| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font
First page > Show document

Show document Help

Title:SORTIRANJE PRIDELKA S POMOČJO BARVNE SEGMENTACIJE
Authors:ID Korošak, David (Author)
ID Rakun, Jurij (Mentor) More about this mentor... New window
Files:.pdf VS_Korosak_David_2015.pdf (1,83 MB)
MD5: F27577E8F05509473977F0C372E7183A
 
Language:Slovenian
Work type:Bachelor thesis/paper
Organization:FKBV - Faculty of Agriculture and Life Sciences
Abstract:Sortiranje pridelkov v kmetijstvu je zelo pomembno, saj določamo cene pridelkov in njihovo uporabnost glede na količino in kvaliteto. Zaradi naštetih razlogov smo v okviru diplomskega dela načrtovali, naredili in testirali enostavno sortirno linijo, ki jo je krmilil osebni računalnik. Naloga linije je, da sama loči predmete in jih klasificira v eno izmed dveh skupin; poznan oz. dober in nepoznan oz. slab pridelek. Klasificirala jih je po principu barvnega ujemanja (»Colour matching«). Prvi preizkus linije je potekal med žogicama zelene in oranžne barve. Natančnost linije pri tem preizkusu je dosegla 97 %. Nato so sledili štirje preizkusi z jabolki. V prvem preizkusu linije med sortama 'Fuji' in 'Zlati delišes' je bila natančnost v povprečju 90 % ± 10 %. V drugem preizkusu med sortama 'Fuji' in 'Jonagold' je bila natančnost v povprečju 78,5 % ± 1,5 %. V tretjem preizkusu sta bili v liniji sorti 'Jonagold' in 'Zlati delišes'. Povprečna natančnost v tem preizkusu je znašala 97 % ± 3%. Četrti preizkus potekal je med sortama 'Fuji' in 'Zlati delišes' pri zmanjšani svetlobi. Povprečna natančnost v zadnjem primeru je znašala 75,5 % ± 24,5 %.
Keywords:sortirni stroj, barvni prostori, barvna segmentacija, pulzno širinska modulacija
Place of publishing:Maribor
Year of publishing:2015
PID:20.500.12556/DKUM-47251 New window
NUK URN:URN:SI:UM:DK:HUIG4GRJ
Publication date in DKUM:30.01.2015
Views:3202
Downloads:98
Metadata:XML DC-XML DC-RDF
Categories:FKBV
:
KOROŠAK, David, 2015, SORTIRANJE PRIDELKA S POMOČJO BARVNE SEGMENTACIJE [online]. Bachelor’s thesis. Maribor. [Accessed 15 April 2025]. Retrieved from: https://dk.um.si/IzpisGradiva.php?lang=eng&id=47251
Copy citation
  
Average score:
0.5
1
1.5
2
2.5
3
3.5
4
4.5
5
(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share


Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Secondary language

Language:English
Title:COLOUR SEGMENTATION BASED APPROACH TO CROP SORTING
Abstract:The step of harvest sorting plays an important role in food production where its quantity as well as quality has to be determined in order to set the optimal price tag. This was the motivation to plan, build and test a simple sorting line controlled by a personal computer. Its job is to sort the harvest in one of two groups (good, known and bad, unknown objects) based on colour segmentation step. The initial test included two artificial objects; one green and one orange ball. The sorting lined achieved promising results reaching up to 97 % accuracy. Four additional tests followed with 'Fuji', 'Jonagold' and 'Golden delicious' apple cultivar. The result of 'Fuji' – 'Golden delicious' test achieved 90 % ± 10 % accuracy, the 'Fuji' – 'Jonagold' test 78.5 % ± 1.5 % accuracy and 'Jonagold' – 'Golden delicious' 97 % ± 3% accuracy. The final test involved 'Fuji' and 'Golden delicious' with poorly illuminated scene, reaching nevertheless a 75.5 % ± 24.5 % accuracy.
Keywords:sorting line, colour space, colour segmentation, pulse – width modulation


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica