Convolutional neural networks have remarkably progressed the performance of distinguishing plant diseases, severity grading, and nutrition deficiency prediction using leaf images. However, these tasks become more challenging in a realistic in-situ field condition. Often, a traditional machine learning model may fail to capture and interpret discriminative characteristics of plant health, growth and diseases due to subtle variations within leaf subcategories. A few deep learning methods have used additional preprocessing stages or network modules to address the problem, whereas several other methods have utilized pre-trained backbone CNNs, most of which are computationally intensive. Therefore, to address the challenge, we propose a lightweight autoencoder using separable convolutional layers in its encoder decoder blocks. A sigmoid gating is applied for refining the prowess of the encoders feature discriminability, which is improved further by the decoder. Finally, the feature maps of the encoder decoder are combined for rich feature representation before classification. The proposed Convolutional Lightweight Autoencoder for Plant disease classification, called CLAP, has been experimented on three public plant datasets consisting of cassava, tomato, maize, groundnut, grapes, etc. for determining plant health conditions. The CLAP has attained improved or competitive accuracies on the Integrated Plant Disease, Groundnut, and CCMT datasets balancing a tradeoff between the performance, and little computational cost requiring 5 million parameters. The training time is 20 milliseconds and inference time is 1 ms per image.
Figures & tables
Fig. 1: CLAP: convolutional lightweight autoencoder to classify plant stress
Fig. 2: Diagram of the proposed convolutional lightweight encoder-decoder model for plant health classification, named CLAP.
Fig. 3: Sample images of disease-infected plants: maize leaf blight, blackgram yellow mosaic, cashew leaf miner, and soybean septoria brown spot.
Method
Val Acc
Test Acc
Prec
Rec
F1-sc
Base Encoder
95.33
93.29
93.0
93.0
93.0
Encoder+Decoder-I
95.85
94.33
94.0
94.0
94.0
CLAP
96.03
95.67
96.0
96.0
96.0
TABLE I: Ablation study: Module-wise Results on IPD Dataset
Plant
Train:Test
Class
Prec
Rec
F1
Diseased
89.0
89.0
89.0
Betel
553:177
Leaf Dried
93.0
93.0
93.0
Healthy
97.0
95.0
96.0
Anthracnose
96.0
96.0
96.0
Healthy
94.0
77.0
85.5
Blackgram
605:201
Leaf Crinkle
83.0
100.0
91.5
TABLE II: Summary of the Integrated Plant Disease (IPD) Dataset and class-wise overall performance of CLAP
Dataset#C
Train : Test
MbN
CLAP
Pre
Rec
F1
IPD-22
5033:1647
95.62
95.67
96.0
96.0
96.0
Groundnut-6
7910:2451
95.54
96.85
97.0
97.0
97.0
Cassava-5
5630:940
93.48
94.02
94.0
94.0
94.0
Cashew-5
4906:826
94.11
94.00
94.0
94.0
94.0
Maize-7
3972:663
80.33
82.77
83.0
83.0
83.0
Tomato-5
4338:721
73.61
76.66
77.0
77.0
77.0
TABLE III: Left: Dataset specifications (No. Classes: #C) with train-test sizes. Middle: Overall Accuracy (Acc) of MobileNet(MbN) and CLAP. Right: CLAP’s performances with other metrics (%)
Fig. 4: Confusion matrix of CLAP on the IPD dataset
Class name
Prec
Rec
F1-sc
Prec
Rec
F1-sc
Early leaf spot
100.0
82.0
91.0
100.0
84.0
92.0
Early rust
100.0
100.0
100.0
100.0
90.0
95.0
Healthy leaf
85.0
98.0
91.5
87.0
100.0
93.5
Late leaf spot
100.0
100.0
100.0
99.0
100.0
99.5
Nutrition deficit
100.0
100.0
100.0
100.0
100.0
100.0
Rust
100.0
100.0
100.0
91.0
100.0
95.5
TABLE IV: Performance on Groundnut, left: CLAP; right: MobileNet
Fig. 5: Confusion matrix on Groundnut, left: CLAP, right:MobileNetV2
Fig. 6: Confusion matrix on CCMT (sequence given in Table III) dataset
Fig. 7: Grad-CAM images show vital regions of different infected leaves
