No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Enhanced Rendering-Based Approach for Improved Quality of Instance Segmentation in Detecting Green Gram (Vigna Rediata) Pods
Plant disease detection is crucial to modern-day agriculture because timely diagnosis can reduce the loss of crops to an appreciable level and improve productivity. This review presents advanced disease detection systems based on machine learning techniques and multimodal data analysis. A comprehensive comparison of different machine learning algorithms, including convolutional neural networks (CNNs), transfer learning models, and object detection methods like YOLO, has been done. This study demonstrates that combining visual data with the analysis of volatile organic compounds (VOC) enhances the accuracy and reliability of the diagnosis. This provides opportunities for the actual development of satellite and cheap systems for monitoring operable in the field. Theoretically, this work contributes to developing strategies for integrating heterogeneous data and optimizing deep neural network models to make them lightweight and effective. The review emphasizes developing scalable and adaptive technologies for plant disease detection within precision agriculture.
The identification of cucumber fruit is an essential procedure in automated harvesting in greenhouses. In order to enhance the identification ability of object detection models for cucumber fruit harvesting, an extended RGB image dataset (n = 801) with 3943 positive and negative labels was constructed. Firstly, twelve channels in four color spaces (RGB, YCbCr, HIS, La*b*) were compared through the ReliefF method to choose the channel with the highest weight. Secondly, the RGB image dataset was converted to the pseudo-color dataset of the chosen channel (Cr channel) to pre-train the YOLOv5s model before formal training using the RGB image dataset. Based on this method, the YOLOv5s model was enhanced by the Cr channel. The experimental results show that the cucumber fruit recognition precision of the enhanced YOLOv5s model was increased from 83.7% to 85.19%. Compared with the original YOLOv5s model, the average values of AP, F1, recall rate, and mAP were increased by 8.03%, 7%, 8.7%, and 8%, respectively. In order to verify the applicability of the pre-training method, ablation experiments were conducted on SSD, Faster R-CNN, and four YOLOv5 versions (s, l, m, x), resulting in the accuracy increasing by 1.51%, 3.09%, 1.49%, 0.63%, 3.15%, and 2.43%, respectively. The results of this study indicate that the Cr channel pre-training method is promising in enhancing cucumber fruit detection in a near-color background.
Peach diseases seriously affect peach yield and people’s health. The precise identification of peach diseases and the segmentation of the diseased areas can provide the basis for disease control and treatment. However, the complex background and imbalanced samples bring certain challenges to the segmentation and recognition of lesion area, and the hard samples and imbalance samples can lead to a decline in classification of foreground class and background class. In this paper we applied deep network models (Mask R-CNN and Mask Scoring R-CNN) for segmentation and recognition of peach diseases. Mask R-CNN and Mask Scoring R-CNN are classic instance segmentation models. Using instance segmentation model can obtain the disease names, disease location and disease segmentation, and the foreground area is the basic feature for next segmentation. Focal Loss can solve the problems caused by difficult samples and imbalance samples, and was used for this dataset to improve segmentation accuracy. Experimental results show that Mask Scoring R-CNN with Focal Loss function can improve recognition rate and segmentation accuracy comparing to Mask Scoring R-CNN with CE loss or comparing to Mask R-CNN. When ResNet50 is used as the backbone network based on Mask R-CNN, the segmentation accuracy of segm_mAP_50 increased from 0.236 to 0.254. When ResNetx101 is used as the backbone network, the segmentation accuracy of segm_mAP_50 increased from 0.452 to 0.463. In summary, this paper used Focal Loss on Mask R-CNN and Mask Scoring R-CNN to generate better mAP of segmentation and output more detailed information about peach diseases.
Gray mold caused by necrotrophic fungus pathogen (Botrytis cinerea) is a lethal disease, which affects various plants. It is also a common disease in strawberry, limiting the yield. Therefore, the detection and quantification of gray mold disease in the field is indispensable. Most of the deep convolutional neural networks (CNNs) were used for the plant disease identification and classification based on the highest probability value scored by the network. However, pixel-level segmentation allows quantifying the disease severity in the plant, which is crucial to determine the pesticides’ dose. Disease severity is also a useful parameter for monitoring the plant's resistance against a particular disease. Therefore, accurate quantification of plant disease is of utmost necessity in agriculture. In this circumstance, a deep learning-based semantic segmentation model was designed and tested to detect and measure the strawberry plants’ gray mold disease. For this purpose, three concentrations of 1 × 103, 1 × 105, 1 × 107 CFU/mL pathogen were inoculated on each group of 10 strawberry plants, and consequent occurrence of disease and its intensity over time were observed. The model performance was evaluated using pixel accuracy, dice accuracy, and intersection over union (IoU) metrics using fivefold cross-validation method. The results were compared with the results obtained from the XGBoost model, K-means, and Otsu image processing algorithms. The pixel, dice, and IoU accuracies were achieved the highest from the Unet model followed by the XGBoost model on 80 test images. Results showed that the Unet model surpasses the conventional XGBoost, K-means, and image processing technique in detecting and quantifying gray mold disease. Thus, a deep learning Unet can be a nifty tool assisting the farmers and agronomists in disease severity measurement.
