Multi-Level Deep Learning Model for Potato Leaf Disease Recognition

Rashid, Javed; Khan, Imran; Ali, Ghulam; Almotiri, Sultan H.; Alghamdi, Mohammed A.; Masood, Khalid

doi:10.3390/electronics10172064

Cited by 126 publications

(46 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, the shortcomings of the PlantVillage dataset were verified, and the PBD-IM dataset was established by data enhancement. By comparing the methods proposed by other researchers in Table 5 , the accuracy rate of the model in this study is 0.06% and 5.81% higher than the models proposed by Rashid et al [ 34 ] and Afzaal et al [ 35 ], respectively. In terms of data enhancement, Chen et al [ 37 ] used a generative adversarial network (GAN) to automatically synthesize diverse images with a 2.08% lower accuracy rate than the generic data enhancement and weather data enhancement methods proposed in this study.…”

Section: Experimental Results and Analysismentioning

confidence: 53%

“…Table 5 reviews the work related to this study. Most of the image data used to detect potatoes' early and late blight came from the PlantVillage dataset, while Rashid et al [ 34 ] and Afzaal et al [ 35 ] established their datasets. In this study, the shortcomings of the PlantVillage dataset were verified, and the PBD-IM dataset was established by data enhancement.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

See 1 more Smart Citation

DA-ActNN-YOLOV5: Hybrid YOLO v5 Model with Data Augmentation and Activation of Compression Mechanism for Potato Disease Identification

Dai

Fan

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

To solve the problems of weak generalization of potato early and late blight recognition models in real complex scenarios, susceptibility to interference from crop varieties, colour characteristics, leaf spot shapes, disease cycles and environmental factors, and strong dependence on storage and computational resources, an improved YOLO v5 model (DA-ActNN-YOLOV5) is proposed to study potato diseases of different cycles in multiple regional scenarios. Thirteen data augmentation techniques were used to expand the data to improve model generalization and prevent overfitting; potato leaves were extracted by YOLO v5 image segmentation and labelled with LabelMe for building data samples; the component modules of the YOLO v5 network were replaced using model compression technology (ActNN) for potato disease detection when the device is low on memory. Based on this, the features extracted from all network layers are visualized, and the extraction of features from each network layer can be distinguished, from which an understanding of the feature learning behavior of the deep model can be obtained. The results show that in the scenario of multiple complex factors interacting, the identification accuracy of early and late potato blight in this study reached 99.81%. The introduced data augmentation technique improved the average accuracy by 9.22%. Compared with the uncompressed YOLO v5 model, the integrated ActNN runs more efficiently, the accuracy loss due to compressed parameters is less than 0.65%, and the time consumption does not exceed 30 min, which saves a lot of computational cost and time. In summary, this research method can accurately identify potato early and late blight in various scenarios.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 53%

Section: Experimental Results and Analysismentioning

confidence: 99%

DA-ActNN-YOLOV5: Hybrid YOLO v5 Model with Data Augmentation and Activation of Compression Mechanism for Potato Disease Identification

Dai

Fan

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…The results of this study were compared with the results of other studies shown in Table 7 . Rashid et al ( 2021 ) and Mathew and Mahesh ( 2022 ) used the same dataset as this study. The accuracy of all these studies is lower than the model presented in this article.…”

Section: Resultsmentioning

confidence: 99%

“…To demonstrate the feasibility of deep learning algorithms based on an encoder-decoder architecture for semantic segmentation of potato late blight spots based on field images, Gao et al ( 2021 ) used a SegNet-based encoder-decoder neural network architecture for lesion segmentation, which can extract semantic features from low to high level, in a disease test dataset with leaves and soil in the background to intersect and union (IOU) values of 0.996 and 0.386, respectively. Rashid et al ( 2021 ) proposed a multilevel deep learning model to classify potato leaf diseases called PDDCNN. First, potato leaves were extracted using the YOLOV5 image segmentation technique from potato plant images.…”

Section: Introductionmentioning

confidence: 99%

An Industrial-Grade Solution for Crop Disease Image Detection Tasks

Dai

Fan

2022

Front. Plant Sci.

