- Property Tax Assessment System (PTAS?) January 27, 2012
- Business Permit and Licensing System January 22, 2012
- Insect Identification December 18, 2011
- Legislative Information Management and Tracking System September 6, 2011
- People Counting - Patent finally approved! July 20, 2011
Posts Tagged ‘classification’
September 1, 2008 | 
Author 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:
- Chalky
- Sound/Good
- Damaged
- Red
- Paddy
- Discolored
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:
- Acquire the image. This could be accomplished by various methods. You can use scanner, digital camera, or video camera.
- 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.
- Extract features (Morphological & Color), one set for training and another set for testing.
- You may need to scale your data, especially if the value of some features are a lot larger than the other.
- 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.
- If you are satisfied with the prediction accuracy of your model, then apply it to your test data, or real data.
- Build your application.
Simple, eh?
Posted in projects, technology | 
Tags: classification, how-to svm, LibSVM, support vectors, svc, SVM, svr | 
3 Comments »
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.
Posted in research | Tags: classification, grain, GRNN, Milled Rice, milled rice classification, milled rice weight estimation, SVM, Weight estimation | No Comments »