Retrieval from Document Image Collections

Balasubramanian, A. R.; Meshesha, Million; Jawahar, C. V.

doi:10.1007/11669487_1

Cited by 43 publications

(31 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Three coarse features such as word profiles, structural features and transform domain represented was addressed to indicate the features of a word image [13] [3]. Feature values are normalized such that the word representations become insensitive to variations in size, fonts and degradations.…”

Section: Related Workmentioning

confidence: 99%

Online Information Search from Tamil Document Images in World Wide Web

Abirami¹,

Murugappan²

2012

IJCA

View full text Add to dashboard Cite

Information Retrieval (IR) from Tamil document images present in World Wide Web (WWW) has become a challenging problem today due to its rising popularity. Among the most valuable Web assets, categorizing web images and retrieval of information from the images on the Web is quite difficult. This paper proposes a simple and effective method to separate the document images from the available web image sources and to retrieve the information present in those web document images. This system works in two phases: In the first phase, it concentrates on Automatic Image categorization process over web images by employing a filtering technique to discriminate the document images from other images available in WWW. Filtering technique employed here captures the image information by intensity and frequency histograms to discriminate the web document images. As for information retrieval in the second phase, feature string generation technique has been used to generate feature strings for every word images by extracting its shape this generates a feature string for every word image by extracting its features relying on their statistical properties, such as lines, black and white disposition rates and outline features of characters, instead of recognizing the letters and assigning its ASCII value like OCR. This kind of information retrieval has been initiated over a list of web sites and experimental results are recorded.

show abstract

Section: Related Workmentioning

confidence: 99%

Online Information Search from Tamil Document Images in World Wide Web

Abirami¹,

Murugappan²

2012

IJCA

View full text Add to dashboard Cite

show abstract

“…Besides the works of William Clocksin [1], no previous work has been published on Syriac handwriting recognition. Different approaches exist for handwriting recognition in historical manuscripts.…”

Section: Related Workmentioning

confidence: 99%

“…To overcome the morphological differences between the words, the matching is performed using a Dynamic Time Warping (DTW) algorithm. DTW is also used in [1] to match whole words. Another segmentation-free approach which uses HMMs and statistical language models for handwritten text recognition is described in [13].…”

Section: Related Workmentioning

confidence: 99%

Local Orientation Extraction for Wordspotting in Syriac Manuscripts

Bilane

Bres

Emptoz

2008

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper presents a contribution to Word Spotting applied for digitized Syriac manuscripts. The Syriac language was wrongfully accused of being a dead language and has been set aside by the domain of handwriting recognition. Yet it is a very fascinating handwriting that combines the word structure and calligraphy of the Arabic handwriting with the particularity of being intentionally written tilted by an angle of approximately 45°. For the spotting process, we developed a method that should find all occurrences of a certain query word image, based on a selective sliding window technique, from which we extract directional features and afterwards perform a matching using Euclidean distance correspondence between features. The proposed method does not require any prior information, and does not depend of a word to character segmentation algorithm which would be extremely complex to realize due to the tilted nature of the handwriting.

show abstract

“…However, we annotate each of the clusters, instead of directly using them to build the index. An attempt at manual annotation of word image clusters was reported in [23], which is generally un-affordable. The motivation to use an annotation based approach comes from recent interest in automatic annotation [16,17,15].…”

Section: Related Workmentioning

confidence: 99%

Enabling Search over Large Collections of Telugu Document Images – An Automatic Annotation Based Approach

Sankar

Jawahar

2006

Computer Vision, Graphics and Image Processing

Self Cite

View full text Add to dashboard Cite

Abstract. For the first time, search is enabled over a massive collection of 21 Million word images from digitized document images. This work advances the state-of-the-art on multiple fronts: i) Indian language document images are made searchable by textual queries, ii) interactive content-level access is provided to document images for search and retrieval, iii) a novel recognition-free approach, that does not require an OCR, is adapted and validated iv) a suite of image processing and pattern classification algorithms are proposed to efficiently automate the process and v) the scalability of the solution is demonstrated over a large collection of 500 digitised books consisting of 75,000 pages.Character recognition based approaches yield poor results for developing search engines for Indian language document images, due to the complexity of the script and the poor quality of the documents. Recognition free approaches, based on word-spotting, are not directly scalable to large collections, due to the computational complexity of matching images in the feature space. For example, if it requires 1 mSec to match two images, the retrieval of documents to a single query, from a large collection like ours, would require close to a day's time. In this paper we propose a novel automatic annotation based approach to provide textual description of document images. With a one time, offline computational effort, we are able to build a text-based retrieval system, over annotated images. This system has an interactive response time of about 0.01 second. However, we pay the price in the form of massive offline computation, which is performed on a cluster of 35 computers, for about a month. Our procedure is highly automatic, requiring minimal human intervention.

show abstract

Retrieval from Document Image Collections

Cited by 43 publications

References 4 publications

Online Information Search from Tamil Document Images in World Wide Web

Online Information Search from Tamil Document Images in World Wide Web

Local Orientation Extraction for Wordspotting in Syriac Manuscripts

Enabling Search over Large Collections of Telugu Document Images – An Automatic Annotation Based Approach

Contact Info

Product

Resources

About