Open AccessJournal Article
Average Grain Size Determination using Mathematical Morphology and Texture Analysis
Hannu Rautio,Olli Silven +1 more
Reads0
Chats0
TLDR
It is concluded that mathematical morphology with texture analysis can be used to determine average grain size of material, which is computationally easy and fast although less accurate to smaller grain classes.Abstract:
Many industrial processes need information about material grain size. In this work we examined rolled chrome concentrate to determine the average grain size. Test material was sieved into 15 fractions, from 37 pm to 500 pm. The analysis method can be divided in three sections: preprocessing, feature extraction and classification. Mathematical morphology was used as preprocessing method, with gray-scale erosion and opening as operations. Feature extraction was implemented with first and second-order statistics. Finally, classification was performed with k-NN and minimum distance classifiers using leave-out method. We conclude that mathematical morphology with texture analysis can be used to determine average grain size of material. It is computationally easy and fast although less accurate to smaller grain classes. This is due to imaging errors and noise but also the fact that the ratio grain size versus size of structuring element must be large enough. Both opening and erosion operations can be used. Erosion is two times faster than opening to perform. Also the number of preprocessing operations can be, for example, reduced to three without the classification result will have a remarkable change.read more
Citations
More filters
Proceedings ArticleDOI
Analysis of rice granules using image processing and neural network
TL;DR: This work has been done to identify the relevant quality category for a given rice sample based on its parameters and the performance of image processing reduced the time of operation and improved the crop recognition greatly.
Proceedings ArticleDOI
A grain quality classification system
TL;DR: A back propagation neural network with two hidden layers has been developed for the quality classification of milled rice by providing a better approach for identification of rice quality by using neural network and image processing concepts.
A visual training based approach to surface inspection
TL;DR: A visual based training method that avoids the problems related to traditional training methods by combining a classifier and a user interface and provides an intuitive way to directly set and tune the class boundaries of high-dimensional data is presented.
Journal ArticleDOI
Analysis of Rice Granules using Image Processing and Neural Network Pattern Recognition Tool
Journal ArticleDOI
An intelligent rice quality classifier
TL;DR: This research, with the aim of implementing a hand-held device for quality testing of rice, focuses on producing a classification system based on neural network and image processing concepts, which shows accuracy in between 94% to 68% for the four grades.
References
More filters
Journal ArticleDOI
Textural Features for Image Classification
TL;DR: These results indicate that the easily computable textural features based on gray-tone spatial dependancies probably have a general applicability for a wide variety of image-classification applications.
Journal ArticleDOI
The evolution of life histories
TL;DR: In this article, age and size at maturity at maturity number and size of offspring Reproductive lifespan and ageing are discussed. But the authors focus on the effects of age and stage structure on fertility.
Journal ArticleDOI
Power‐law relationships between the dependence of ultrasonic attenuation on wavelength and the grain size distribution
TL;DR: In this paper, a simple relationship between the power law that describes the grain size distribution and the power-law dependence of attenuation on wavelength was established, and two types of measurements were presented to verify the theoretical development.
Proceedings ArticleDOI
Mathematical morphology toolbox for the KHOROS system
TL;DR: The Mathematical Morphology Toolbox for Image Processing and Visualization (KHOROS) as mentioned in this paper is an open and general environment for image processing and visualization that has become very popular.