FindImageText
✖
FindImageText
Details and Options



- FindImageText is used to detect the region of an image containing text. When asking for a specific structural level, it returns a list of bounding boxes, each given as a Parallelogram.
- Coordinates {x,y} are assumed to be in the standard image coordinate system.
- Use TextRecognize to recognize the content of the detected text.
- Possible settings for level include:
-
Automatic text found in the whole image as a single result (default) "Block" a list of results for each block of text "Line" a list of results for each line "Word" a list of results for each word "Character" a list of results for each character - Possible settings for prop include:
-
"AlignedImage" cropped aligned image containing each detected text "BoundingBox" bounding box around each detected text as a Rectangle "BoundingBoxArea" area of the bounding box around each text "Confidence" strength of the recognized text "DeskewAngle" deskew angle of the detected text "Image" cropped image containing the detected text "OrientedBoundingBox" parallelogram around each detected text (default) "RegionCentroid" centroid of bounding box around the text {prop1,prop2,…} a list of properties - The following options can be specified:
-
AcceptanceThreshold Automatic detection acceptance threshold MaxFeatures All number of text boxes to return MaxOverlapFraction Automatic maximum allowed overlap fraction Method Automatic method to use PaddingSize 0 amount of padding around each detection - Possible settings for Method include:
-
Automatic automatic choice of the method "Document" optimized for detection in scanned documents "NaturalScene" optimized for detection in natural scene images detector the text detection method to use - Possible setting for detector are:
-
"DBNet" differentiable binarization net "Tesseract" Tesseract engine - FindImageText uses machine learning. Its methods, training sets and biases included therein may change and yield varied results in different versions of the Wolfram Language.
- FindImageText may download resources that will be stored in your local object store at $LocalBase, and that can be listed using LocalObjects[] and removed using ResourceRemove.

Examples
open allclose allBasic Examples (2)Summary of the most common use cases
Scope (8)Survey of the scope of standard use cases
Basic Uses (2)
Level (1)
Detect the text content of an image:

https://wolfram.com/xid/0dquynhfmr2-uui0zv


https://wolfram.com/xid/0dquynhfmr2-7jgkso


https://wolfram.com/xid/0dquynhfmr2-qa1k1d


https://wolfram.com/xid/0dquynhfmr2-8kkp8f


https://wolfram.com/xid/0dquynhfmr2-vrgvgy

Properties (5)
By default, an oriented bounding box is returned for every detection:

https://wolfram.com/xid/0dquynhfmr2-v6fc1h

Return the standard axis-aligned bounding box:

https://wolfram.com/xid/0dquynhfmr2-hkzhav

Extract the portion of the image containing each detected word:

https://wolfram.com/xid/0dquynhfmr2-mf2nse

Align the crops to the image frame:

https://wolfram.com/xid/0dquynhfmr2-51au1w

Extract the bounding box area of each detected word:

https://wolfram.com/xid/0dquynhfmr2-fsemn0

Region centroid of every word:

https://wolfram.com/xid/0dquynhfmr2-ccs6wz

Compute and return multiple properties at once:

https://wolfram.com/xid/0dquynhfmr2-thb4jn

Options (7)Common values & functionality for each option
AcceptanceThreshold (1)
MaxFeatures (1)
By default, all detected text is returned:

https://wolfram.com/xid/0dquynhfmr2-ssi381

Use MaxFeatures30 to return only the 30 strongest detections:

https://wolfram.com/xid/0dquynhfmr2-f5wml5

MaxOverlapFraction (1)
By default, boxes that are slightly overlapping are returned:

https://wolfram.com/xid/0dquynhfmr2-3sqxx0

Specify a custom maximum overlap:

https://wolfram.com/xid/0dquynhfmr2-qa90ow

Return only non-overlapping boxes:

https://wolfram.com/xid/0dquynhfmr2-ojm1v3


https://wolfram.com/xid/0dquynhfmr2-ywps52

Method (3)
By default, FindImageText tries to pick the detection method more suitable to the image:

