| Case I |
|
| Thunderbird campus newspaper for American Graduate School of International Management, Arizona. OCR cleanup and basic HTML tagging. |
|
| Two sample issues |
|
| 0602070888_tif |
|
| 0602070888_text |
|
| 0603071588_tif |
|
| 0603071588_text |
| |
| Case II |
|
| OCR cleanup and tagging to create a Digital Talking Book in XML file format using the DAISY - NISO specifications developed by the National Information Standards Organization (NISO), USA and the DAISY Consortium. |
|
| Input_sample_tif |
|
| Output_sample_XML |
| |
| Case III |
|
| A leading US company holding Job Fairs every month, sends the resumes submitted by visitors. The resumes are scanned and OCR cleanup is done. Text file for each resume along with a header file containing contact information for each is sent back. Turn-around time 5 days including a weekend. |
|
| sample_resume_tif |
|
| resume_output_text |
| |
| Case IV |
|
| OCR cleanup of a large dictionary "Knight's Mechanical Dictionary" from 1881 for the digital library of a US university. |
|
| knight's_tif |
|
| knight's_mechanical_dictionary.txt |
| |
| Case V |
|
| Creation of ebooks from hardcopy for a client. |
|
| Oxford Thesaurus |
| |