Implementasi Perbaikan Kualitas Citra Tanaman terhadap Perbedaan Kamera untuk Prediksi Pigmen Fotosintesis berbasis Machine Learning


  • Felix Adrian Tjokro Atmodjo Universitas Ma Chung
  • Kestrilia Rega Prilianti Universitas Ma Chung
  • Hendry Setiawan Universitas Ma Chung



3D-TPS, plant leaves, pigment, image quality improvement, 3D – TPS, daun tanaman, pigmen, perbaikan kualitas citra


Implementation of Plant Image Quality Improvement based on Machine Learning on Camera Variation to Predict Photosynthetic Pigments. Pigments are natural dyes found in plants and animals. In photosynthesis, there are 3 essential pigments: chlorophyll, cartenoid, and anthocyanin. Pigment analysis can be performed with High Performance Liquid Chromatography (HPLC) and a spectrophotometer. However, HPLC and spectrophotometers require high resources and time. Thus, the Fuzzy Piction Android application built using the FP3Net model is the best choice in pigment prediction since it is low on cost and accessible. However, the Fuzzy Piction produces different performance, which is affected by light conditions and camera specifications. The experiment used ten sample images for Jasminum sp., P. betle, Syzygium oleina of green and red variations, and Graptophyllum pictum leaves with three smartphone cameras and three lighting levels. Improvements using 3D-TPS produced the best SSIM values in the range of 0.9191 – 0.9797 for images Syzygium oleina of green and red variations leaves, and the predicted MAE value of pigment was 0.0296 – 0.0492.
Keywords: 3D-TPS, plant leaves, pigment, image quality improvement

Implementasi Perbaikan Kualitas Citra Tanaman terhadap Perbedaan Kamera untuk Prediksi Pigmen Fotosintesis berbasis Machine Learning. Pigmen merupakan pewarna alami yang ditemukan pada tumbuhan dan hewan. Dalam proses fotosintesis terdapat tiga pigmen yang penting, yaitu klorofil, kartenoid, dan antosianin. Analisis pigmen dapat dilakukan dengan Kromatorafi Cair Kinerja Tinggi (KCKT) dan spektrofotometer. Namun, KCKT dan spektrofotometer membutuhkan sumber daya dan waktu yang tinggi. Sehingga, aplikasi Android Fuzzy Piction yang dibangun menggunakan model FP3Net mejadi pilihan dalam prediksi pigmen dengan biaya murah dan mudah. Akan tetapi, aplikasi Android Fuzzy Piction menghasilkan kinerja yang berbeda-beda yang dipengaruhi oleh kondisi cahaya dan spesifikasi kamera. Dilakukan percobaan dengan mengambil sepuluh sampel citra daun dari empat varietas tanaman yaitu, pucuk merah, daun ungu, melati, dan sirih. Citra diambil dengan tiga kamera smartphone dan tiga tingkat pencahayaan yang berbeda. Perbaikan yang dilakukan menggunakan algoritma 3D-TPS menghasilkan nilai SSIM terbaik pada rentang 0.9191 – 0.9797 untuk citra daun pucuk merahdan nilai MAE prediksi pigmen sebesar 0.0296 –0.0492.
Kata Kunci: 3D – TPS, daun tanaman, pigmen, perbaikan kualitas citra


J. E. Thrane, "Spectrophotometric Analysis of Pigmens: A Critical Assesment of a High Throughput Method for Analysis of Agal Pigment Mixtures by Spectral Deconvolution," Plos One, vol. 10, no. 9, p. e0137645, 2015.

J. C. D. Valle, A. Gallardo-Lopez, M. L. Buide, J. B. Whittall and E. Narbona, "Digital Photography Provides a Fast Reliable and Noninvasive Methon to Estimate Antocyanin Pigment Concentration in Reproductive and Vegetative Plant Tissues," Ecology and

Evolution, vol. 8, no. 6, pp. 3064-3076, 2018.

A. Pak, S. Reichel and J. Burke, "Machine-Learning-Inspired Workflow for Camera Calibration," Sensors, vol. 22, no. 18, p. 6804, 2022.

A. Justine, "Pengembangan Aplikasi Prediksi Kandungan Pigmen Daun Secara Non Destruktif Berbasis Android," Universitas Ma Chung, Malang, 2020.

