Dursun, Ö. O., Toraman, S., Er, Y., Oksuztepe, E. (2023). Apricot Position Determination Using Deep Learning for Apricot Stone Extraction Machine. , 25(3), 595-607. doi: 10.22034/jast.25.3.595
Ö. O. Dursun; S. Toraman; Y. Er; E. Oksuztepe. "Apricot Position Determination Using Deep Learning for Apricot Stone Extraction Machine". , 25, 3, 2023, 595-607. doi: 10.22034/jast.25.3.595
Dursun, Ö. O., Toraman, S., Er, Y., Oksuztepe, E. (2023). 'Apricot Position Determination Using Deep Learning for Apricot Stone Extraction Machine', , 25(3), pp. 595-607. doi: 10.22034/jast.25.3.595
Dursun, Ö. O., Toraman, S., Er, Y., Oksuztepe, E. Apricot Position Determination Using Deep Learning for Apricot Stone Extraction Machine. , 2023; 25(3): 595-607. doi: 10.22034/jast.25.3.595

Apricot Position Determination Using Deep Learning for Apricot Stone Extraction Machine

Journal of Agricultural Science and Technology
Article 7, Volume 25, Issue 3, 2023, Pages 595-607    PDF (1.11 M)
Document Type: Original Research
DOI: 10.22034/jast.25.3.595
Authors
Ö. O. Dursun* 1; S. Toraman2; Y. Er3; E. Oksuztepe1
1Avionics Department, Civil Aviation High School, Firat University, 23119 Elazig, Turkey.
2Air Traffic Control Department, Civil Aviation High School, Firat University, 23119 Elazig, Turkey.
3Airframes and Powerplants Department, Civil Aviation High School, Firat University, 23119 Elazig, Turkey.
Abstract
Despite the developing technology, extraction of Sulfured Dried Apricot (Prunus armeniaca) (SDA) stones is still done manually and thus requires a significant amount of labor and time and also causes serious problems in terms of hygiene. According to International Food Standards (CXS 130-1981) and Turkish Standard 485, the SDA stones must be extracted from the peduncle side of the apricot. Therefore, the correct position of the apricot peduncle and style side must be determined. In this study, a deep learning architecture was improved for the first time to determine the position of SDA stones as a component of the agricultural machine developed to extract SDA stones. In this study, a new Capsule Network architecture was used. With the original capsule network, SDA images were classified with 86.23% accuracy, while it increased to 94.47%with the improved capsule network. Also, the processing time of the developed network architecture was about twice as fast as the original. The result clearly demonstrates that the SDA stone positions are easily determined. Therefore, the designed agricultural machine can extract the SDA stones hygienically and rapidly, without any need for human power.
Keywords
Capsule networks; Deep features; Prunus armeniaca; Sulfured dried apricots
References
Statistics
Article View: 167
PDF Download: 114
Statistics
Number of Journals45
Number of Issues2,160
Number of Articles24,584
Article View20,263,966
PDF Download16,213,092