The detection of duplicates in document image databases

Doermann, David; Li, Huiping; Kia, Omid E.

doi:10.1109/icdar.1997.619863

Cited by 31 publications

(19 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With document images as queries, the task of finding similar or equivalent document images has been considered. For scanned documents it is called "document image matching" or "duplicate detection" [2,3]. This paper concerns a kind of document image matching with camera captured documents as queries.…”

Section: Introductionmentioning

confidence: 99%

Use of Affine Invariants in Locally Likely Arrangement Hashing for Camera-Based Document Image Retrieval

Nakai

Kise

Iwamura

2006

Document Analysis Systems VII

View full text Add to dashboard Cite

Abstract. Camera-based document image retrieval is a task of searching document images from the database based on query images captured using digital cameras. For this task, it is required to solve the problem of "perspective distortion" of images, as well as to establish a way of matching document images efficiently. To solve these problems we have proposed a method called Locally Likely Arrangement Hashing (LLAH) which is characterized by both the use of a perspective invariant to cope with the distortion and the efficiency: LLAH only requires Ç´AEµ time where AE is the number of feature points that describe the query image. In this paper, we introduce into LLAH an affine invariant instead of the perspective invariant so as to improve its adjustability. Experimental results show that the use of the affine invariant enables us to improve either the accuracy from 96.2% to 97.8%, or the retrieval time from 112 msec./query to 75 msec./query by selecting parameters of processing.

show abstract

Section: Introductionmentioning

confidence: 99%

Use of Affine Invariants in Locally Likely Arrangement Hashing for Camera-Based Document Image Retrieval

Nakai

Kise

Iwamura

2006

Document Analysis Systems VII

View full text Add to dashboard Cite

show abstract

“…It can therefore be used for finding duplicates in a database or for avoiding entering duplicates in the first place. Calligraphic images are now widely reproduced on the web, which makes this an actual rather than a hypothetical problem [6].…”

Section: Other Possible Applications Of Calliguimentioning

confidence: 99%

CalliGUI: Interactive Labeling of Calligraphic Character Images

Nagy

Zhang

2011

2011 International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

Abstract-Calligraphic data entry is accelerated by generating, with a feature-based character classifier, an ordered list of reference candidate labels for each character image. The improvement of labeling throughput depends on the top-N accuracy of the classifier, which in turn is a function of the available already-labeled patterns. Experiments on a database of 13,351 ancient calligraphic characters indicate that clicking on reference labels is more than twice as fast as Pinyin keyboard entry.

show abstract

“…This requires character segmentation and linking each character image with a label, a pointer to its physical location in the original source material, and a reference to the relevant bibliographic data (author, title, date, etc.). The increased level of access will facilitate studies of the evolution of calligraphic styles and shapes, developing style-based taxonomies, and detecting duplicates, copies and forgeries [1,2,3,4,5]. Access to individual character images will also increase the usefulness of the database for further experiments on calligraphic document image processing.…”

Section: Introductionmentioning

confidence: 99%

The CADAL calligraphic database

Zhang

Nagy

2011

Proceedings of the 2011 Workshop on Historical Document Imaging and Processing

View full text Add to dashboard Cite

A set of 13,351 digitized calligraphic characters were segmented and labeled, with 12,918 characters extracted from 21 books scanned by the CADAL scanning center located in Zhejiang University's library, and 1443 characters from calligraphy works from web sources. The database contains calligraphy from 208 works, some from over 1000 years ago. Statistics are provided on provenance, character size and shape, and label frequency distribution. Specific problems encountered in creating a calligraphic database are illustrated and discussed. Progress is reported on a classifier-based interactive labeling system that halves the human labor necessary to expand the database.

show abstract

The detection of duplicates in document image databases

Cited by 31 publications

References 4 publications

Use of Affine Invariants in Locally Likely Arrangement Hashing for Camera-Based Document Image Retrieval

Use of Affine Invariants in Locally Likely Arrangement Hashing for Camera-Based Document Image Retrieval

CalliGUI: Interactive Labeling of Calligraphic Character Images

The CADAL calligraphic database

Contact Info

Product

Resources

About