Vividata features three OCR products: |
OCR Shop XTR: Command-line driven OCR software for high volume OCR applications. Designed for applications requiring customization and flexibility. |
OCR Shop XTR Lite: Simplified, command-line driven OCR software based on OCR Shop XTR. Designed for applications with basic image conversion requirements. |
OCR Shop XTR/API : An SDK encompassing an optical character recognition and image processing API for developing large applications. Operations using the API may be completed in small, interactive steps for maximum control and flexibility. |
OCR Shop XTR/API | |||
Features | |||
Programmatic usage | yes |
yes |
yes |
Image to searchable PDF conversion |
yes
|
yes |
|
Forms processing | yes |
yes |
|
Server farm support | yes |
yes |
|
Document and image analysis | yes | yes | |
Embedded systems | yes
|
||
TCP/IP distributed processing | yes | ||
Basics of Usage | |||
Interface |
command-line
|
command-line
|
C/C++ API
|
Invokable from scripting languages, such PERL, shell scripts, and php | yes | yes | |
Invokable from languages, such as Java and C/C++ | yes | yes | yes |
Interactive feedback and control | yes | ||
Input Formats and Functionality | |||
JPEG, GIF, PPM, and other raster formats |
yes
|
yes
|
yes
|
Multi-page TIFF |
yes
|
yes
|
yes
|
PDF * |
yes
|
yes
|
yes
|
PostScript® * |
yes
|
yes
|
yes
|
Contrast control |
yes
|
yes
|
|
Resolution control | yes | yes | |
File I/O | yes | yes | yes |
Memory and socket I/O | yes | ||
Processing and Recognition Functionality | |||
Point size range |
default (5-72)
|
configurable within 5-72
|
configurable within 5-72
|
Auto-deskew |
automatic
|
configurable
|
configurable
|
Auto-orientation correction |
automatic
|
configurable
|
configurable
|
Auto-photometric interpretation |
automatic
|
configurable
|
configurable
|
Inverted region detection |
automatic
|
configurable
|
configurable
|
dot-matrix processing |
automatic
|
configurable
|
configurable
|
Special fax processing |
automatic
|
configurable
|
configurable
|
Special newsprint processing |
automatic
|
configurable
|
configurable
|
Degraded document mode |
automatic
|
automatic
|
configurable
|
By region |
yes
|
yes
|
|
Output Formats and Functionality | |||
ASCII text |
yes
|
yes
|
yes
|
Unicode |
yes
|
yes
|
yes
|
HTML* |
yes
|
yes
|
|
PDF* |
yes
|
yes
|
|
XDOC† | yes
|
yes
|
|
Document layout information | in output |
in output
and interactively |
|
Character and word confidences† | yes |
yes |
|
Character and word coordinates† | yes |
yes |
|
Image region output |
yes
|
yes
|
|
Output on a region basis | yes | yes | |
Resolution scaling | yes | yes | |
Pixel depth control | yes | yes | |
File I/O | yes | yes | yes |
Memory and socket I/O | yes | ||
1 output document per input document | always | yes | yes |
1 output document may encompass multiple input documents | yes | yes | |
output by region | yes | yes | |
Language Support | |||
Total number |
56**
|
56**
|
56**
|
Recognition of multiple languages |
yes
|
yes
|
yes
|
User lexicon |
yes
|
yes
|
To learn more about the language features: Refer to the Documentation for
each product.
For purchasing information, refer to the individual product pricing pages: OCR Shop XTR Pricing, OCR Shop XTR Lite Pricing, OCR Shop XTR/API Pricing
Contact Vividata Sales for more information.
* These features are licensed as Optional Add-on Modules. Please Contact
Sales for more information.
** Each product comes with one language; additional languages may be purchased.
†The XDOC format provides detailed information about text, images, and formatting, including: word and character confidence values, word and character coordinates, whitespace coordinates, image placement, font characteristics, and layout information.