of it for providing or acquiring information, we are witnessing an enormous volume of text documents and online images. This is considered as information redundancy, which is one of the prominent features of modern day life. In this regard, fast and accurate access to important and favorite resources is one of the concerns of users of these enormous resources of information. Today, what is of great importance is the lack of methods to find and optimally exploit the information available, rather than the shortage or lack of information. The problem with big image data, the effort to eliminate noise and visual disturbances such as parameters from inappropriate light sources, the inadequacy of color combinations, and many other factors in received images, are very important issues in working on images and processing them. In this regard, the method of classification of the texts from the images using a fuzzy system and neural network based algorithm is suggested. In this method, the location of the fuzzy system is introduced at the begin and end of the neural network synchronized with fuzzification operation and fuzzy inversion. In fact, the main idea in this article is to eliminate or minimize noise in classifying the documents with high inaccuracy.


2018 ◽  
Vol 18 (04) ◽  
pp. 1850020
Author(s):  
Himani Sharma ◽  
D. C. Mishra ◽  
R. K. Sharma ◽  
Naveen Kumar

Conventional techniques for security of data, designed by using only one of the security mechanisms, cryptography or steganography, are suitable for limited applications only. In this paper, we propose a crypto-stego system that would be appropriate for secure transmission of different forms of data. In the proposed crypto-stego system, we present a mechanism to provide secure transmission of data by multiple safety measures, firstly by applying encryption using Affine Transform and Discrete Cosine Transform (DCT) and then merging this encrypted data with an image, randomly chosen from a set of available images, and sending the image so obtained to the receiver at the other end through the network. The data to be sent over a communication channel may be a gray-scale or colored image, or a text document (doc, .txt, or .pdf file). As it is encrypted and sent hidden in an image, it avoids any attention to itself by the observers in the network. At the receiver’s side, reverse transformations are applied to obtain the original information. The experimental results, security analysis and statistical analysis for gray-scale images, RGB images, text documents (.doc, .txt, .pdf files), show robustness and appropriateness of the proposed crypto-stego system for secure transmission of the data through unsecured network. The security analysis and key space analysis demonstrate that the proposed technique is immune from cryptanalysis.


2019 ◽  
Vol 29 (1) ◽  
pp. 1179-1187
Author(s):  
N. Karthika ◽  
B. Janet

Abstract Text documents are significant arrangements of various words, while images are significant arrangements of various pixels/features. In addition, text and image data share a similar semantic structural pattern. With reference to this research, the feature pair is defined as a pair of adjacent image features. The innovative feature pair index graph (FPIG) is constructed from the unique feature pair selected, which is constructed using an inverted index structure. The constructed FPIG is helpful in clustering, classifying and retrieving the image data. The proposed FPIG method is validated against the traditional KMeans++, KMeans and Farthest First cluster methods which have the serious drawback of initial centroid selection and local optima. The FPIG method is analyzed using Iris flower image data, and the analysis yields 88% better results than Farthest First and 28.97% better results than conventional KMeans in terms of sum of squared errors. The paper also discusses the scope for further research in the proposed methodology.


2011 ◽  
Vol 341-342 ◽  
pp. 565-569 ◽  
Author(s):  
Ahmed Dena Rafaa ◽  
Jan Nordin

One of the most important application these days in Pattern Recognition (PR) is Optical Character recognition (OCR) which is a system used to convert scanned printed or handwritten image files into machine readable and editable format such as text documents. The main motivation behind this study is to build an OCR system for offline machine-printed Turkish characters to convert any image file into a readable and editable format. This OCR system started from preprocessing step to convert the image file into a binary format with less noise to be ready for recognition. The preprocessing step includes digitization, binarization, thresholding, and noise removal. Next, horizontal projection method is used for line detection and word allocation and 8-connected neighbors’ schema is used to extract characters as a set of connected components. Then, the Template matching method is utilized to implement the matching process between the segmented characters and the template set stored in OCR database in order to recognize the text. Unlike other approaches, template matching takes shorter time and does not require sample training but it is not able to recognize some letters with similar shape or combined letters, for this reason, this OCR system combines both the template matching and the size feature of the segmented characters to achieve accurate results. Finally, upon a successful implementation of the OCR, the recognized patterns are displayed in notepad as readable and editable text. The Turkish machine-printed database consists of a list of 630 names of cities in Turkey written by using Arial font with different sizes in uppercase, lowercase and capitalizes the first character for each word. The proposed OCR’s result show that the accuracy of the system is from 96% to 100%.