Plant diseases must be identified at the earliest stage for pursuing appropriate treatment procedures and reducing economic and quality losses. There is an indispensable need for low-cost and highly accurate approaches for diagnosing plant diseases. Deep neural networks have achieved state-of-the-art performance in numerous aspects of human life including the agriculture sector. The current state of the literature indicates that there are a limited number of datasets available for autonomous strawberry disease and pest detection that allow fine-grained instance segmentation. To this end, we introduce a novel dataset comprised of 2500 images of seven kinds of strawberry diseases, which allows developing deep learning-based autonomous detection systems to segment strawberry diseases under complex background conditions. As a baseline for future works, we propose a model based on the Mask R-CNN architecture that effectively performs instance segmentation for these seven diseases. We use a ResNet backbone along with following a systematic approach to data augmentation that allows for segmentation of the target diseases under complex environmental conditions, achieving a final mean average precision of 82.43%.
Coffee is an important economic crop and one of the most popular beverages worldwide. The rise of speciality coffees has changed people's standards regarding coffee quality. However, green coffee beans are often mixed with impurities and unpleasant beans. Therefore, this study aimed to solve the problem of time‐consuming and labour‐intensive manual selection of coffee beans for speciality coffee products. The second objective of the authors’ study was to develop an automatic coffee bean picking system. They first used image processing and data augmentation technologies to deal with the data. They then used deep learning of the convolutional neural network to analyse the image information. Finally, they applied the training model to connect an IP camera for recognition. They successfully divided good and bad beans. The false‐positive rate was 0.1007, and the overall coffee bean recognition rate was 93%.
The cucumber fruits have the same color with leaves and their shapes are all long and narrow, which is different from other common fruits, such as apples, tomatoes, and strawberries, etc. Therefore, cucumber fruits are more difficult to be detected by machine vision in greenhouses for special color and shape. A pixel-wise instance segmentation method, mask region-based convolutional neural network (Mask RCNN) of an improved version, is proposed to detect cucumber fruits. Resnet-101 is selected as the backbone of Mask RCNN with feature pyramid network (FPN). To improve the detection precision, region proposal network (RPN) in original Mask RCNN is improved. Logical green (LG) operator is designed to filter non-green background and limit the range of anchor boxes. Besides, the scales and aspect ratios of anchor boxes are also adjusted to fit the size and shape of fruits. Improved Mask RCNN has a better performance on test images. The test results are compared with that of original Mask RCNN, Faster RCNN, you only look once (YOLO) V2 and YOLO V3. The F1 score of improved Mask RCNN in test results reaches 89.47%, which is higher than the other methods. The average elapsed time of improved Mask RCNN is 0.3461 s, which is only lower than the original Mask RCNN. Meanwhile, the mean value and standard deviation of location deviation in improved Mask RCNN are 2.10 pixels and 1.73 pixels respectively, which are lower than the other methods.
This study presents an image processing procedure to identify two different classes and types of fruits. The proposed method recognizes fruits by extracting two features (color and shape) based upon the training dataset analysis. In this study, an image processing method has been done using Canny Edge Detection (CED) algorithm to identify and sort the fruits. In addition to that modified Canny Edge Detection (MCED) algorithm is proposed to develop a fruit recognition method using color and shape of the fruits. In this work, only two different types of fruits (i.e. apples and oranges) are chosen for the experiment. At the end of this study, a comparative study has been shown to evaluate the performance of CED algorithm and MCED algorithm based on the training dataset.
It is important to precisely segment apples in an orchard during the growth period to obtain accurate growth information. However, the complex environmental factors and growth characteristics, such as fluctuating illumination, overlapping and occlusion of apples, the gradual change in the ground colour of apples from green to red, and the similarities between immature apples and background leaves, affect apple segmentation accuracy. The purpose of this study was to develop a precise apple instance segmentation method based on an improved Mask region-based convolutional neural network (Mask RCNN). An existing Mask RCNN model was improved by fusing an attention module into the backbone network to enhance its feature extraction ability. A combination of deformable convolution and the transformer attention with the key content only term was used as the attention module in this study. The experimental results showed that the improved Mask RCNN can accurately segment apples under various conditions, such as apples with shadows and different ground colours, overlapped apples, and apples occluded by branches and leaves. A recall, precision, F1 score, and segmentation mAP of 97.1%, 95.8%, 96.4% and 0.917, respectively, were achieved, and the average run-time on the test set was 0.25 s per image. Our method outperformed the two methods in comparison, indicating that it can accurately segment apples in the growth stage with a near real-time performance. This study lays the foundation for realizing accurate fruit detection and long-term automatic growth monitoring.