View full text Add to dashboard Cite

Crop leaf diseases can reflect the current health status of the crop, and the rapid and automatic detection of field diseases has become one of the difficulties in the process of industrialization of agriculture. In the widespread application of various machine learning techniques, recognition time consumption and accuracy remain the main challenges in moving agriculture toward industrialization. This article proposes a novel network architecture called YOLO V5-CAcT to identify crop diseases. The fast and efficient lightweight YOLO V5 is chosen as the base network. Repeated Augmentation, FocalLoss, and SmoothBCE strategies improve the model robustness and combat the positive and negative sample ratio imbalance problem. Early Stopping is used to improve the convergence of the model. We use two technical routes of model pruning, knowledge distillation and memory activation parameter compression ActNN for model training and identification under different hardware conditions. Finally, we use simplified operators with INT8 quantization for further optimization and deployment in the deep learning inference platform NCNN to form an industrial-grade solution. In addition, some samples from the Plant Village and AI Challenger datasets were applied to build our dataset. The average recognition accuracy of 94.24% was achieved in images of 59 crop disease categories for 10 crop species, with an average inference time of 1.563 ms per sample and model size of only 2 MB, reducing the model size by 88% and the inference time by 72% compared with the original model, with significant performance advantages. Therefore, this study can provide a solid theoretical basis for solving the common problems in current agricultural disease image detection. At the same time, the advantages in terms of accuracy and computational cost can meet the needs of agricultural industrialization.

show abstract

“…Examples of the one-stage detector are SSD [ 17 ], YOLO [ 18 ], and CenterNet [ 19 ]. These one-stage detectors are not only able to reach high accuracies, but also have a faster processing speed [ 12 ], making them notable in the field of agriculture, where plant images are collected and utilized to classify plant species [ 20 , 21 , 22 ], count plants or fruits [ 23 , 24 ], identify pests [ 25 , 26 , 27 ] and weeds [ 28 , 29 ], and detect diseases [ 26 , 27 , 30 , 31 , 32 , 33 , 34 ].…”

Section: Related Workmentioning

confidence: 99%

Detection of Tip-Burn Stress on Lettuce Grown in an Indoor Environment Using Deep Learning Algorithms

Hamidon

Ahamed

2022

Sensors

View full text Add to dashboard Cite

Lettuce grown in indoor farms under fully artificial light is susceptible to a physiological disorder known as tip-burn. A vital factor that controls plant growth in indoor farms is the ability to adjust the growing environment to promote faster crop growth. However, this rapid growth process exacerbates the tip-burn problem, especially for lettuce. This paper presents an automated detection of tip-burn lettuce grown indoors using a deep-learning algorithm based on a one-stage object detector. The tip-burn lettuce images were captured under various light and indoor background conditions (under white, red, and blue LEDs). After augmentation, a total of 2333 images were generated and used for training using three different one-stage detectors, namely, CenterNet, YOLOv4, and YOLOv5. In the training dataset, all the models exhibited a mean average precision (mAP) greater than 80% except for YOLOv4. The most accurate model for detecting tip-burns was YOLOv5, which had the highest mAP of 82.8%. The performance of the trained models was also evaluated on the images taken under different indoor farm light settings, including white, red, and blue LEDs. Again, YOLOv5 was significantly better than CenterNet and YOLOv4. Therefore, detecting tip-burn on lettuce grown in indoor farms under different lighting conditions can be recognized by using deep-learning algorithms with a reliable overall accuracy. Early detection of tip-burn can help growers readjust the lighting and controlled environment parameters to increase the freshness of lettuce grown in plant factories.

show abstract

Multi-Level Deep Learning Model for Potato Leaf Disease Recognition

Cited by 126 publications

References 45 publications

DA-ActNN-YOLOV5: Hybrid YOLO v5 Model with Data Augmentation and Activation of Compression Mechanism for Potato Disease Identification

DA-ActNN-YOLOV5: Hybrid YOLO v5 Model with Data Augmentation and Activation of Compression Mechanism for Potato Disease Identification

An Industrial-Grade Solution for Crop Disease Image Detection Tasks

Detection of Tip-Burn Stress on Lettuce Grown in an Indoor Environment Using Deep Learning Algorithms

Contact Info

Product

Resources

About