jump to navigation

Caliper Software for Milled-Rice – Counts the number of grains, headrice and broken kernels September 14, 2008

Posted by whaldsz in : projects, software, technology , 1 comment so far

Milled rice software caliper This is an application for counting milled rice grains, determining the count of headrice, broken, and brewers. Using these grade factors, the caliper software (as I call it) is able to estimate the total weight in terms of percentage. Weight estimation of rice grain is performed using linear regression and support vector machines (SVM). It uses AForge library from AForge.NET for various image processing task.

I did this software for Bureau of Post-harvest Research Extension (BPRE) and indirectly, to National Food Authority (NFA) for the purpose of quickly determining the grain size of milled rice.

The demo and initial version of the caliper software is available for download here:

To use the software, simply install the application, then open the sample image included in the installation (“bigas.bmp”), then that’s it!  You can try it for other similar problems, like corn, barley, etc.  Please give me feedback if problems arises.  For any questions, you may email me at {vlad_crasher at yahoo point com}.

UPDATE: Yesterday (September 15, 2008), they told me that the test was successful!  The classification result did matched with the manual methods performed by human inspector.

Bookmark and Share

New update for Google Chrome! September 6, 2008

Posted by whaldsz in : technology , add a comment

Update your Google Chrome now… old build is 0.2.149.27, the new build 0.2.149.29 is available!  Existing installation can be updated by clicking the Customize and control Google Chrome ~~> About Google Chrome.

chrome_newbuild

Also, if you are unaware of the new Google Chrome’s updated terms of service, read Mike Yang’s post on Google blog.

Bookmark and Share

Using convex hull to define the initial boundary of active contour model September 5, 2008

Posted by whaldsz in : research , add a comment

Few hour ago, I was reading some papers to increase my understanding on (SVM).  I came across the term and I was reminded of challenge I had when I was working on image segmentation of medium to long milled rice grains for quality evaluation. Although there are some published papers that deal with this problem (e.g. “” and “Separation and identification of touching kernels and dockage components in digital images“), they were able to solve only those touching grains with circular-like objects.

So I thought, using convex hull to define the initial boundary of an active contour could be an interesting idea.  But it looks like somebody has already done it – see An unsupervised GVF snake approach for white blood cell segmentation based on nucleus.

Bookmark and Share

Google Chrome: The new internet browser September 3, 2008

Posted by whaldsz in : news, technology , 1 comment so far

I installed the new internet browser from Google – ! Try it for yourselves and you’ll be surprised by its simplicity and speed.  The best feature that I like the most is the incognito mode – websites you visit does not show up in your web history. Very useful for internet users who value their privacy highly.

Google claims that Chrome is more stable, faster (especially for web applications), secure, clean/efficient UI, and open source. It is a new kind of browser that runs tab windows in separate separate processes much like a windows operating system runs your applications.

For more information, go to their site at http://www.google.com/chrome/ and read the full features with corresponding video demonstration.  A that explains Google Chrome in easy-to-understand  english is also available. Highly recommended!

Bookmark and Share

How to use SVM for classification September 1, 2008

Posted by whaldsz in : projects, technology , 2comments

Support Vector Machine or simply SVM is a machine learning algorithm for data regression and classification.  I have adopted it for use in my project in milled rice kernel classification according to the following categories:

My goal is to share how to build a model, apply this classifier to your test data to determine its accuracy, and finally, implement the model as an application.  The library called LibSVM has made my work a lot simpler.  Why reinvent the wheel?  Here’s how you do it:

  1. Acquire the image.  This could be accomplished by various methods.  You can use scanner, digital camera, or video camera.
  2. Pre-process the captured image.  The goal is to ensure that unimportant objects are discarded, and enhance your region of interests to prevent lost of features.
  3. Extract features (Morphological & Color), one set for training and another set for testing.
  4. You may need to scale your data, especially if the value of some features are a lot  larger than the other.
  5. Train and build the SVM model.  You may need to find the optimal parameters (the penalty, C and kernel parameter, gamma).  This may take a while depending on the type of SVM and kernel you choose.
  6. If you are satisfied with the prediction accuracy of your model, then apply it to your test data, or real data.
  7. Build your application.

Simple, eh?

Technorati Tags: ,,,,
Bookmark and Share