Information Retrieval from Large Document Image Collections
We focuses on the challenging problem of Information Retrieval from large document image collections. We propose to develop algorithms and approaches that are scalable to large datasets. We use and extend ideas from machine learning (ML), information retrieval (IR) and computer vision (CV) for this task. Our results are expected to impact the way retrieval is carried out from document images (documents which have textual content and image format). Effective retrieval systems built over textual content (often crawled from web) have changed the way we look at multimedia collections. Since we work on images, traditional IR solutions are not directly applicable. Popular approach is to recognize (e.g. with an OCR) the images and build a textual representation. However recognizers can be brittle and result in noisy outputs in many practical settings (e.g. historic documents, handwritten documents, Indian language documents etc.). We design representations that can scale to millions of document images seamlessly from a small corpus of annotated datasets.
Word Image Retrieval using Bag of Visual Words
In this work, we present a Bag of Visual Words (BoVW) based approach to retrieve similar word images from a large database, efficiently and accurately. We show that a text retrieval system can be adapted to build a word image retrieval solution. This helps in achieving scalability. We demonstrate the method on more than 1 Million word images with a sub-second retrieval time. We validate the method on four Indian languages, and report a mean average precision of more than 0.75. To address the lack of spatial structure in the BoVW representation, we re-rank the retrieved list.
- Language independent system : Demonstrated on 5 different languages.
- Scalable to huge datasets : Demonstrated on 1 Million images.
- Handles noisy document images : Demonstrated on dataset for which Commercial OCRs fail.
Ravi Sekhar and C V Jawahar - Word Image Retrieval Using Bag of Visual words Proceedings of 10th IAPR International Workshop on Document Analysis Systems 27-29 Mar. 2012, ISBN 978-1-4673-0868-7, pp. 297-301, Queensland, Australia. [PDF] [Poster] [bibtex]
Content Level Access to Digital Library of India Pages
In this work, we propose a framework for content level access to the scanned pages of Digital Library of India (DLI). We propose a search scheme which fuses noisy OCR output and holistic visual features for content level access to the DLI pages. Visual content is captured using Bag of Visual Words (BoVW) approach. The fusion scheme improves over the individual methods in terms of mean Average Precision (mAP) and mean precision at 10 (mPrec@10). We exploit the fact that OCR has a high precision while BoVW has a high recall.
Digital Library of India
Digital Library of India (DLI) has emerged as one of the largest collections of document images in Indian scripts. DLI, as a part of Million Book Project (MBP), has contributed to the free access of knowledge to Billions of people. In addition, it also helped in digitally archiving the rare and precious books in many of the Indian languages. All these digital contents are stored as scanned images of printed documents. A major challenge presently faced bythe DLI is the lack of content level access to the individual pages.