Content from the DAE group

DAE Random Image Selector (1)

• Download

DAE Webservice providing n random images from a given data set. 

Created: 2012-10-16

Credits: Bart Lamiroy

NCC Image Binarization (1)

• Download

Converts color or grayscale image to black-and-white. Winning contribution by the NCI/CADD group at the National Institutes of Health for the ICDAR 2011 Document Analysis Algorithm Contributions in End-to-End Applications Contest.

Created: 2012-10-16

Credits: Bart Lamiroy

NCC Document Layout Segmentation (1)

• Download

Segments a black-and-white input image into text, line drawing and picture images. Contribution by the NCI/CADD group at the National Institutes of Health for the ICDAR 2011 Document Analysis Algorithm Contributions in End-to-End Applications Contest.

Created: 2012-10-16

Credits: Bart Lamiroy

Standford Named Entity Detection (1)

• Download

 Elementary OCR workflow for execution on the on-line DAE platform. Takes a text file as input. Implements a Named entity detection algorithm by Jenny Finkel and Christopher Manning as described in Jenny Rose Finkel, Trond Grenager, and Christopher Manning. 2005. "Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling". Proceedings of the 43nd Annual Meeting of the Association for Computational Linguistics (ACL 2005), pp. 363-370. ...

Created: 2012-10-16

Credits: Bart Lamiroy

Convert (1)

• Download

Elementary workflow for execution on the on-line DAE platform. Converts an input image into another format by using the ImageMagick "convert" program.

Created: 2012-10-16 | Last updated: 2012-10-16

Credits: Bart Lamiroy

Ocrad 0.19 Basic Workflow (1)

• Download

Elementary OCR workflow for execution on the on-line DAE platform. Implement v0.19 of the ocrad OCR engine. (requires an PGM or PMB input image URL) 

Created: 2012-10-16 | Last updated: 2012-10-16

Credits: Bart Lamiroy

Tesseract 2.04 Basic Workflow (1)

• Download

 Elementary workflow for execution on the on-line DAE platform. (requires an uncompressed tiff image URL as input or will fail otherwise)

Created: 2012-10-16

Credits: Bart Lamiroy

ICDAR 2011 End-to-End Applications contest... (1)

• Download

Full workflow for use with the DAE platform and as used for the ICDAR 2011 "Document Analysis Algorithm Contributions in End-to-End Applications" contest, including contributed algorithms.

Created: 2012-04-14 | Last updated: 2012-04-14

Credits: Bart Lamiroy

localhost Tesseract-Ocrad comparison (3)

• Download

Simple demo workflow, for use with a standalone (localhost) version of the DAE platform. Compares Tesseract and Ocrad OCR results. For demonstration reasons and ease of use, this workflow has hardcoded username/password values. This is, obviously, very bad, but since it relates only to a sandboxed virtual server, potential damage is null.

Created: 2012-03-16 | Last updated: 2012-05-16

Credits: Bart Lamiroy

Simple Tesseract-Ocrad comparison (1)

• Download

Simple demonstration workflow for use with the on-line Lehigh-based DAE server, comparing the results of Tesseract and Ocrad OCR engines on a specific document image.

Created: 2012-03-16 | Last updated: 2012-03-16

Credits: Bart Lamiroy