Rice Quality Classification Using Artificial Neural Network

Simple item page
dc.contributor.authorNanayakkara, N.P.M.
dc.contributor.authorSubashini, L.D.C.S.
dc.date.accessioned2021-12-05T04:52:55Z
dc.date.available2021-12-05T04:52:55Z
dc.date.issued2010
dc.description.abstractThis project presents an improved method for classification of foreign bodies mixed rice grain image samples using a Neural Network Approach. Today competitive market rice contains many foreign bodies. To solvethis problem only visual inspection is performed. In manual system human inspectors look at the foreign bodies in the samples and evaluate the grades for rice. Neural Network system automatically determines the amount of foreign bodies present in rice grains. Thresholding technique is used to identify foreign bodies. Samba rice type was considered in this study. Feature extraction concept to collect information in images was used. Features are extracted using gray level co occurrence matrix method. The multilayer feed forward neural network is developed to classify rice grain images. Key words: Neural Network, Classificationen_US
dc.identifier.isbn9789550481002
dc.identifier.urihttp://www.erepo.lib.uwu.ac.lk/bitstream/handle/123456789/7902/120-2010-Rice%20Quality%20Classification%20Using%20Artificial%20Neural%20Network.pdf?sequence=1&isAllowed=y
dc.language.isoenen_US
dc.publisherUva Wellassa University of Sri Lankaen_US
dc.subjectNetworksen_US
dc.subjectInformation Systemen_US
dc.subjectAgricultureen_US
dc.titleRice Quality Classification Using Artificial Neural Networken_US
dc.title.alternativeResearch Symposium 2010en_US
dc.typeOtheren_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
120-2010-Rice Quality Classification Using Artificial Neural Network.pdf
Size:
506.92 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Research Symposium-2010