Skip to main content
SpringerLink
Log in

A mobile application to identify poison ivy (Toxicodendron radicans) plants in real time using convolutional neural network

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Poison ivy (Toxicodendron radicans) is an important noxious plants in many countries around the world. Currently, the primary method used to identify this plant is based on visual evaluations of the leaf shape and arrangement. In this study, we evaluated four variations of YOLO-Tiny to identify Poison ivy and we proposed a smartphone application (APP) to perform the detection in real-time. Images were taken in different parks located in the United States and then augmented, totaling 3,407 images and 73,824 annotations. The model with the highest mean average precision (mAP), precision (P), recall (R), F1-score, and lowest loss function value was selected to build the APP. Two smartphones (Motorola M51 and Xiaomi Redmi Note 11 Pro) and five input resolutions were evaluated (224, 288, 320, 384, and 416 width and height pixels). The best performance during the training was achieved using a YOLOv4-Tiny-3 L architecture with mAP of 78.8%, 0.85 (P), 0.60 (R), 0.7 (F1-score), and 3.55 for the loss function. The APP evaluation revealed that at 224 and 288 pixels, F1-scores were lower (around 0.39) and fewer plants were identified but the FPS was relatively high (around 4.87). At 416 pixels, more plants were identified with high F1-scores (around 0.66), but with a low FPS rate (around 1.96). The best balance between performance and accuracy was observed at 340 and 320 pixels for both devices. Overall, the results suggest that YOLOv4-tiny-Tiny-3 L can successfully be deployed in smartphones to identify Poison ivy.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Data availability

The dataset will be made available on request.

References

  1. Agarwal S, Terrail JOD, Jurie F (2018) Recent advances in object detection in the age of deep convolutional neural networks. arXiv preprint arXiv:1809.03193

  2. Aldughayfiq B, Ashfaq F, Jhanjhi NZ, Humayun M (2023) YOLO-based deep learning model for pressure ulcer detection and classification. Healthcare 11(9):1222. https://doi.org/10.3390/healthcare11091222

    Article  Google Scholar 

  3. Bochkovskiy A, Wang CY, Liao HYM (2020) Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934

  4. Baldwin RW, Clegg JA, Curran AC, Austin EB, Khan T, Ma Y, Gunn B, Hudecz F, Byers VS, Lepoittevin J-P, Price MR (1999) Regulation of the contact sensitivity response to urushiol with anti-urushiol monoclonal antibody ALG 991. Arch Dermatol Res 291(2):652–658. https://doi.org/10.1007/s004030050470

    Article  Google Scholar 

  5. Britton C, Lynch CF, Ramirez M, Torner J, Buresh C, Peek-Asa C (2013) Epidemiology of injuries to wildland firefighters. Am J Emerg Med 31(2):339–345. https://doi.org/10.1016/j.ajem.2012.08.032

    Article  Google Scholar 

  6. Brook I, Frazier EH, Yeager JK (2000) Microbiology of infected poison ivy dermatitis. Br J Dermatol. 142(5):943–946. https://doi.org/10.1046/j.1365-2133.2000.03475.x

    Article  Google Scholar 

  7. Chen J-W, Lin W-J, Cheng H-J, Hung C-L, Lin C-Y, Chen S-P (2021) A smartphone-based application for scale pest detection using multiple-object detection methods. Electronics 10(4):372. https://doi.org/10.3390/electronics10040372

    Article  Google Scholar 

  8. Chen W, Lu S, Liu B, Li G, Qian T (2020) Detecting citrus in orchard environment by using improved YOLOv4. Sci Program 2020:1–13. https://doi.org/10.1155/2020/8859237

    Article  Google Scholar 

  9. Corceiro A, Alibabaei K, Assunção E, Gaspar PD, Pereira N (2023) Methods for detecting and classifying weeds, diseases and fruits using ai to improve the sustainability of agricultural crops: a review. Processes 11(4):1263. https://doi.org/10.3390/pr11041263

