dc.contributor.author |
Attygalla, S. S. |
|
dc.contributor.author |
Wanniarachchi, W. K. L L. . |
|
dc.contributor.author |
Mendis, M. |
|
dc.date.accessioned |
2018-12-03T07:17:50Z |
|
dc.date.available |
2018-12-03T07:17:50Z |
|
dc.date.issued |
2017 |
|
dc.identifier.citation |
Attygalla, S. S., Wanniarachchi, W. K. L L., Mendis, M., (2017). "Develop an Electronic Eye to Improve efficiency and Accuracy of Cuttile Meacuring Function based on Image Processing Techniques ", Proceedings of the 3'd Symposium organized by the University of Sri Jayewardenepura |
en_US |
dc.identifier.issn |
2550-2638 |
|
dc.identifier.uri |
http://dr.lib.sjp.ac.lk/handle/123456789/7723 |
|
dc.description.abstract |
attached |
en_US |
dc.description.abstract |
Lanka Walltiles produces cut tile for export market at the 3rd firing section, where they use
manual measuring device with linear encoder for measuring the length and width of a cut
tile. Currently, three workers work for measuring and recoding the dimensions of a cut tile
and averagely 20 seconds take for a single cycle. As this process rather inefficient and less
accurate, Lanka Walltiles desires to automate these processes while improving the
efficiency and accuracy.
This research work aims to improve efficiency and accuracy of cut tile measurement
function by developing an electronic eye measuring device. The proposed automated
system consists three main parts. First, conveyer belt that carries the cut tiles one after the
other. The color of the belt is black and the color of tiles may vary, but it can easily separate
from the background color. Second part is the camera unit. The cameta unit directly
connects to a computer which is the third main part of the automated system. To maintain
the same light condition throughout the process, two 10W LED external light system is
used. The developed algorithm will capture the image of the cut tile when its reach to the
center of the frame. Then image processing techniques applied for calculating the length
and the width of the cut tile. The captured RGB image first converts to a hinary using the
pre-defined threshold value. Then the angle correction has to implement as the tiles reach
to the belt in different angles. Here we used radon transformation to locate the horizontal
and vertical lines and angle correction was done accordingly. Row and column sum were
used to separate the tile area from the background of the noise reduced image. Then, the
average value for the length and width of the cut tile calculate as number of pixels. Then
the pixel value convefts to length in mm and datawill be saved in a text file. If the cut tile
dimension is not in the given range the system automatically warn to the worker. When
using this system only one worker is needed to be employed. Another result obtained was
0.001mm resolutions and measurement time is 2.5 seconds per one tile.As the final
conclusion it can be stated that efficiency and accuracy has developed after using this
system. |
|
dc.language.iso |
en |
en_US |
dc.subject |
Cut Tile |
en_US |
dc.subject |
Image Processing |
en_US |
dc.subject |
Electrtonic Eye |
en_US |
dc.subject |
Linear Encoder |
en_US |
dc.subject |
Walltiles |
en_US |
dc.title |
Develop an Electronic Eye to Improve efficiency and Accuracy of Cuttile Meacuring Function based on Image Processing Techniques |
en_US |
dc.type |
Article |
en_US |