Quantitative Analysis of Deep Leaf: a Plant Disease Detector on the Smart Edge
Abstract
Diagnosis of plant health conditions is gaining significant attention in smart agriculture. Timely recognition of early symptoms of a disease can help avoid the spread of epidemics on the plantations. In this regard, most of the existing solutions use some AI techniques on smart edge devices (IoTs or intelligent Cyber Physical Systems), typically equipped with a hardware like sensors and actuators. However, the resource constraints on such devices like energy (power), memory and computation capability, make the execution of complex operations and AI algorithms (neural network models) for disease detection quite challenging. To this end, compression and quantization techniques offer viable solutions to reduce the memory footprint of neural networks while maximizing performance on the constrained devices. In this paper, we realized a real intelligent CPS on top of which we implemented an AI application, called Deep Leaf running on a microcontroller of the STM32 family, to detect coffee plant diseases with the help of a Quantized Convolutional Neural Network (Q-CNN) model. We present a quantitative analysis of Deep Leaf by comparing five different deep learning models: a 32-bit floating point model, a compressed model, and three different types of quantized models exhibiting differences in terms of accuracy, memory utilization, average inference time, and energy consumption. Experimental results show that the proposed Deep Leaf detector is able to correctly classify the plant health condition with an accuracy of 96%, thus demonstrating the feasibility of our approach on a Smart Edge platform.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Authors in [118] proposed a low-power and realtime image detector for grape leaf esca diseases based on a compressed CNN model.
“The authors in [118] proposed a low-power and realtime image detector for grape leaf esca diseases based on a compressed CNN model.”
From A Comprehensive Survey on TinyML (2023) · cites this paper as [118]
Cites
Internet of Things (IoT): A vision, architectural elements, and future directions
Gubbi, J., Buyya, R., Marusic, S., & Palaniswami, M. (2013) · Future Generation Computer Systems · doi:10.1016/j.future.2013.01.010 · Cited by 12,293 · see citing works
ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression
Luo, J.-H., Wu, J., & Lin, W. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.541 · Cited by 1,889 · see citing works
Data augmentation for improving deep learning in image classification problem
Mikołajczyk, A., & Grochowski, M. (2018) · International Interdisciplinary PhD Workshop (IIPhDW) · doi:10.1109/iiphdw.2018.8388338 · Cited by 1,737 · see citing works
Plant Disease Detection Using Machine Learning
Ramesh, S., Hebbar, R., Niveditha, M. K., et al. (2018) · International Conference on Design Innovations for 3Cs Compute Communicate Control (ICDI3C) · doi:10.1109/icdi3c.2018.00017 · Cited by 574 · see citing works
Plant Leaf Disease Detection and Classification Based on CNN with LVQ Algorithm
Sardoğan, M., Tuncer, A., & Özen, Y. (2018) · International Conference on Computer Science and Engineering (UBMK) · doi:10.1109/ubmk.2018.8566635 · Cited by 545 · see citing works
Hello Edge: Keyword Spotting on MicrocontrollersPreprint
Zhang, Y., Suda, N., Lai, L., & Chandra, V. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.07128 · Cited by 356 · see citing works
CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUsPreprint
Lai, L., Suda, N., & Chandra, V. (2018) · arXiv (Cornell University) · doi:10.4230/oasics.ng-res.2025.4 · Cited by 304 · see citing works
A survey on fog computing for the Internet of Things
Bellavista, P., Berrocal, J., Antonio Corradi, A., Das, S. K., Foschini, L., & Zanni, A. (2018) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2018.12.007 · Cited by 268 · see citing works
Self-citationA Survey on Methods and Theories of Quantized Neural NetworksPreprint
Guo, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.04752 · Cited by 249 · see citing works
Diseases Detection of Various Plant Leaf Using Image Processing Techniques: A Review
Kumar, S., & Raghavendra, B. K. (2019) · doi:10.1109/icaccs.2019.8728325 · Cited by 136 · see citing works
Cerutti, G., Prasad, R., Brutti, A., & Farella, E. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2969775 · Cited by 61 · see citing works
I/Ocloud: Adding an IoT Dimension to Cloud Infrastructures
Bruneo, D., Distefano, S., Longo, F., et al. (2018) · Computer · doi:10.1109/mc.2018.1151016 · Cited by 41 · see citing works
Self-citationIntelligent Cyber-Physical Systems for Industry 4.0
Cogliati, D., Falchetto, M., Pau, D. P., et al. (2018) · International Conference on Artificial Intelligence for Industries (AI4I) · doi:10.1109/ai4i.2018.8665681 · Cited by 33 · see citing works
Work-in-Progress: Quantized NNs as the Definitive Solution for Inference on Low-Power ARM MCUs?
Rusci, M., Capotondi, A., Conti, F., & Luca Benini, C. (2018) · International Conference on Hardware/Software Codesign and System Synthesis · doi:10.1109/codesisss.2018.8525915 · Cited by 24 · see citing works
Using Deep Reinforcement Learning for Application Relocation in Multi-Access Edge Computing
Vita, F. D., Nardini, G., Virdis, A., et al. (2019) · IEEE Communications Standards Magazine · doi:10.1109/mcomstd.2019.1900011 · Cited by 17 · see citing works
Intelligent Recognition of TCP Intrusions for Embedded Micro-controllers
Varenne, R., Delorme, J.-M., Plebani, E., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30754-7_36 · Cited by 3 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
A Comprehensive Survey on TinyML
Abadade, Y., Temouden, A., Bamoumen, H., Benamar, N., Chtouki, Y., & Hafid, A. S. (2023) · IEEE Access · doi:10.1109/access.2023.3294111 · Cited by 366 · see citing works
“The authors in [118] developed a TinyML CNN model aims to classify between infected and healthy coffee plant.”
Background
- Authors
- de Vita, F., Nocera, G., Bruneo, D., Tomaselli, V., Giacalone, D., & Das, S. K.
- Affiliations
- University of Messina (IT)
- STMicroelectronics (Italy) (IT)
- Missouri University of Science and Technology (US)
- Venue
- 2020 IEEE International Conference on Smart Computing (SMARTCOMP)
- Publisher
- IEEE
- Published
- 2020-09
- Pages
- 49-56
- OpenAlex
- W3095388995
- Cited by
- 41
- References
- 16
- Citations by year
- 2026: 3 · 2025: 7 · 2024: 12 · 2023: 8 · 2022: 8 · 2021: 2 · 2020: 1
- FWCI
- 6.99
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE International Conference on Smart Computing (publishedVersion)
- Topics
- Life Sciences › Agricultural and Biological Sciences › Plant Science › Smart Agriculture and AI
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Keywords
- plant disease detection, coffee plant disease, quantized convolutional neural networks, neural network compression, STM32 microcontroller, resource-constrained devices, energy consumption, inference latency, smart agriculture, cyber-physical systems
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
