Increasing Precision of Water Sprout Detection based on Mask R-CNN with Data Augmentation

Intan Sari Areni (1), Nurul Maulidyah (2), - Indrabayu (3), Anugrayani Bustamin (4), Azran Budi Arief (5)
(1) Department of Electrical Engineering, Hasanuddin University, Makassar, 90245, Indonesia
(2) Department of Electrical Engineering, Hasanuddin University, Makassar, 90245, Indonesia
(3) Department of Informatics Engineering, Hasanuddin University, Makassar, 90245, Indonesia
(4) Department of Informatics Engineering, Hasanuddin University, Makassar, 90245, Indonesia
(5) Department of Electrical Engineering, Hasanuddin University, Makassar, 90245, Indonesia
Fulltext View | Download
How to cite (IJASEIT) :
Areni, Intan Sari, et al. “Increasing Precision of Water Sprout Detection Based on Mask R-CNN With Data Augmentation”. International Journal on Advanced Science, Engineering and Information Technology, vol. 13, no. 2, Apr. 2023, pp. 794-00, doi:10.18517/ijaseit.13.2.16468.
This study evaluated the detection performance of four Mask R-CNN models trained in different scenarios. The first two scenarios are trained with a learning rate of 0.01 using data augmentation on the training data. The other two scenarios are trained with a learning rate of 0.001 and the same as previously, using augmentation on training data. These models are trained to detect water sprouts in cacao plants. The original data used are obtained from photographed pictures on the cocoa farm. As much as 150 images, the data is divided into 120 images for training data and 30 images for testing data. In previous studies, the model was trained without performing data augmentation, so that the amount of data trained was less than this study. Data augmentation is implemented to compromise the small amount of data and prevent over-fitting during the model training process. This process uses six augmentation parameters, namely horizontal flip, blur using Gaussian blur, contrast modification using linear contrast, color saturation alteration, cropping the sides of the image randomly by 50 pixels, and rotating the image. The test is carried out by varying the threshold value in the range of 0.6 to 0.9. The results obtained indicate that the model trained with a learning rate of 0.001 with data augmentation can detect objects better than other models with an F1score of 0.966 at a threshold of 0.8. This research will be developed to create a water sprout cutting robot in the future.

E. Emma, “Can water sprouts and suckers be prevented on trees?,” Universitas of New Hampshire Extension, Feb, 26, 2021. [Online]. Available:

S. Abo”Hamed, H. A. Collin, and K. Hardwick, “Biochemical and Physiological Aspects of Leaf Development in Cocoa (theobroma Cacao L.),” New Phytol., vol. 95, no. 1, pp. 9-17, 1983, doi: 10.1111/j.1469-8137.1983.tb03463.x.

A. D. Mckelvie, “Cherelle Wilt of CacaoI. POD Development and ITS Relation to Wilt,” J. Exp. Bot., vol. 7, no. 2, pp. 252-263, Jan. 1956, doi: 10.1093/jxb/7.2.252.

P. A. Sleigh, H. A. Collin, and K. Hardwick, “Distribution of assimilate during the flush cycle of growth in Theobroma cacao L.,” Plant Growth Regul., vol. 2, no. 4, pp. 381-391, Dec. 1984, doi: 10.1007/BF00027297.

L. Diby, J. Kahia, C. Kouamí©, and E. Aynekulu, “Tea, Coffee, and Cocoa,” in Encyclopedia of Applied Plant Sciences (Second Edition), B. Thomas, B. G. Murray, and D. J. Murphy, Eds. Oxford: Academic Press, 2017, pp. 420-425. doi: 10.1016/B978-0-12-394807-6.00179-9.

G. Komitov, I. Mitkov, V. Harizanov, N. Neshev, and M. Yanev, “Justification of Agrotechnical Indicators of Agrorobot,” in 2020 7th International Conference on Energy Efficiency and Agricultural Engineering (EE AE), Nov. 2020, pp. 1-5. doi: 10.1109/EEAE49144.2020.9279046.