Agriculture is a key sector of the economies of developing countries. It serves as a primary source of income and employment for rural populations. However, each year, a large portion of crops is wasted because of pests and diseases. Well-timed prediction of plant diseases is crucial to sustainable, high-quality agricultural production. Detection of plant diseases through conventional methods is both labour-intensive and time-consuming. Researchers have developed image classification based automated techniques for this purpose. Most accurate methods are based on deep convolutional neural networks, which are computationally intensive, with many layers and millions of trainable parameters. In resource-constrained settings, especially in rural areas, it is difficult to deploy deep convolutional neural network models for efficient plant disease identification. To address these issues, an efficient and light-weight Multi-View Convolutional Neural Network is proposed. These additional features aid the proposed model to identify the plant diseases accurately and efficiently with less number of parameters. The proposed model is tested on a benchmark Plantvillage dataset and achieves an improvement of 2.9% in classification accuracy compared to the baseline convolutional neural network model, which was trained only on Red, Green, and Blue (RGB) plant images. Compared with state-of-the-art deep convolutional neural network models, the proposed model is less computationally expensive and achieves comparable accuracy for plant disease identification on the PlantVillage dataset.
Accurate and resource-efficient automated diagnosis is a cornerstone of modern agricultural expert systems. While Convolutional Neural Networks (CNNs) have established benchmarks in plant pathology, their ability to capture long-range spatial dependencies is often limited by standard pooling layers, and their high memory footprint hinders deployment on portable devices. This paper proposes a lightweight hybrid CNN-LSTM system for bean leaf disease classification. By integrating an LSTM layer to model the spatial-sequential relationships within feature maps, our hybrid architecture achieves a 94.38% accuracy while maintaining an exceptionally small footprint of 1.86 MB; a 70% reduction in size compared to traditional CNN-based systems. Furthermore, we provide a systematic evaluation of image augmentation strategies, demonstrating that tailored transformations are superior to generic combinations for maintaining the integrity of diagnostic patterns. Results on the ibean dataset confirm that the proposed system achieves state-of-the-art F1 scores of 99.22% with EfficientNet-B7+LSTM, providing a robust and scalable framework for real-time agricultural decision support in resource-constrained environments. The code and augmented datasets used in this study are publicly available on this Github repo.
Hye Jin Rhee, Joseph Damilola Akinyemi
University of York, Heslington, York, YO10 5DD, United Kingdom
Deep learning has markedly advanced image based plant disease diagnosis as improved hardware and dataset quality have enabled increasingly accurate neural network models. This paper presents PD36 C, a compact convolutional neural network (1,250,694 parameters and 4.77 MB) for plant disease classification. Trained with TensorFlow Keras on the New Plant Diseases Dataset (87k images, 38 classes), PD36 C is designed for robustness and edge deployability, complemented by a Qt for Python desktop application that offers an intuitive GUI and offline inference on commodity hardware. Across experiments, training accuracy reached 0.99697 by epoch 30, and average test accuracy was 0.9953 across 38 classes. Per class performance is uniformly high; on the lower end, Corn (maize) Cercospora leaf spot achieved precision around 0.9777 and recall around 0.9634, indicating occasional confusion with visually similar categories, while on the upper end numerous classes including Apple Black rot, Cedar apple rust, Blueberry healthy, Cherry Powdery mildew, Cherry healthy, and all four grape categories achieved perfect precision 1.00 and recall of 1.00, indicating no false positives and strong coverage. These results show that with a well curated dataset and careful architectural design, small CNNs can achieve competitive accuracy compared with recent baselines while remaining practical for edge scenarios. We also note typical constraints such as adverse weather, low quality imagery, and leaves exhibiting multiple concurrent diseases that can degrade performance and warrant future work on domain robustness. Overall, PD36 C and its application pipeline contribute a field ready, efficient solution for AI assisted plant disease detection in smart agriculture.