A. Justine, "Pengembangan Fuzzy Convolutional Neural Network untuk Pengenalan Warna pada Sistem Prediksi Pigmen Tanaman," Universitas Ma Chung, Malang, 2021.

S. Sunoj, C. Igathinathane, N. Saliendra, J. Hendrickson and D. Archer, "Color Calibration of Digital Images for Agriculture and Other Applications," Journal of Photogrammetry and Remote Sensing, vol. 146, pp. 221-234, 2018.

A. Hashimoto, T. Muramatsu, K. Suehara, S. Kameoka and T. Kameoka, "Color Evaluation of Images Acquired Using Open Platform Camera and Mini-spectrometer under natural lighting conditions," Food Packaging and Shelf Life, vol. 14, pp. 26-33, 2017.

P. Menasatti, C. Angelini, F. Pallotino, F. Antonucci, J. Aguzzi and C. Costa, "GPU Accelerated 3D Image Deformation Using Thin-Plate Splines," 2014 IEEE International Conference on High Performance Computing and Communications, 6th Inti Symp On Cyberspace Safety and Security, 11th Inti Conf on Embedded Software and Syst (HPCC, CSS, ICESS), pp. 1142-1149, 2014.

O. Hassanijalilian, C. Igathinathane, C. Doetkott, S. Bajwa, J. Nowatzki and S. A. H. Esmaeili, "Chlorophyll estimation in soybean leaves infield with smartphone digital imaging and machine learning," J. Compag, p. 105433, 2020.

K. S. Ng, "A Simple Explanation of Partial Least Squares," CECC Autralian National Uniersity , 2013.

H. Abdi and L. J. Williams, "Partial Least Square Methods: Partial Least Squares Correlation and Partial Least Square Regression,"Methods in Molecular Biology, vol. 930, pp. 549-579, 2013.

Z. Tang, K. Chen, M. Pan, M. Wang and Z. Song, "An Augmentation Strategy for Medical Image Processing Based on Statistical Shape Model and 3D Thin Plate Spline," IEEE Access, vol. 7, pp. 133111-133121, 2019.

D. Kendal, C. E. Hauser, G. Garrard, S. Jellinek, K. M. Gilijohann and J. L. Moore, "Quantifying Plant Colour and Colour Difference as Perceived by Humans using Digital Images," Plos One, vol. 8, no. 8, p. e72296, 2013.

F. Gasparini and R. Schettini, "Unsupervised Color Correction for Digital Photographs," 2014.

V. K. Vishnoi, K. Kumar and B. Kumar, "Plant Disease Detection using Computational Intelligence and Image Processing," Journal of Plant Diseases and Protection, vol. 128, no. 1, pp. 19-53, 2021.

M. Amani, H. Falk, O. D. Jensen, G. Vartdal, A. Aune and F. Lindseth, "Color Calibration on Human Skin Images," in Computer Vision Systems, Springer International Publishing, 2019, pp. 211-223.

W. Li and S. Duan, "Color calibration and correcction applying linear interpolation technique for color fringe projecton system," J. IJLEO, vol. 127, no. 4, pp. 2074-2082, 2016.

H. Huang, A. Yang, Y. Tang, J. Zhuang, C. Hou, Z. Tan, S. Dananjayan, Y. He, Q. Guo and S. Luo, "Deep color calibration for UAV imagery in crop monitoring using semantic style transfer with local to global attention," International Journal of Applied Earth Observation and Geoinformation, vol. 104, p. 102590, 2021.

T. Vitorino, A. Casini, C. Cucci, A. Gebejes, J. Hiltunen, M. H. Kasari, M. Picollo and L. Stefani, "Accuracy in Colour Reproduction: Using a ColorChecker Chart to Assess the Usefullnes and COmparability of Data Acquired with Two Hyper-Spectral Systems," in International Workshop on Computational Color Imaging, 2015.

Navarasu, "Using Machine Learning for Color Calibration with a Color Checker," 2019. [Online]. Available: [Accessed November 2021].

P. D. Kusuma, Machine Learning Teori, Program, dan Studi Kasus, Yogyakarta: Deepublish Publisher, 2020.

K. Prilianti, S. Anam, T. Brotosudarmo and A. Suryanto, "Real-time Assessment of Plant Photosynthetic Pigment Contents with an Artificial Intelligence Approch in A Mobile Application," Jurnal of Agricultural Engineering, vol. 51, no. 4, pp. 220-229, 2020.