https://wolfram.com/xid/0dquynhfmr2-4892lu


https://wolfram.com/xid/0dquynhfmr2-nw1ec8

Using an unsuitable method might not give a good result:

https://wolfram.com/xid/0dquynhfmr2-g2kbhp

Use Method"NaturalScene" to detect text present in natural scenes:

https://wolfram.com/xid/0dquynhfmr2-puvzp3

Use Method"Document" for scanned documents:

https://wolfram.com/xid/0dquynhfmr2-40gc94

PaddingSize (1)
Use PaddingSizes to specify a padding for the detected word bounding boxes:

https://wolfram.com/xid/0dquynhfmr2-vvh18p

Use different padding sizes along the two bounding box axes:

https://wolfram.com/xid/0dquynhfmr2-vs99vo


https://wolfram.com/xid/0dquynhfmr2-fw7jok

Use a negative padding to return tighter bounding boxes:

https://wolfram.com/xid/0dquynhfmr2-e2spvy

Applications (1)Sample problems that can be solved with this function
It might be difficult to perform OCR on an image with a lot of non-textual content:

https://wolfram.com/xid/0dquynhfmr2-4tv61r

Use FindImageText first to preprocess the image:

https://wolfram.com/xid/0dquynhfmr2-4ahw87

Performing OCR on the crops yields better results:

https://wolfram.com/xid/0dquynhfmr2-kxqoxg

Properties & Relations (3)Properties of the function, and connections to other functions
FindImageText can detect text regardless of the orientation:

https://wolfram.com/xid/0dquynhfmr2-xbwzxm

FindImageText is used to detect text content within an image:

https://wolfram.com/xid/0dquynhfmr2-4cgib4

Use TextRecognize to perform OCR on the image content:

https://wolfram.com/xid/0dquynhfmr2-rbxrhh

Use FindImageText to detect the license plate in the image:

https://wolfram.com/xid/0dquynhfmr2-vkq3un

https://wolfram.com/xid/0dquynhfmr2-m6gy6w

Use TextRecognize to recognize the license plate and highlight it in the original image:

https://wolfram.com/xid/0dquynhfmr2-4o2pea


Possible Issues (4)Common pitfalls and unexpected behavior
The detection is not optimized for handwritten text:

https://wolfram.com/xid/0dquynhfmr2-p232ah

Depending on the text orientation, the detected bounding boxes may extend beyond the image borders:

https://wolfram.com/xid/0dquynhfmr2-gg4rqk

The detection might fail for images with multiple text orientations:

https://wolfram.com/xid/0dquynhfmr2-hn25zw

Text in certain orientations might not be detected:

https://wolfram.com/xid/0dquynhfmr2-o38je9

Wolfram Research (2020), FindImageText, Wolfram Language function, https://reference.wolfram.com/language/ref/FindImageText.html (updated 2025).
Text
Wolfram Research (2020), FindImageText, Wolfram Language function, https://reference.wolfram.com/language/ref/FindImageText.html (updated 2025).
Wolfram Research (2020), FindImageText, Wolfram Language function, https://reference.wolfram.com/language/ref/FindImageText.html (updated 2025).
CMS
Wolfram Language. 2020. "FindImageText." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2025. https://reference.wolfram.com/language/ref/FindImageText.html.
Wolfram Language. 2020. "FindImageText." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2025. https://reference.wolfram.com/language/ref/FindImageText.html.
APA
Wolfram Language. (2020). FindImageText. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/FindImageText.html
Wolfram Language. (2020). FindImageText. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/FindImageText.html
BibTeX
@misc{reference.wolfram_2025_findimagetext, author="Wolfram Research", title="{FindImageText}", year="2025", howpublished="\url{https://reference.wolfram.com/language/ref/FindImageText.html}", note=[Accessed: 08-July-2025
]}
BibLaTeX
@online{reference.wolfram_2025_findimagetext, organization={Wolfram Research}, title={FindImageText}, year={2025}, url={https://reference.wolfram.com/language/ref/FindImageText.html}, note=[Accessed: 08-July-2025
]}