This browser is no longer supported.
Upgrade to Microsoft Edge to take advantage of the latest features, security updates, and technical support.
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(128, 33%, 22%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EZ2%3C/text%3E%3C/svg%3E)
The Computer Vision Form Recognizer read (OCR) model response contains bounding boxes for words, but no character/glyph positions. Is there any way to get individual character positions?
Zhivko I noticed that your recent experience was not helpful, and to better improve our processes and learn from our customers, I'm eager to know what could have been done better.
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(249.60000000000002, 5%, 34%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ERO%3C/text%3E%3C/svg%3E)
I'm sure that getting the character coordinates would be beneficial for many customers (including my company).
We're struggling with words that are incorrectly joined by the Computer Vision API. Getting the character coordinates would allow us to split those words.
Zhivko The OCR and Read API can provide only the co-ordinates of each word from the lines that include all extracted words with their coordinates and confidence scores. Currently, there is no setting to get the individual character positions in the response.
-Please kindly accept the answer if the answer was helpful to support the community, thanks.
@Zhivko I understand that the current limitation of the service did not help in this case and might have not answered your question. To add to my response above, there is a feedback portal for Azure services where you could log this requirement for the product team to review and assess the requirements as part of future releases. Please log your request here. I hope this helps!!