Public Lab Research note


Opencv.js for blob detection in microscopic images

by aashnaaashna | June 26, 2019 21:39 | 159 views | 2 comments | #19880 | 159 views | 2 comments | #19880 26 Jun 21:39

Read more: i.publiclab.org/n/19880


This is a procedural guide for using Opencv.js for blob detection in microscopic images. Opencv.js provides javascript bindings for opencv, bringing the powerful image processing operations to javascripts. It can be embedded using a script tag and it is ready for use!image description


For the demonstration a simple image is taken and the various stages of processing are shown:

image description

Step 1: Threshold the image for a simple segmentation of your image to identify background and foreground regions. For our sample image it results as :

image description

Step 2: We are now certain of the background and the foreground but the region we are uncertain about is the boundary region. Now for this we use the processing functions - erode and dilate. Erosion removes the boundary pixels, so we are certain of the pixels that are inside the object. Dilation increases the region's boundary to the background.Now we use distance transformation for gray level intensities of points inside region with respect to the boundary.

image description

Step 3: Finally mark the boundary regions and it is done !!

image description


1 Comments

This is cool! You're working on an Image Sequencer module for this, right? This will be so cool to be able to use in the simple interface at https://sequencer.publiclab.org -- I'm excited to see that running! Thanks @aashnaaashna!

Is this a question? Click here to post it to the Questions page.

Reply to this comment...


Login to comment.

Public Lab is open for anyone and will always be free. By signing up you'll join a diverse group of community researchers and tap into a lot of grassroots expertise.

Sign up