OCR for Local File

Options

File

Input image or PDF

Language (*)

Language used for OCR. If no language is specified, English eng is taken as default.

IMPORTANT: The language code has always 3-letters (not 2). So it is eng and not en.

Engine2 has automatic Western language detection, so this value will be ignored. Any Western language can be processed.

Engine3 supports additional writing systems/languages. More can be added on request.

• Arabic=ara
• Bulgarian=bul
• Chinese(Simplified)=chs
• Chinese(Traditional)=cht
• Croatian = hrv
• Czech = cze
• Danish = dan
• Dutch = dut
• English = eng
• Finnish = fin
• French = fre
• German = ger
• Greek = gre
• Hungarian = hun
• Korean = kor
• Italian = ita
• Japanese = jpn
• Polish = pol
• Portuguese = por
• Russian = rus
• Slovenian = slv
• Spanish = spa
• Swedish = swe
• Turkish = tur

Engine3 also supports:

• Hindi = hin
• Kannada = kan
• Persian (Fari) = per
• Telugu = tel
• Tamil = tam
• Thai = tai
• Vietnamese = vie

Is Overlay Required

If true, returns the coordinates of the bounding boxes for each word. If false, the OCR'ed text is returned only as a text block (this makes the JSON reponse smaller). Overlay data can be used, for example, to show text over the image.

Filetype (*)

Overwrites the automatic file type detection based on content-type. Supported image file formats are png, jpg (jpeg), gif, tif (tiff) and bmp. For document ocr, the api supports the Adobe PDF format. Multi-page TIFF files are supported.

Detect Orientation

If set to true, the api autorotates the image correctly and sets the TextOrientation parameter in the JSON response. If the image is not rotated, then TextOrientation=0, otherwise it is the degree of the rotation, e. g. "270".

Is Create Searchable Pdf

If true, API generates a searchable PDF. This parameter automatically sets isOverlayRequired = true.

Is Searchable Pdf Hide Text Layer

If true, the text layer is hidden (not visible)

Scale

If set to true, the api does some internal upscaling. This can improve the OCR result significantly, especially for low-resolution PDF scans. Note that the front page demo uses scale=true, but the API uses scale=false by default. See also this OCR forum post.

Is Table

If set to true, the OCR logic makes sure that the parsed text result is always returned line by line. This switch is recommended for table OCR, receipt OCR, invoice processing and all other type of input documents that have a table like structure.

OCR Engine

The OCR API offers two different OCR engine with a different processing logic. We recommend that you try both and then use whatever engine gives you the best OCR result. You can use both OCR engines with our free online OCR service on the front page and with the OCREngine=1/2 parameter in your API call.

Features of OCR Engine 1:

• Supports many languages (including Asian languages like Chinese, Japanese and Korean)
• Fastest OCR
• Supports larger images
• Multi-Page TIFF scan support

Features of OCR Engine 2:

• Western Latin Character languages only (English, German, French,...)
• Language auto-detect. It does not matter what OCR language you select, as long as it uses Latin characters
• Usually better at single number OCR, single character OCR and alphanumeric OCR in general (e. g. SUDOKO, Dot Matrix OCR, MRZ OCR, Single digit OCR, Missing 1st letter after OCR, ... )
• Usually better at special characters OCR like @+-...
• Usually better with rotated text (Forum: Detect image spam)
• Image size limit 5000px width and 5000px height

Features of OCR Engine 3:

• Experimental new OCR Engine. The key advantage of using this OCR engine is the expanded language support. The drawback is that it is a bit slower, especially for larger images.
• Additional, new languages (not available in Engine1 and 2) are: Hindi, Kannada, Persian (Fari), Telugu, Tamil, Thai and Vietnamese. (Contact us of you need any other OCR language/script)
• The recognition logic works different than OCR Engine 1 and 2. So if you have a situation where E1 or E2 can not read the OCR input correctly, try it with Engine3 - it might work!
• Hint: For best number OCR results (e. g. invoice amount, date, order ID, math symbol) select an Asian language as OCR language e. g. Korean. If you have some numbers that OCR.space can not read yet, please contact us.
• Image size limit FREE OCR Api 1000px width and 1000px height, PRO API: 5000px width and 5000px height

Features of OCR Engine 5:

• Experimental new OCR Engine. The advantage of using this OCR engine is its high speed for larger images and overall good detection accurracy.
• The recognition logic works different than OCR Engine 1 and 2. So if you have a situation where E1 or E2 can not read the OCR input correctly, try it with Engine5 - it might work!

Enterprise Support: Both OCR engines 1+2 are available for offline, self-hosting as On-Premise OCR!

The returned OCR result JSON response is identical for both engines! You can switch between both engines as needed. The features that are not mentioned in this OCR engine comparison are the same for both engines, for example PDF OCR, detect orientation and receipt scanning support. If you have any question about using the different OCR engines, please ask in our OCR API Forum.

Result Format

Specify how the response should be mapped to the table output. The following formats are available:

• Raw Response: Returns the raw response in a single row with the following columns:
  • body: Response body
  • status: HTTP status code

Views

This node has no views

Workflows

• No workflows found

Links

• No links available

Developers