Got Questions? Get Answers.
Discover MakerZone

MATLAB and Simulink resources for Arduino, LEGO, and Raspberry Pi

Learn more

Discover what MATLAB® can do for your career.

Opportunities for recent engineering grads.

Apply Today

Thread Subject:
re-labeling to catch blobs that were previously missed

Subject: re-labeling to catch blobs that were previously missed

From: Nicolas

Date: 2 May, 2011 00:10:04

Message: 1 of 2

Hi all,

I've been using ImageAnalyst's SimpleColorDetectionByHue, http://www.mathworks.com/matlabcentral/fileexchange/28512-simple-color-detection-by-hue (with my own tweaks) to identify blobs in an image. I have it working quite well, but when I visually inspect the image, I personally identify more blobs than the algorithm does.

For example: http://s92.photobucket.com/albums/l25/Affeyistruth/?action=view¤t=test3.png

The algorithm finds 4 blobs, marked here by dark asterisks (sorry, a little hard to see). However, I personally consider the image to have 6 blobs.

My question is: after labeling/identifying blobs, is there a way to perform a second pass in order to catch extra blobs that were 'missed' the first time?

Subject: re-labeling to catch blobs that were previously missed

From: ImageAnalyst

Date: 2 May, 2011 04:11:14

Message: 2 of 2

No. You just get your binary image set up right the first time. No
need to do a relabeling. You may need to adjust your thresholds, or
split apart blobs that are perhaps connected by a thin path (for
example by using watershed or imopen). Once you have the proper
binary image, then you label.

Tags for this Thread

What are tags?

A tag is like a keyword or category label associated with each thread. Tags make it easier for you to find threads of interest.

Anyone can tag a thread. Tags are public and visible to everyone.

Contact us