    Article  Google Scholar 

  10. Dang F, Chen D, Lu Y, Li Z (2023) YOLOWeeds: a novel benchmark of YOLO object detectors for multi-class weed detection in cotton production systems. Comput Electron Agric 205:107655. https://doi.org/10.1016/j.compag.2023.107655

    Article  Google Scholar 

  11. Gai R, Chen N, Yuan H (2023) A detection algorithm for cherry fruits based on the improved YOLO-v4 model. Neural Comput Appl 35(19):13895–13906. https://doi.org/10.1007/s00521-021-06029-z

    Article  Google Scholar 

  12. Gan HM, Penix TS, Wengert PC, Wong NH, Hudson AO, Kumar G, Savka MA (2023) Whole-genome sequence of endophytic bacteria associated with poison ivy vine (Toxicodendron radicans). Microbiol Resour Announcements 12(4). https://doi.org/10.1128/mra.01232-22

  13. Genaev MA, Komyshev EG, Shishkina OD, Adonyeva NV, Karpova EK, Gruntenko NE, Zakharenko LP, Koval VS, Afonnikov DA (2022) Classification of Fruit Flies by Gender in images using smartphones and the YOLOv4-Tiny Neural Network. Mathematics 10(3):295. https://doi.org/10.3390/math10030295

    Article  Google Scholar 

  14. Gladman AC (2006) Toxicodendron Dermatitis: Poison Ivy, Oak, and Sumac. Wilderness Environ Med 17(2):120–128. https://doi.org/10.1580/PR31-05.1

  15. Hu K, Wang Z, Coleman G, Bender A, Yao T, Zeng S, Song D, Schumann A, Walsh M (2023) Deep learning techniques for in-crop weed recognition in large-scale grain production systems: a review. Precision Agric. https://doi.org/10.1007/s11119-023-10073-1

    Article  Google Scholar 

  16. Jelesko JG, Thompson K, Magerkorth N, Verteramo E, Becker H, Flowers JG, Sachs J, Datta J, Metzgar J (2023) Poison ivy (Toxicodendron radicans) leaf shape variability: why plant avoidance-by-identification recommendations likely do not substantially reduce poison ivy rash incidence. Plants People Planet. https://doi.org/10.1002/ppp3.10439

    Article  Google Scholar 

  17. Redmon J, Farhadi A (2018) Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767

  18. Junior FA, Suharjito (2023) Video based oil palm ripeness detection model using deep learning. Heliyon 9(1):e13036. https://doi.org/10.1016/j.heliyon.2023.e13036

  19. Kligman AM (1958) Poison Ivy (Rhus) Dermatitis. AMA Arch Derm 77(2):149. https://doi.org/10.1001/archderm.1958.01560020001001

    Article  Google Scholar 

  20. Lee J, Hwang K (2022) YOLO with adaptive frame control for real-time object detection applications. Multimed Tools Appl 81(25):36375–36396. https://doi.org/10.1007/s11042-021-11480-0

    Article  Google Scholar 

  21. Li J, Zhu X, Jia R, Liu B, Yu C (2022) Apple-YOLO: a novel mobile terminal detector based on YOLOv5 for early apple leaf diseases. 2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC), pp 352–361

  22. Li S, Kang X, Feng Y, Liu G (2021) Detection method for individual pig based on improved YOLOv4 Convolutional Neural Network. 2021 4th International Conference on Data Science and Information Technology (New York, NY, USA), pp 231–235

  23. Liu G, Nouaze JC, Touko Mbouembe PL, Kim JH (2020) YOLO-Tomato: a robust algorithm for tomato detection based on YOLOv3. Sensors 20(7):2145. https://doi.org/10.3390/s20072145

    Article  Google Scholar 

  24. Malik OA, Ismail N, Hussein BR, Yahya U (2022) Automated real-time identification of medicinal plants species in natural environment using deep learning models—a case study from Borneo Region. Plants 11(15):1952. https://doi.org/10.3390/plants11151952