Y. Liu, X. Ma, L. Shu, G. P. Hancke, and A. M. Abu-Mahfouz, “From Industry 4.0 to Agriculture 4.0: Current Status, Enabling Technologies, and Research Challenges,” IEEE Trans. Ind. Inform., vol. 17, no. 6, pp. 4322-4334, Jun. 2021, doi: 10.1109/TII.2020.3003910.

K. Jha, A. Doshi, P. Patel, and M. Shah, “A comprehensive review on automation in agriculture using artificial intelligence,” Artif. Intell. Agric., vol. 2, pp. 1-12, Jun. 2019, doi: 10.1016/j.aiia.2019.05.004.

B. Narayanavaram, E. M. K. Reddy, and M. R. Rashmi, “Arduino based Automation of Agriculture A Step towards Modernization of Agriculture,” in 2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA), Nov. 2020, pp. 1184-1189. doi: 10.1109/ICECA49313.2020.9297546.

V. Puranik, Sharmila, A. Ranjan, and A. Kumari, “Automation in Agriculture and IoT,” in 2019 4th International Conference on Internet of Things: Smart Innovation and Usages (IoT-SIU), Apr. 2019, pp. 1-6. doi: 10.1109/IoT-SIU.2019.8777619.

T. W. Cenggoro, A. Budiarto, R. Rahutomo, and B. Pardamean, “Information System Design for Deep Learning Based Plant Counting Automation,” in 2018 Indonesian Association for Pattern Recognition International Conference (INAPR), Sep. 2018, pp. 329-332. doi: 10.1109/INAPR.2018.8627019.

N. O. S. Matthew et al., “Robotic Automation in Agriculture,” International Journal of Trend in Research and Development., vol. 8, no. 3, pp. 381-384, Jun 2021.

T. Veramakali et al., “Smart Agricultural Management using IoT Based Automation Sensors,” International Journal of Recent Technologyand Engineering (IJRTE), vol.8, no. 6, March 2020.

L. Zhang, C. Xia, D. Xiao, P. Weckler, Y. Lan, and J. Lee, “A leaf vein detection scheme for locating individual plant leaves,” in 2018 International Conference on Information and Communication Technology Robotics (ICT-ROBOT), Sep. 2018, pp. 1-4. doi: 10.1109/ICT-ROBOT.2018.8549901.

N. M. Yusoff, I. S. Abdul Halim, N. E. Abdullah, and A. A. Ab. Rahim, “Real-time Hevea Leaves Diseases Identification using Sobel Edge Algorithm on FPGA: A Preliminary Study,” in 2018 9th IEEE Control and System Graduate Research Colloquium (ICSGRC), Aug. 2018, pp. 168-171. doi: 10.1109/ICSGRC.2018.8657603.

J. Qi, D. Xie, L. Li, W. Zhang, X. Mu, and G. Yan, “Estimating Leaf Angle Distribution From Smartphone Photographs,” IEEE Geosci. Remote Sens. Lett., vol. 16, no. 8, pp. 1190-1194, Aug. 2019, doi: 10.1109/LGRS.2019.2895321.

Y. Chen, S. Baireddy, E. Cai, C. Yang, and E. J. Delp, “Leaf Segmentation by Functional Modeling,” in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Jun. 2019, pp. 2685-2694. doi: 10.1109/CVPRW.2019.00326.

Z. Wang, K. Wang, F. Yang, S. Pan, and Y. Han, “Image segmentation of overlapping leaves based on Chan-Vese model and Sobel operator,” Inf. Process. Agric., vol. 5, no. 1, pp. 1-10, Mar. 2018.

M. A. Kutlugí¼n, Y. Sirin, and M. Karakaya, “The Effects of Augmented Training Dataset on Performance of Convolutional Neural Networks in Face Recognition System,” in 2019 Federated Conference on Computer Science and Information Systems (FedCSIS), Sep. 2019, pp. 929-932. doi: 10.15439/2019F181.

A. S. Paste and S. Chickerur, “Analysis of Instance Segmentation using Mask-RCNN,” in 2019 2nd International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT), Jul. 2019, vol. 1, pp. 191-196. doi: 10.1109/ICICICT46008.2019.8993224.

