Weight estimation of sunshine mango using 3-dimensional machine vision technique
Access is limited to UniMAP community.
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Learning Object |
| Language: | English |
| Published: |
Universiti Malaysia Perlis (UniMAP)
2021
|
| Subjects: | |
| Online Access: | http://dspace.unimap.edu.my:80/xmlui/handle/123456789/73478 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Malaysia Perlis |
| Language: | English |
| id |
my.unimap-73478 |
|---|---|
| record_format |
dspace |
| spelling |
my.unimap-734782022-01-18T07:37:35Z Weight estimation of sunshine mango using 3-dimensional machine vision technique Nur Hafizah, Mohamad Idris Mohd Firdaus, Ibrahim School of Bioprocess Engineering Sunshine mango Grading Machine vision Mass estimation Access is limited to UniMAP community. This research is aim to estimate the weight of sunshine mango using 3-Dimensional machine vision technique. The size of the mango is depending weight which is can affect the consumer buying preferences Current method of grading sunshine mango is done manually and time consuming. An image processing based technique was developed to measure volume and mass of sunshine mango by using 3-Dimensional technique of machine vision. A workstation for capturing image samples were design and constructed to obtain two viewpoints which top view and side view in a single acquisition. In this study, 50 sunshine mango fruit were measured with respect to their length, maximum width and maximum thickness, to within an accuracy of 0.01mm and their weight was determined using weighing scale within an accuracy of 5 g. The actual sunshine mango volumes determined by water displacement method and measured volume determined by disk method using image processing technique. Then, the data were analyzed using paired samples t- test. The results of paired samples test indicated the difference between the volumes determined by disk method and water displacement and has been found to be statistically significant (P < 0.05). The estimated volume by disk method then used to estimate the mass of the mango. The results show that the R2 value between the estimated volume and actual mass was high correlation which R2 is equal to 0.943. Therefore, the result show that algorithm obtained from the prediction model was fit to estimate the mass. Overall result for weight grading using our proposed method yields 94% accuracy. 2021 2022-01-18T07:37:35Z 2022-01-18T07:37:35Z 2017-06 Learning Object http://dspace.unimap.edu.my:80/xmlui/handle/123456789/73478 en Universiti Malaysia Perlis (UniMAP) |
| institution |
Universiti Malaysia Perlis |
| building |
UniMAP Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Malaysia Perlis |
| content_source |
UniMAP Library Digital Repository |
| url_provider |
http://dspace.unimap.edu.my/ |
| language |
English |
| topic |
Sunshine mango Grading Machine vision Mass estimation |
| spellingShingle |
Sunshine mango Grading Machine vision Mass estimation Nur Hafizah, Mohamad Idris Weight estimation of sunshine mango using 3-dimensional machine vision technique |
| description |
Access is limited to UniMAP community. |
| author2 |
Mohd Firdaus, Ibrahim |
| author_facet |
Mohd Firdaus, Ibrahim Nur Hafizah, Mohamad Idris |
| format |
Learning Object |
| author |
Nur Hafizah, Mohamad Idris |
| author_sort |
Nur Hafizah, Mohamad Idris |
| title |
Weight estimation of sunshine mango using 3-dimensional machine vision technique |
| title_short |
Weight estimation of sunshine mango using 3-dimensional machine vision technique |
| title_full |
Weight estimation of sunshine mango using 3-dimensional machine vision technique |
| title_fullStr |
Weight estimation of sunshine mango using 3-dimensional machine vision technique |
| title_full_unstemmed |
Weight estimation of sunshine mango using 3-dimensional machine vision technique |
| title_sort |
weight estimation of sunshine mango using 3-dimensional machine vision technique |
| publisher |
Universiti Malaysia Perlis (UniMAP) |
| publishDate |
2021 |
| url |
http://dspace.unimap.edu.my:80/xmlui/handle/123456789/73478 |
| _version_ |
1729704625495343104 |