Get correct image orientation by Google Cloud Vision api (TEXT_DETECTION)
I tried Google Cloud Vision api (TEXT_DETECTION) on 90 degrees rotated image. It still can return recognized text correctly. (see image below)
That means the engine can recognize text even the image is 90, 180, 270 degrees rotated.
However the response result doesn't include information of correct image orientation. (document: EntityAnnotation)
Is there anyway to not only get recognized text but also get the orientation?
Could Google support it similar to (FaceAnnotation: getRollAngle)
As described in the Public Issue Tracker, our engineering team is now aware of this feature request, and there is currently no ETA for its implementation.
Note, orientation information may already be available in your image's metadata. An example of how to extract the metadata can be seen in this Third-party library.
A broad workaround would be to check the returned "boundingPoly" "vertices" for the returned "textAnnotations". By calculating the width and height of each detected word's rectangle, you can figure out if an image is not right-side-up if the rectangle 'height' > 'width' (aka the image is sideways).
- Japanese Vertical text recognition with VNRecognizeTextRequest not working
- How to grab subtitle from screenshot with PHP?
- How to find Base-line of Curved Text?
- OCR and pytesseract detecting numbers in an image
- Offline Image To Text Recognition (OCR) in android
- emgucv: pan card improper skew detection in C#
- OCR - Azure Document Intelligence to recreate document digitally
- Tesseract does not recognize single characters
- Is it possible to check orientation of an image before passing it through pytesseract ocr module
- Extracting Text from led panel
- Text detection & Segmentation using Python OpenCV
- How to print the table and lines in their reading order from a document analyzed by AWS Textract
- Improving Text Recognition in the Presence of Overlay Lines
- Highlighting specific text in an image using python
- How to read seven segment display and logos in images using Python?
- Crop the title (text) on the image to a certain border (by color)
- Definite OCR Quality
- How do I link a Kotlin and Python project?
- Pytesseract doesnt recognize plate correctly
- Wrong numbers retrieved in pytesseract
- Getting the bounding box of the recognized words using python-tesseract
- How to OCR a text with white colour characters on a blue background from a cropped image?
- Using Tesseract not able to identify single character from the image
- OCR with the Tesseract interface
- Are we able to integrate OCR using bus64 or image link with Microsoft Power Automate?
- Tesseract training for a new font
- Get correct image orientation by Google Cloud Vision api (TEXT_DETECTION)
- Extracting Word-Level BoundingBoxes with VNRecognizeTextRequest's .accurate in Vision Framework - SwiftUI
- Need good OCR for printed source code listing, any ideas?
- Selective Thresholding in OpenCV