jump to navigation

People Counting August 28, 2008

Posted by whaldsz in : research , add a comment

We are currently doing research in people counting.  The goal is to develop an algorithm that would solve the problem of occlusion. More info later….

Rice quality evaluation August 21, 2008

Posted by whaldsz in : research , add a comment

Prior to the previous post, I also finished a paper entitled “Automatic milled rice quality evaluation” that’s about to appear in one international conference proceedings.  The idea is to build a low-cost, efficient, and reliable alternative for the milled rice quality evaluation.  As you know, some rice quality standards require the grading factors or defectives in terms weight (grams) , making this problem a very challenging and interesting one!  Read on, some results are discussed in the succeeding paragraphs.

This is the block diagram of the milled rice quality evaluation system, comprised of 6 different stages.

automatic milled rice evaluation framework

(more…)

Weight estimation of milled rice August 20, 2008

Posted by whaldsz in : research , add a comment

This article presents a method for weight estimation and classification of milled rice kernels using supervised learning algorithm. Shape descriptors are used as geometric features for determining the grade factors such as headrice, broken kernel, and brewer. Color histogram is extracted from milled rice image to obtain 24 color features in RGB and Cielab color spaces. A support vector machines (SVM) is adopted for addressing the classification and regression problem in milled rice quality evaluation. We built a support vector regression (SVR) model for estimating rice kernel weight and support vector classifier (SVC) for rice defectives.

Results showed that in real data, the performance of SVR is better than linear regression (LR) with a mean square error (MSE), mean absolute error (MAE) and correlation coefficient of 0.078, 0.21 and 99.4%, respectively. For classification of rice defectives using SVC, the accuracy is 98.9% outperforming the general regression neural network (GRNN) model.

Software caliper for milled rice August 20, 2008

Posted by whaldsz in : projects , 1 comment so far

Few months ago, I completed a utility capable of measuring the percentage by weight of headrice, broken kernels and brewers for .  A screen shot is shown below.

software_caliper

The software is used for determining the grain size of a given milled rice sample.  Additional information about other milled rice grade factors are also provided as follows:

  1. Total number of kernels and weight of the milled rice sample
  2. Number of headrice and weight
  3. Number of broken kernels including its total weight
  4. Brewers

I will provide more information soon.  Keep posted!  And hey… feel free to comment.  Tell me what you think!