    Article  Google Scholar 

  25. Martinez-Alpiste I, Golcarenarenji G, Wang Q, Alcaraz-Calero JM (2021) A dynamic discarding technique to increase speed and preserve accuracy for YOLOv3. Neural Comput Appl 33(16):9961–9973. https://doi.org/10.1007/s00521-021-05764-7

    Article  Google Scholar 

  26. Matthews J, Beringen R, Leuven R S E W, Velde G, van Valkenburg JHCH, Odé B (2015) Knowledge document for risk analysis of the non-native poison ivy (Toxicodendron radicans) in the Netherlands. Nijmegen. 477 p 57. https://repository.ubn.ru.nl/bitstream/handle/2066/149839/149839.pdf?sequence=1

  27. Parico AIB, Ahamed T (2021) Real time pear fruit detection and counting using YOLOv4 models and deep SORT. Sensors 21(14):4803. https://doi.org/10.3390/s21144803

    Article  Google Scholar 

  28. Pariser DM, Ceilley RI, Lefkovits AM, Katz BE, Paller AS (2003) Poison ivy, oak and sumac. Derm Insights 4(1):26–28

    Google Scholar 

  29. Parupalli S, Akhsitha S, Naval D, Kasam P, Yavagiri S (2023) Performance evaluation of YOLOv2 and modified YOLOv2 using face mask detection. Multimed Tools Appl. https://doi.org/10.1007/s11042-023-16770-3

    Article  Google Scholar 

  30. Redmon J, Divvala S, Girshick R, Farhadi A (2015) You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 779–788

  31. Ren P, Wang L, Fang W, Song S, Djahel S (2020) A novel squeeze YOLO-based real-time people counting approach. Int J Bio-Inspired Comput 16(2):94. https://doi.org/10.1504/IJBIC.2020.109674

    Article  Google Scholar 

  32. Resler LM, Fry JT, Leman S, Jelesko JG (2022) Assessing poison ivy (Toxicodendron radicans) presence and functional traits in relation to land cover and biophysical factors. Phys Geogr 43(5):614–637. https://doi.org/10.1080/02723646.2021.1883802

    Article  Google Scholar 

  33. Richey B, Shirvaikar MV (2021) Deep learning based real-time detection of Northern Corn Leaf Blight crop disease using YoloV4. In: Real-Time Image Processing and Deep Learning 11736, pp. 39–45. SPIE

  34. Ryu S-E, Chung K-Y (2021) Detection model of occluded object based on YOLO using hard-example mining and augmentation policy optimization. Appl Sci 11(15):7093. https://doi.org/10.3390/app11157093

    Article  Google Scholar 

  35. Sachar S, Kumar A (2022) Deep ensemble learning for automatic medicinal leaf identification. Int J Inf Technol 14(6):3089–3097. https://doi.org/10.1007/s41870-022-01055-z

    Article  Google Scholar 

  36. Shafiee MJ, Chywl B, Li  F, Wong A (2017) Fast YOLO: A fast you only look once system for real-time embedded object detection in video. arXiv preprint arXiv:1709.05943

  37. Shelke A, Mehendale N (2023) A CNN-based android application for plant leaf classification at remote locations. Neural Comput Appl 35(3):2601–2607. https://doi.org/10.1007/s00521-022-07740-1

    Article  Google Scholar 

  38. Shi R, Li T, Yamaguchi Y (2020) An attribution-based pruning method for real-time mango detection with YOLO network. Comput Electron Agric 169:105214. https://doi.org/10.1016/j.compag.2020.105214

    Article  Google Scholar 

  39. Shorten C, Khoshgoftaar TM (2019) A survey on image data augmentation for deep learning. J Big Data 6(1):60. https://doi.org/10.1186/s40537-019-0197-0

    Article  Google Scholar 

  40. Song C, Wang C, Yang Y (2020) Automatic detection and image recognition of precision agriculture for citrus diseases. 2020 IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE), p 187–190

