Information extraction is the task of extracting structured data from a degraded document. It includes data extraction such as text, image or graphics from the sources such as an image, video or documents. Text detection and extraction from the degraded document finds application in wide range of study. In this paper, an Optical Character Recognition less (OCR-less) method of obtaining an origi...

0167-8655/$ see front matter 2013 Elsevier B.V. All rights reserved. http://dx.doi.org/10.1016/j.patrec.2013.07.007 ⇑ Corresponding author at: Department of Computer Science, Triangle Research & Development Center, Kafr Qarea, Israel. Fax: +972 4 6356168. E-mail addresses: [email protected] (R. Saabni), [email protected] (A. Asi), [email protected] (J. El-Sana). 1 These authors contribut...

We studied the effect of adjunct displays on recall in an expository text (based on McCrudden, Schraw, Lehman, & Poliquin, 2007) in order to find out which means of display aided pupils in the last years of secondary school to recall information. We included four conditions in the experiment: text only, text and causal diagram, text and images and causal diagram only. Participants were checked ...

We present a distributional semantic model combining textand image-based features. We evaluate this multimodal semantic model on simulating similarity judgments, concept clustering and the BLESS benchmark. When integrated with the same core text-based model, image-based features are at least as good as further text-based features, and they capture different qualitative aspects of the tasks, sug...

There are contents with a strong visual component, e.g., in the engineering field, such as technical drawings, charts, diagrams, etc., virtually inaccessible for people with visual disabilities (blind, visually impaired, etc.). These contents are mostly vector based and can generally be found on the Web in various formats, but the recommended one is SVG. The authors created an online applicatio...

Motivation: In recent years, with the continuing increase in available storage space, image repositories have grown to such sizes that it is becoming ever more difficult to keep track of this large amount of data. These images are usually ”unlabeled.” If these images were categorized and ”labeled,” it would allow for the simple retrieval of a specific image upon request. It is important therefo...

The proposed OCR algorithm to retrieve the text in the scanned document images. Here the text detection algorithm based on two machine learning classifiers: one allows generating candidate word regions and the other filters out non-text ones. The extract connected components (CCs) in images by using the maximally stable extremal region algorithm. In CC clustering adaboost classifiers are used t...

Often we encounter documents with text printed on complex color background. Readability of textual contents in such documents is very poor due to complexity of the background and mix up of color(s) of foreground text with colors of background. Automatic segmentation of foreground text in such document images is very much essential for smooth reading of the document contents either by human or b...

A patent always contains some images along with the text. Many text based systems have been developed to search the patent database. In this paper, we describe PATSEEK that is an image based search system for US patent database. The objective is to let the user check the similarity of his query image with the images that exist in US patents. The user can specify a set of key words that must exi...

This paper evaluates a system, UBMedTIRS, for retrieval of medical images. The system uses a combination of image and text features as well as mapping of free text to UMLS concepts. UBMedTIRS combines three publicly available tools: a content-based image retrieval system (GIFT), a text retrieval system (SMART), and a tool for mapping free text to UMLS concepts (MetaMap). The system is evaluated...