Normal view MARC view ISBD view

Tomato ripeness classification using artificial neural network / Salidy Chindamanee A/P Chamlong

By:

Salidy Chindamanee Chamlong

Material type: Text

TextPublication details: Kuantan, Pahang : UMP, 2016Description: xiv, 85 p. : ill. (some col.) ; 30 cm. + 1 CD-ROMISBN:

THE0001252(Local)

Subject(s):

Dissertation note: Project paper (Bachelor of Computer Science (Computer Systems & Networking) With Honours) -- Universiti Malaysia Pahang – 2016 Abstract: The classification of tomato into its maturity level can be determined by several parameters such as size, shape and color. It is important to classify it before send to markets, because to import to distant market, the tomato should be pack at colour break stage and for local market, it should be pack when it is fully red. The purpose of this research is to proposed neural network algorithm for classification and identifying the maturity level, by which this algorithm can be run in the software called “Matlab” by using the Matlab code. In this research, the parameter that will be used to identify the maturity of the tomato is external color. At start, some of the tomato image will be prepare, which include image for ripe tomato, halp ripe tomato and unripe tomato. Then, each of the image will be extract its rgb value using Matlab. After obtain the value, this value will be manually rescale. Next ANN algorithm will be train and test by perform some calculation to classify the tomato into stage. Some sample data sets is prepared used to train the network and backpropagation algorithm will be use. The trained data then will produce MSE and RMSE value to show the difference of the actual result with the expected one. From this study, the neural network model for tomato classification has achieved the best MSE value of 0.009972142. The colour of tomato is believed to be the major method in determining its maturity.

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings ( 2 )
Title notes ( 4 )

Holdings
Item type	Current library	Call number	Copy number	Status	Date due	Barcode
Final Year Report	UMPLIB PEKAN	FSKKP .S25 2016 r Bc. (Browse shelf(Opens below))	1	Not for loan		0000117576
Final Year Report	UMPLIB PEKAN	CD 10691 \| FSKKP .S25 2016 r Bc. (Browse shelf(Opens below))	1	Not for loan		0000117577

Faculty of Computer Systems and Software Engineering

Project paper (Bachelor of Computer Science (Computer Systems & Networking) With Honours) -- Universiti Malaysia Pahang – 2016

Bibliography : p. 55-56

The classification of tomato into its maturity level can be determined by several parameters such as size, shape and color. It is important to classify it before send to markets, because to import to distant market, the tomato should be pack at colour break stage and for local market, it should be pack when it is fully red. The purpose of this research is to proposed neural network algorithm for classification and identifying the maturity level, by which this algorithm can be run in the software called “Matlab” by using the Matlab code. In this research, the parameter that will be used to identify the maturity of the tomato is external color. At start, some of the tomato image will be prepare, which include image for ripe tomato, halp ripe tomato and unripe tomato. Then, each of the image will be extract its rgb value using Matlab. After obtain the value, this value will be manually rescale. Next ANN algorithm will be train and test by perform some calculation to classify the tomato into stage. Some sample data sets is prepared used to train the network and backpropagation algorithm will be use. The trained data then will produce MSE and RMSE value to show the difference of the actual result with the expected one. From this study, the neural network model for tomato classification has achieved the best MSE value of 0.009972142. The colour of tomato is believed to be the major method in determining its maturity.