Read more

Nicomsoft OCR library v4.4 is available for downloading now. Below are changes made in this version:

• Now NSOCR is cross-platform OCR, this release of OCR SDK also has a version for Linux platform.
• Added "Blk_SetWordRegEx" function that sets a regular expression for a word, a line or entire text block to improve recognition of formatted data.
• Dramatically reduced size of output PDF files for black-white input images.
• Reduced memory usage for black-white and gray images.
• Minor improvements in recognition quality.
• Updated sample projects.
• Updated documentation.

Subscribe to Nicomsoft OCR SDK news.

Download a trial version of Nicomsoft OCR SDK.

Subscribe to Nicomsoft OCR news.

Download a trial version of Nicomsoft OCR SDK.

• OCRSTEP_FIRST
• OCRSTEP_PREFILTERS
• OCRSTEP_BINARIZE
• OCRSTEP_POSTFILTERS
• OCRSTEP_REMOVELINES
• OCRSTEP_ZONING
• OCRSTEP_PREOCR
• OCRSTEP_OCR
• OCRSTEP_LAST

These steps are used in "Img_OCR" function, it has "FirstStep" and "LastStep" parameters so you can specify a range of OCR steps to execute. The most simple case is to specify full range  OCRSTEP_FIRST... OCRSTEP_LAST, so all steps are executed and entire OCR process is done. But you also can call "Img_OCR" function several times and execute steps one by one, or execute a few steps. Note that you cannot skip any steps, though you can execute some steps twice or more if necessary. So, in fact, both code samples below do exactly the same:

NsOCR.Img_OCR(ImgObj, TNSOCR.OCRSTEP_FIRST, TNSOCR.OCRSTEP_LAST, TNSOCR.OCRFLAG_NONE);

and

NsOCR.Img_OCR(ImgObj, TNSOCR.OCRSTEP_FIRST, TNSOCR.OCRSTEP_BINARIZE, TNSOCR.OCRFLAG_NONE);
//... you can get binarized image here, check if it is good and re-binarize it with different settings if necessary
NsOCR.Img_OCR(ImgObj, TNSOCR.OCRSTEP_BINARIZE + 1, TNSOCR.OCRSTEP_ZONING, TNSOCR.OCRFLAG_NONE);
//... you can analyze detected zones here, remove some of them or create new ones
NsOCR.Img_OCR(ImgObj, TNSOCR.OCRSTEP_ZONING + 1, TNSOCR.OCRSTEP_LAST, TNSOCR.OCRFLAG_NONE);

Another example: There is some image that contains both barcodes and text and you need to recognize both barcodes and text. Let's do it (assume image is already loaded to ImgObj object):

int w, h, BlkObj;
string txt1, txt2;
NsOCR.Img_OCR(ImgObj, TNSOCR.OCRSTEP_FIRST, TNSOCR.OCRSTEP_ZONING - 1, TNSOCR.OCRFLAG_NONE); //execute steps before zoning
NsOCR.Img_GetSize(ImgObj, out w, out h);
NsOCR.Img_AddBlock(ImgObj, 0, 0, w, h, out BlkObj); //create a zone that covers entire image
NsOCR.Blk_SetType(BlkObj, TNSOCR.BT_BARCODE); //mark it as barcode zone
NsOCR.Img_OCR(ImgObj, TNSOCR.OCRSTEP_ZONING, TNSOCR.OCRSTEP_LAST, TNSOCR.OCR_FLAG_NONE); //recognize all barcodes on image
NsOCR.Img_GetImgText(ImgObj, out txt1, TNSOCR.FMT_EDITCOPY); //get barcodes text
NsOCR.Img_DeleteAllBlocks(ImgObj); //remove our barcode zone
NsOCR.Img_OCR(ImgObj, TNSOCR.OCRSTEP_ZONING, TNSOCR.OCRSTEP_LAST, TNSOCR.OCRFLAG_NONE); //execute the same steps again, since now there are not any defined zones, OCR will find text/picture zones automatically and recognize them.
NsOCR.Img_GetImgText(ImgObj, out txt2, TNSOCR.FMT_EDITCOPY); //get OCRed text

Detailed description of OCR steps:

• OCRSTEP_FIRST - first step, it must be specified as "FirstStep" parameter value for first "Img_OCR" function call every time when new image is loaded or new image page is selected with "Img_SetPage" function. This step does nothing, it only marks OCR process as started.
• OCRSTEP_PREFILTERS - important step when a lot of actions are performed on loaded (original) image, the most important thing is that at the end of this step image (final) can be rescaled for the best recognition results. All functions that get or set position/size of blocks/words/characters will use coordinates of rescaled image, you can use "Img_CalcPointPosition" function to convert coordinates between original and final images.

