Application of Digital Image Processing to Predict the Diameter of Chrysanthemum Flowers Ready to Harvest
Abstract
Since 1940, chrysanthemum was developed commercially. Potentially, the cut chrysanthemum commodity still has problems in its development. Chrysanthemum flower production scheduling is needed to increase the quantity, quality and continuity of chrysanthemum production according to market demand. This happens because usually managers or entrepreneurs only harvest flowers en masse without seeing some flowers that should not be suitable for harvesting are also cut off. Therefore, it is detrimental to the manager itself and reduces the quality of the chrysanthemum flower products that are sold. The solution to the existing problem is that there is a need to observe flowers by applying precise agricultural technology according to the times to ensure the bloom time. By knowing this phase, the flower harvest period can be predicted correctly so that the fulfillment of market demand can be met appropriately. Observations in this study use digital image processing with the threshold method, which is then used as a basis for predicting the diameter of chrysanthemum flowers ready for harvest, hopefully this will help farmers or chrysanthemum managers to optimize their harvest. The results showed that the data image observation as a whole experienced the percentage of missing data or errors with possible causal factors due to the density of storage traffic, the effect of lighting, humidity and air temperature. In addition, the use of "image processing" to find the diameter of chrysanthemum flowers ready for harvest has succeeded in approaching the actual condition, although it has not been tested in other varieties.
References
Firgiyanto R, Harjoso T and Tini E W 2018 J. Agrovigor 11 88 – 95
Kasutjianingati, Firgiyanto R and Warisu A E. 2020. IOP Conf. Series: Earth and Environmental Science 411 012005doi:10.1088/1755-1315/411/1/012005
Rosyidah H A, Kristanto B A and Slamet W 2019 J. Agromedia 37 25-31
Indah T, Dewanti P and Wijaya K A 2015 J. Berkala Ilmiah Pertanian Universitas Jember 91-4
Febrianto R A and Islami T 2019 J. Produksi Tanaman. 7 1427–1434
Pin D D, Yang Y T and Gow C Y 1999 LWT-Food Science and Technology 32 269-277
Zhu S, Yang Y, Yu H, Ying Y and Zou G 2005 J. of Ethnopharmacology 96 151-158
Yang L, Aobulikasimu N, Ping C, Jin H W and Hong L 2017 Molecules Article 22
Ohmiya A 2018 Breed. Sci 68 17075
Zhao D and Tao J 2015 Front. Plant Sci 6 261.
Ramadijanti N 2006 Content Based Image Retrieval Berdasarkan Ciri Tekstur Menggunakan Wavelet. Paper Aplikasi Teknologi Informasi (Surabaya Indonesia: Politeknik Elektronika Negeri Surabaya)
Badan Pusat Statistika [BPS] 2018 Statistik Tanaman Hias Indonesia. Badan Pusat Statistika (Jakarta Indonesia: Badan Pusat Statistika)
Anwar S, Setyohadi D P S , Utami M M D, Damanhuri and Hariono B 2018 J of Physics: Conference Series 953 012123. doi:10.1088/1742-6596
Riskiawan H Y, Rizaldi T, Setyohadi D P S and Leksono T 2017 4th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI). doi:10.1109/eecsi.2017.8239080
Cahyono F B 1999 Chrysanthemum (Jakarta: Elex Media Komputindo)
Haryani (1995) dalam Rukmana dan Mulyana (1997)
Widiawan B, Kautsar S, Purnomo F and Etikasari B 2017 J. Ilmiah Pendidikan Teknik Elektro 2 143-148. Doi http://dx.doi.org/10.30870/volt.v2i2.2047
Yu S, Yuan L, Guan W and Haiyan Z 2017 Comput Intell Neurosci 7361042.
Pawara P, Okafor E, Surinta O, Schomaker L and Wiering M 2017 In: Proceedings of the 6th international conference on pattern recognition applications and methods (ICPRAM 2017) p. 479–86
Andradesanchez P 2014 Funct Plant Biol. 41 68–79
Liu Z, Wang J, Tian Y and Dai S. 2019 Plant Methods 15 146-157 https://doi.org/10.1186/s13007-019-0532-7
Widodo Y. 2003. Penggunaan Color Histogram Dalam Image Retrievl [internet]. Diakses 17 Maret 2020. Tersedia pada http://www.ilmukomputer.com.