  41. Watchmaker L, Reeder M, Atwater AR (2021) Plant dermatitis: More than just poison ivy. Cutis 108(3):124–127

  42. Wehtje G, Gilliam CH, McElroy JS (2013) Poison ivy (Toxicodendron radican) control with triclopyr and metsulfuron, applied alone and in tank mixture. Weed Technol 27(4):725–728. https://doi.org/10.1614/WT-D-13-00034.1

    Article  Google Scholar 

  43. Wu D, Lv S, Jiang M, Song H (2020) Using channel pruning-based YOLO v4 deep learning algorithm for the real-time and accurate detection of apple flowers in natural environments. Comput Electron Agric 178(Nov 2020):105742. https://doi.org/10.1016/j.compag.2020.105742

    Article  Google Scholar 

  44. Wu F, Zhao H, Wang M (2021) Nighttime cattle detection based on YOLOv4. Twelfth International Conference on Graphics and Image Processing (ICGIP 2020), p116

  45. Xu Q, Li Y, Shi Z (2022) LMO-YOLO: a ship detection model for low-resolution optical satellite imagery. IEEE J Select Topics Appl Earth Observ Remote Sens 15(2022):4117–4131. https://doi.org/10.1109/JSTARS.2022.3176141

    Article  Google Scholar 

  46. Yang B, Gao Z, Gao Y, Zhu Y (2021) Rapid detection and counting of wheat ears in the field using YOLOv4 with attention module. Agronomy 11(6):1202. https://doi.org/10.3390/agronomy11061202

    Article  Google Scholar 

  47. Yijing W, Yi Y, Xue-fen W, Jian C, Xinyun L (2021) Fig fruit recognition method based on YOLO v4 Deep learning. 2021 18th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), p 303–306

  48. Ying B, Xu Y, Zhang S, Shi Y, Liu L (2021) Weed detection in images of carrot fields based on improved YOLO v4. Traitement du Signal 38(2):341–348. https://doi.org/10.18280/ts.380211

    Article  Google Scholar 

  49. Yuan W, Choi D, Bolkas D, Heinemann PH, He L (2022) Sensitivity examination of YOLOv4 regarding test image distortion and training dataset attribute for apple flower bud classification. Int J Remote Sens. 43(8):3106–3130. https://doi.org/10.1080/01431161.2022.2085069

    Article  Google Scholar 

  50. Zeng T, Li S, Song Q, Zhong F, Wei X (2023) Lightweight tomato real-time detection method based on improved YOLO and mobile deployment. Comput Electron Agric 205(Feb 2023):107625. https://doi.org/10.1016/j.compag.2023.107625

    Article  Google Scholar 

  51. Zhou B, Song Z, Wang Y, Hu F (2021) Flower Gender Recognition Based on YOLO V4. In: 3D Imaging Technologies—Multidimensional Signal Processing and Deep Learning: Methods, Algorithms and Applications 2(pp. 43–49). Springer Singapore

Download references

Funding

The authors have no relevant financial or non-financial interests to disclose.

Author information

Authors and Affiliations

  1. Weed Science Laboratory – Gulf Coast Research and Education Center, University of Florida, Wimauma, FL, 33598, USA

    Renato Herrig Furlanetto & Nathan Boyd

  2. Citrus Research and Education Center, University of Florida, Lake Alfred, FL, USA

    Arnold Schumann

Authors
  1. Renato Herrig Furlanetto
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Arnold Schumann
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Nathan Boyd
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Nathan Boyd.

Ethics declarations

Competing interests

No potential conflict of interest was reported by the authors.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Furlanetto, R.H., Schumann, A. & Boyd, N. A mobile application to identify poison ivy (Toxicodendron radicans) plants in real time using convolutional neural network. Multimed Tools Appl (2024). https://doi.org/10.1007/s11042-023-17920-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11042-023-17920-3

Keywords

Search

Navigation