Convert DCM to HOCR
Turn DCM images into HOCR. Only the first frame is read, its contrast stretched from the darkest to the brightest pixel rather than the window stored in the file.
Converted in an isolated sandbox on our serversDeleted after 24 hours
Drop DCM files on the dialor turn it to pick what to do
Text from a medical image.The pixels are read with OCR and returned as one hOCR file.
What you get
One hOCR file. hOCR is OCR output as HTML with the position of every word on the page. The source is a DICOM image, the kind of medical image made by CT, MRI, X-ray and ultrasound.
What it leaves behind
Patient and study tags are left out. A DICOM file carries those tags alongside the pixels, and the hOCR file does not include them.
Setting the language
Set Language to the languages the text is in, so OCR knows which letters to expect. Naming the right language matters most for Korean, Japanese and Chinese. To name several, separate them with commas, such as en,ko.
DCM and HOCR.What each format is, and the options this conversion takes.
- 01 · language
Language
The languages the text is in, so OCR knows which letters to expect. Without it the text is read as English, so letters such as é, ß and ł come out wrong and other scripts, such as Cyrillic, Arabic, Thai, Korean or Chinese, are not read. Separate several with commas, such as fr,en.
The formats
DICOM
Medical images from CT, MRI, X-ray and ultrasound, with the patient and study tags alongside the pixels.
- Extensions
- .dcm .dicom
- MIME type
- application
/dicom - Kind
- Images
hOCR
OCR output as HTML with the position of every word on the page.
- Extensions
- .hocr
- MIME type
- text
/x -hocr - Kind
- Text and data
In your code.The same DCM to HOCR conversion through the API, for your app or your agent.
$ cv convert photo.dcm photo.hocr$ cv convert photo.dcm photo.hocrQuestions.What people ask about DCM to HOCR.
No. Patient and study tags are left out.
Yes. hOCR records the position of every word on the page.
It matters most for Korean, Japanese and Chinese, where naming the right language tells OCR which letters to expect.
One file.