Author(s):  
Alicia Fornés ◽  
Josep Lladós ◽  
Gemma Sánchez ◽  
Horst Bunke

Writer identification in handwritten text documents is an active area of study, whereas the identification of the writer of graphical documents is still a challenge. The main objective of this work is the identification of the writer in old music scores, as an example of graphic documents. The writer identification framework proposed combines three different writer identification approaches. The first one is based on the use of two symbol recognition methods, robust in front of hand-drawn distortions. The second one generates music lines and extracts information about the slant, width of the writing, connected components, contours and fractals. The third approach generates music texture images and computes textural features. The high identification rates obtained demonstrate the suitability of the proposed ensemble architecture. To the best of our knowledge, this work is the first contribution on writer identification from images containing graphical languages.


2020 ◽  
Vol 17 (9) ◽  
pp. 4368-4374
Author(s):  
Perpetua F. Noronha ◽  
Madhu Bhan

Digital data in huge amount is being persistently generated at an unparalleled and exponential rate. In this digital era where internet stands the prime source for generating incredible information, it is vital to develop better means to mine the available information rapidly and most capably. Manual extraction of the salient information from the large input text documents is a time consuming and inefficient task. In this fast-moving world, it is difficult to read all the text-content and derive insights from it. Automatic methods are required. The task of probing for relevant documents from the large number of sources available, and consuming apt information from it is a challenging task and is need of the hour. Automatic text summarization technique can be used to generate relevant and quality information in less time. Text Summarization is used to condense the source text into a brief summary maintaining its salient information and readability. Generating summaries automatically is in great demand to attend to the growing and increasing amount of text data that is obtainable online in order to mark out the significant information and to consume it faster. Text summarization is becoming extremely popular with the advancement in Natural Language Processing (NLP) and deep learning methods. The most important gain of automatic text summarization is, it reduces the analysis time. In this paper we focus on key approaches to automatic text summarization and also about their efficiency and limitations.


2015 ◽  
Vol 4 (3) ◽  
Author(s):  
Abdul Ghaffar ◽  
Muhammad Naeem Younis

AbstractMulti-walled carbon nanotubes (MWCNTs) and their oxidized derivatives were used as adsorbents for the removal of methylene blue dye from aqueous solution. CNTs have consistent surface and distinct structure, thus they were selected as the novel adsorbents in this study. The site-energy distribution analysis could provide significant information for adsorption mechanisms. Therefore, this study concentrated on the site-sorption energy distribution analysis in combination with thermodynamic behavior of methylene blue adsorption on CNTs. The single point adsorption coefficient


2019 ◽  
Vol 8 (9) ◽  
pp. 418 ◽  
Author(s):  
Ding ◽  
Fan

In recent years, volunteered-geographic-information (VGI) image data have served as a data source for various geographic applications, attracting researchers to assess the quality of these images. However, these applications and quality assessments are generally focused on images associated with geolocation through textual annotations, which is only part of valid images to them. In this paper, we explore the distribution pattern for most relevant VGI images of specific landmarks to extend the current quality analysis, and to provide guidance for improving the data-retrieval process of geographic applications. Distribution is explored in terms of two aspects, namely, semantic distribution and spatial distribution. In this paper, the term semantic distribution is used to describe the matching of building-image tags and content with each other. There are three kinds of images (semantic-relevant and content-relevant, semantic-relevant but content-irrelevant, and semantic-irrelevant but content-relevant). Spatial distribution shows how relevant images are distributed around a landmark. The process of this work can be divided into three parts: data filtering, retrieval of relevant landmark images, and distribution analysis. For semantic distribution, statistical results show that an average of 60% of images tagged with the building’s name actually represents the building, while 69% of images depicting the building are not annotated with the building’s name. There was also an observation that for most landmarks, 97% of relevant building images were located within 300 m around the building in terms of spatial distribution.


The images play a vital role in various fields of applications; medical field is the one, where images more widely used in diagnosis. Best image data analysis results if the quality of the image is high. To attain best image quality some popular techniques are available, among that image fusion is one of the technique, it enhances the information of the image by selecting and merging the significant information from two or more similar multi-focus images. Using the features of image fusion a new technique is proposed in this paper. In proposed technique, fusion of sources images with 2D Laplacian Pyramid Discrete Cosine Transformation (2D LP - DCT) and Modified Principal Component Analysis (MPCA). In this, two similar multi-focus images are considered, first, they undergone to 2D LP-DCT and then MPCA technique. The 2D LP-DCT enhances important image features, which are best utilized in image fusion and results good image quality. In Modified PCA, the concept of dimensionality reduction is used. The experimental results indicate that the suggested strategy can produce fused images with good visual quality and computational effectiveness than other state-of-the-art works.


Sign in / Sign up

Export Citation Format

Share Document