CIB ocr technical manual (EN)
8. Properties Text-Recognition with deepER
Instead of using Tesseract for OCR it is possible to also choose text-recognition with deepER. The OCR will be calculated on a server. A RESTFUL Service is running on the server, while the client utilizes libcurl in order to send the request.
DataFolder
InputFilename
OutputFilename
Recognize
DeeperURL
DeeperAuthentication
DeeperImageFormat
OcrGrayScaleConversion
InputFilename
This Property is mandatory.
It is not yet possible to use In-Memory-Processing for the input.
Property-Name |
Datentyp |
Art |
InputFilename |
String |
Set/Get |
This property specifies the name of the input file.
The following input-formats are supported:
- bmp image;
- tiff image (includes multipage tiff);<
- jpeg image;
- png image;
OutputFilename
Property-Name |
Data-Type |
Type |
OutputFilename |
String |
Set |
This property specifies the name of the out
putfile.
The Outputformat is fixed to hOCR.
Syntax
OutputFilename=<name>
<name>: name.ext
Example
OutputFilename=Rechnung.html
Recognize
Property-Name |
Data-Type |
Type |
Recognize |
String |
Set |
Syntax
Recognize=<Value> <Value>: OcrRecognizerWithDeeper
default=OcrRecognizer
Example
Recognize= OcrRecognizerWithDeeper
DeeperURL
Property-Name |
Data-Type |
Type |
DeeperUrl |
String |
Set |
Syntax
DEEPERURL=<Value> <Value>: http://localhost:5000
default= http://localhost:5000
Example
DeeperUrl = http://graphix:5000
DeeperAuthentication
Property-Name |
Data-Type |
Type |
DeeperAuthentication |
String |
Set |
Syntax
DEEPERURL=<Value> <Value>: User:password
default= “”
Example
DeeperUrl = Franz:TopSecret
DeeperImageFormat
Property-Name |
Data-Type |
Type |
DeeperImageFormat |
String |
Set |
Default value (if not set) is PNG. Possible values: JPG (JPEG) / PNG / Smallest.
CIB ocr converts input image into the requested format, before sending it to the deeper server.
If DeeperImageFormat is set as Smallest then CIB ocr converts the input image into both: PNG and JPG and the smallest representation will be sent to the deeper server for recognition .
OcrGrayScaleConversion
Property-Name |
Data-Type |
Type |
OcrGrayScaleConversion |
String |
Set |
Syntax
OcrGrayScaleConversion=<Value> <Value>: 0|1
Default =1
Example
OcrGrayScaleConversion = 0