Git Product home page Git Product logo

Comments (4)

spreka avatar spreka commented on September 17, 2024

@swathi24prabhu Thank you for reaching out. The exported masks are 16-bit files for multi-labelled export option (this is the default for instance annotation) with increasing intensity values by objects. Default image viewers might not be able to visualize the labels. I would recommend either ImageJ/Fiji (any OS, you can set the intensity range with the keys ctrl+shift+c then adjust maximum if needed) or Irfanview (shift+u) if you are on Windows. If your mask is still completely black, can you check your annotation file ([filename]_ROIs.zip) by loading it in AnnotatorJ to see if you have saved any ROIs in the ROI Manager?

from annotatorj.

swathi24prabhu avatar swathi24prabhu commented on September 17, 2024

Thanks a lot. I have increased the intensity range and problem solved.

from annotatorj.

swathi24prabhu avatar swathi24prabhu commented on September 17, 2024

from annotatorj.

spreka avatar spreka commented on September 17, 2024

@swathi24prabhu

  1. Is it not possible to store with increased intensity images by default?

The 16-bit format ensures that correct intensity values correspond to individual objects when there are more than 255 objects on the image (0: background, 1-255: object labels is the maximum that can be fit to an 8-bit mask). This format is suitable to train most types of deep learning models.
If this does not work for your application or preference, you can change it in Annotator_ExportFrameNew.java:
replace ShortProcessor with ByteProcessor and change the max value from 65535 to 255 in setMinAndMax below it. Other export formats can be changed similarly.
Alternatively, you can export to overlay which will save the ROI outlines to the original image as an overlay for visual inspection - note that this cannot be used for training.

  1. Is it possible to store annotations?

Annotations are saved to the [filename]_ROIs.zip files (if you use instance annotation) according to ImageJ's ROI structure and can be loaded in the ROI Manager. Does this answer your question?

  1. Is it required to have the image in tif format? because my next button not working

Masks are saved to .tiff files for optimal resolution, input images can be in any commonly used image format (png, bmp, jpg, jpeg, tif, tiff). What do you mean your next button doesn't work? If you open the mask image file with the Open button in AnnotatorJ, it opens like any other image file, and the other image files found in the same folder can be stepped through with the "<" and ">" buttons. If no further image files exist in the same folder, these buttons are inactive - when the selected image is the first in the list, the previous button is inactive, or when it is the last, the next button is inactive. Can you make sure you have further image files in the same folder?

from annotatorj.

Related Issues (4)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.