Y. Song and Z. Lin, “Species recognition technology based on migration learning and data augmentation,” in 2018 5th International Conference on Systems and Informatics (ICSAI), Nanjing, Nov. 2018, pp. 1016-1021. doi: 10.1109/ICSAI.2018.8599361.

S. Park, S. Lee, and J. Park, “Data augmentation method for improving the accuracy of human pose estimation with cropped images,” Pattern Recognit. Lett., vol. 136, pp. 244-250, Aug. 2020, doi: 10.1016/j.patrec.2020.06.015.

A. Almutairi and M. Almashan, “Instance Segmentation of Newspaper Elements Using Mask R-CNN,” in 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA), Dec. 2019, pp. 1371-1375. doi: 10.1109/ICMLA.2019.00223.

M. Z. Islam et al, “Static Hand Gesture Recognition using Convolutional Neural Network with Data Augmentation,” in 8th International Conference on Informatics, Electronics and Vision (ICIEV), Washington, USA, April 2019, doi:10.1109/ICIEV.2019.8858563.

N. Maulidyah, Indrabayu, and I. S. Areni, “Water Sprouts Detection of Cacao Tree Using Mask Region-based Convolutional Neural Network,” in 2020 27th International Conference on Telecommunications (ICT), Oct. 2020, pp. 1-5. doi: 10.1109/ICT49546.2020.9239443.

K. He, G. Gkioxari, P. Dollí¡r, and R. Girshick, “Mask R-CNN,” in 2017 IEEE International Conference on Computer Vision (ICCV), Oct. 2017, pp. 2980-2988. doi: 10.1109/ICCV.2017.322.

S. Li, M. Yan, and J. Xu, “Garbage object recognition and classification based on Mask Scoring RCNN,” in 2020 International Conference on Culture-oriented Science Technology (ICCST), Oct. 2020, pp. 54-58. doi: 10.1109/ICCST50977.2020.00016.

J. Shi, Y. Zhou, and W. X. Q. Zhang, “Target Detection Based on Improved Mask Rcnn in Service Robot,” in 2019 Chinese Control Conference (CCC), Jul. 2019, pp. 8519-8524. doi: 10.23919/ChiCC.2019.8866278.

M. Bizjak, P. Peer, and Ž. EmerÅ¡iÄ, “Mask R-CNN for Ear Detection,” in 2019 42nd International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), May 2019, pp. 1624-1628. doi: 10.23919/MIPRO.2019.8756760.

M. A. Malbog, “MASK R-CNN for Pedestrian Crosswalk Detection and Instance Segmentation,” in 2019 IEEE 6th International Conference on Engineering Technologies and Applied Sciences (ICETAS), Dec. 2019, pp. 1-5. doi: 10.1109/ICETAS48360.2019.9117217.

X. Zhang, G. An, and Y. Liu, “Mask R-CNN with Feature Pyramid Attention for Instance Segmentation,” in 2018 14th IEEE International Conference on Signal Processing (ICSP), Beijing, China, Aug. 2018, pp. 1194-1197. doi: 10.1109/ICSP.2018.8652371.

R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” ArXiv13112524 Cs, Oct. 2014, [Online]. Available:

K. S. Htet and M. M. Sein, “Toddy Palm Trees Classification and Counting Using Drone Video: Retuning Hyperparameter Mask-RCNN,” in 2021 7th International Conference on Control, Automation and Robotics (ICCAR), Apr. 2021, pp. 196-200. doi: 10.1109/ICCAR52225.2021.9463466.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” ArXiv151203385 Cs, Dec. 2015, [Online]. Available:

T. Liu, M. Chen, M. Zhou, S. S. Du, E. Zhou, and T. Zhao, “Towards Understanding the Importance of Shortcut Connections in Residual Networks,” ArXiv190904653 Cs Math Stat, Nov. 2019, [Online]. Available:

T.-Y. Lin, P. Dollí¡r, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature Pyramid Networks for Object Detection,” ArXiv161203144 Cs, Apr. 2017, [Online]. Available:

T.-Y. Lin et al., “Microsoft COCO: Common Objects in Context,” ArXiv14050312 Cs, Feb. 2015, [Online]. Available:

Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
    3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).