Implementasi Convolutional Neural Network untuk sistem Prediksi Pigmen Fotosintesis pada Tanaman Secara Real Time

Kestrilia Rega Prilianti, Ivan Christianto Onggara, Hendry Setiawan


It is common that evaluation on plant health is done by conducting measurement on photosynthetic pigments. Analysis of the presence or absence of some particular pigments could reveal any information about plant responses to the environment or climate changes. This is due to the fact that relative pigment concentrations are influenced by environmental factors such as light and nutrient availability. In this research, a non-destructive and rapid method was developed to identify the existence of photosynthetic pigments in plant leaf i.e. chlorophyll, carotenoid, and anthocyanin. The method used leaf’s RGB digital image as the color representation of the pigments contained in the plant being evaluated. The intelligence agent which is responsible to learn the data and provide information about the pigments was developed based on convolutional neural network (CNN) model. This model was chosen due to its capability to receive a digital image and automatically search for the best feature to learn it. Therefore, plant evaluation could run in real time. Result of the experiment reveals that CNN model could learn the color-pigment relationship very well. The best architecture is ShallowNet using Adam optimizer, batch size 30 and trained with 15 epoch. The MSE of the pigments prediction reaches 0.0055 (actual data range -0.2 up to 2.2) for training and 0.029 for testing.

Full Text:



A.J.S. Neto, D.C. Lopes, & J.C.F.B Junior, “Assesment of Photosynthetic Pigment and Water Contents in Intact Sunflower Plants from Spectral Indices,” Agriculture, vol.7, no.8. 2017.

A.E. Strever, “Non-Destructive Assessment of Leaf Composition as Related to Growth of The Grapevine (Vitis vinifera L. cv. Shiraz),” Doctoral thesis, Stellenbosch University, 2012.

(2017) The Avantes website. [Online]. Tersedia: www.azom. com/article.aspx?ArticleID=14434.

L. Li, Q. Zhang, & D. Huang, “A Review of Imaging Techniques for Plant Phenotyping,” Sensors, vol.14, pp.20078-20111, 2014.

M. Radovic, O. Adarkwa, & Q. Wang, “Object Recognition in Aerial Image Using Convolutional Neural Networks,” Journal of Imaging, vol.3, no.21, pp.1-9, 2017.

B. Zhao, J. Feng, X. Wu, & S. Yang, “A Survey on Deep Learning-Based Fine-grained Object Classification and Semantic Segmentation,” International Journal of Automation and Computing, vol.14, no.2, pp.119-135, 2017.

Z. Cheng, X. Li, & C.C. Loy, “Pedestrian Color Naming via Convolutional Neural Network,” Proceeding ACCV, 2018, pp.35-51.

V.O. Yazici, J.V. Weijer, & A. Ramisa, “Color Naming for Multi-Color Fashion Items,” Proceeding WorldCIST’18, 2018, pp. 64-73.

M. Dyrmann, H. Karstoft, & H.S. Midtiby, “Plant Species Classification Using Deep Convolutional Neural Network. Biosystems Engineering,” Engineering, vol.151, pp.72-80, 2016.

M.M. Ghazi, B. Yanikoglu, & E. Aptoula, “Plant Identification Using Deep Neural Networks Via Optimization of Transfer Learning Parameters,” Neurocomputing, vol.235, pp.228-235, 2017.

S.P. Mohanty, D.P. Hughes, & M. Salathe, “Using Deep Learning for Image-Based Plant Disease Detection,” Frontier in Plant Science, vol.22, no.7, 2016.

E. Mlodzinska, “Survey of Plant Pigments: Molecular and Environmental Determinants of Plant Colors,” Acta Biologica Cracoviensia, vo. 51, no.10, pp.7-16, 2009.

A.S. Harrera, “The Biological Pigments in Plants Physiology,” Agricultural Sciences, vol.6, pp.1262-1271, 2015.

H. Croft, & J.M. Chen, Leaf Pigment Content. Elsevier Canada, 2017.

A.A. Gitelson, & M.N. Merzlyak, “Non-Destructive Assessment of Chlorophyll Carotenoid and Anthocyanin Content in Higher Plant Leaves: Principles and Algorithms,” Proceeding Remote Sensing for Agriculture and the Environment Conf., Greece, Ella. 2004, pp.78-94.

Sukardi, Z. Arifin, & M. Risaldi, 2017. “Klasifikasi Penentuan Gambar Berbasis Tensorform dan Framework dengan Algoritma CNN,” Prosiding SEMNASTIKOM, 2017.

H.E. Khiyari, & H, Wechsler, “Face Recognition across Time Lapse Using Convolutional Neural Networks,” Journal of Information Security,vol.7, pp. 141-151, 2016.

S. Albewi, & A. Mahmood, “A Framework for Designing the Architectures of Deep Convolutional Neural Networks,” Entropy, vol.19, no. 6, pp. 1-20, 2017.



  • There are currently no refbacks.

Copyright (c) 2018 Jurnal Teknik Informatika dan Sistem Informasi