  The following actions are applied at this step: image rotation, mirroring, inversion, deskew, rescaling, noise removing. This step can be executed only once, subsequent calls will be ignored  because at first call original image is removed to reduce memory usage.

• OCRSTEP_BINARIZE - at this step binarized image is generated.
• OCRSTEP_POSTFILTERS - at this step some additional algorithms for noise removing are applying.
• OCRSTEP_REMOVELINES - at this step NSOCR detects and removes lines and frames from the image, after this step you can get parameters of detected lines with "Img_GetPixLineCnt" and "Img_GetPixLine" functions.
• OCRSTEP_ZONING - if no blocks(zones) were created before this step, NSOCR performs autozoning, i.e. detects text and picture zones on the image. This step is ignored if some block(s) were created before this step.
• OCRSTEP_PREOCR -  additional preparations are applied at this step, for example, some blocks can be binarized again at this step.
• OCRSTEP_OCR - the main step, OCR process itself, when NSOCR recognizes text in defined zones.
• OCRSTEP_LAST - last step, it must be specified as "LastStep" parameter value at the last "Img_OCR" call. This step does nothing, it only marks OCR process as finished.

Typical mistakes:

• Some functions cannot be called if appropriate OCR steps was not executed, ERROR_MISSEDSTEP error code is returned in this case. Check API documentation for such notes, for example, you cannot call "Img_GetImgText" function if OCRSTEP_OCR step was not executed.
• Skipping OCR steps is not allowed. All steps must be executed, if some step is not necessary you can disable it in configuration.
• If you load new image or select different image page, OCR steps must be executed from the beginning, i.e. starting from OCRSTEP_FIRST step.
• OCRSTEP_PREFILTERS step can be executed only once, subsequent calls will be ignored. It is because at first call original image is removed to reduce memory usage.

Nicomsoft OCR library v4.3 is available for downloading now. Below are changes made in this version:

• Added a lot of new languages, now OCR supports 26 languages: Bulgarian, Catalan, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Hungarian, Indonesian, Italian, Latvian, Lithuanian, Norwegian, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, Turkish.
• Improved recognition quality.
• Improved spaces detection.
• Updated sample projects.
• Updated documentation.

Subscribe to Nicomsoft OCR SDK news.

Download a trial version of Nicomsoft OCR SDK.

• FINNISH
• CATALAN
• INDONESIAN
• SWEDISH
• TURKISH
• ROMANIAN
• DANISH
• NORWEGIAN
• POLISH
• HUNGARIAN
• ESTONIAN
• SLOVENIAN
• CROATIAN
• CZECH
• SLOVAK
• LITHUANIAN
• LATVIAN
• BULGARIAN

New version of OCR SDK will be available within two weeks.

Read more

An update for Nicomsoft OCR library v4.2 is available for downloading now. Below are changes made in this build:

• Fixed issue with Windows XP support.
• Fixed issue with Img_DrawToDC and Img_GetBmpData functions.

Subscribe to Nicomsoft OCR SDK news.

Download a trial version of Nicomsoft OCR SDK.

Nicomsoft OCR library v4.2 is available for downloading now. Below are changes made in this version:

• Dramatically reduced memory consumption (in several times).
• Increased recognition speed by 15-20%.
• Improved "Img_DrawToDC" and "Img_GetBmpData" functions: now they can scale image if necessary.
• Added "Img_Unload" function.
• Fixed issue with saving to PDF when input image has incorrect DPI value.
• Improved support of PDF files with big page sizes.
• Updated sample projects.
• Updated documentation.

Subscribe to Nicomsoft OCR SDK news.

Download a trial version of Nicomsoft OCR SDK.

An update for Nicomsoft OCR library v4.1 is available for downloading now. Below are changes made in this build:

• Improved page rotation detection algorithm.
• Fixed performance issue in page layout analysis module.
• Added "Svr_GetText" function.
• Improved NSOCR API wrapper for Delphi (nsocr.pas).
• Updated sample projects.
• Updated documentation.

Subscribe to Nicomsoft OCR SDK news.

Download a trial version of Nicomsoft OCR SDK.