Agriculture, along with its allied industries, is a vital part of a country’s economy. This sector employs nearly half of the workforce in a country like India. Identifying crop diseases in an accurate and timely manner is the key to preventing qualitative and quantitative loss of agricultural yields by providing the required treatment on time. It is the most effective in reducing economic losses to the fields. Normal human vision would not be sufficient to identify the early symptoms of crop diseases, leading to a delay in treatment and significant yield loss. In this paper, we present an investigation into determining the existence of plant-based pathogens present in the crops using real-life photographs captured and the most efficient ways of detecting them promptly. We tested two CNN models, namely VGG16 and GoogLeNet, for their efficiency in predicting crop diseases. To increase the generalization of our model predictions, we have used various image augmentation techniques to improve our dataset and trained the model to predict infected plants accurately. For more accurate disease prediction, we have also used different edge detection techniques on the input images like Laplacian, Sobel, and Prewitt to improve the image quality.
Crop protection aims to develop an agriculture system that is resilient to common agricultural threats like diseases, pests, and weeds that result in sub-optimal growth of crops in terms of quality and quantity. Therefore, timely disease detection and identification is a crucial concern for farmers across the globe. At present, crop diseases are identified by farmers manually, which is time-consuming, subjective, and also error-prone due to human involvement. The early disease identification and detection would help the farmers reduce the use of pesticides, minimizing the environmental footprint while increasing the profits by reducing the losses. To precisely identify the crop diseases at the initial stages, the machine learning (ML) algorithms or, in more precise, deep learning (DL) algorithms are very helpful. The research aims to develop a deep convolutional neural network (DCNN) model to identify and classify grape diseases based on the RGB leaf images. The proposed model uses an image dataset of grape crops from the Plant Village dataset publicly available for researchers and engineers. The specialty of the developed model is that the CNN classification model is built from scratch that provides accuracy close to or even more significant than the accuracy obtained for some pre-trained models using transfer learning. The model achieved an accuracy of 99.34% and equal values for precision, recall, and an F1 score of 0.9934. These results indicate models’ capability to accurately identify and classify grapes’ common diseases based on the RGB leaf images. The trained model is converted and saved in TensorFlow tflite format, and it can be readily deployed to mobile devices to provide real-time disease identification in precision agriculture (PA) application.
Honey bees are not only the fundamental producers of honey but also the leading pollinators in nature. While honey bees play such a vital role in the ecosystem, they also face a variety of threats, including parasites, ants, hive beetles, and hive robberies, some of which could even lead to the collapse of colonies. Therefore, early and accurate detection of abnormalities at a beehive is crucial to take appropriate countermeasures promptly. In this paper, deep learning-based image classification models are proposed for beehive monitoring. The proposed models particularly classify honey bee images captured at beehives and recognize different conditions, such as healthy bees, pollen-bearing bees, and certain abnormalities, such as Varroa parasites, ant problems, hive robberies, and small hive beetles. The models utilize transfer learning with pre-trained deep neural networks (DNNs) and also a support vector machine classifier with deep features, shallow features, and both deep and shallow features extracted from these DNNs. Three benchmark datasets, consisting of a total of 19,393 honey bee images for different conditions, were used to train and evaluate the models. The results of the extensive experimental work revealed that the proposed models can recognize different conditions as well as abnormalities with an accuracy of up to 99.07% and stand out as good candidates for smart beekeeping and beehive monitoring.
The cultivation of crops, conservation of plants, restoration of landscape, and management of soil are the phases incorporated in agriculture and horticulture. During the cultivation and conservation stages, the plants and the crops are affected by various diseases such as Bacterial scourge, Bacterial Leaf Blight, Brown spot, Seeding blight, Leaf streak, Powdery Mildew, Fire Blight, Black Rot and Apple Scab. These diseases in plants will lead to losses such as manufacturing and financial loss in farming industry worldwide. To maintain the sustainability in horticulture, the detection of crop disease and maintaining the condition of the plants are important. The Computer Aided Detection (CAD) in the agriculture and horticulture is the emerging trend, based on the digital imaging that provides the detailed analysis about the disease by applying the image mining process. In this work, the Cross Central Filter (CCF) technique is proposed to perform the noise removal process in the image and the identification of objects in the image is applied by using the Cognitive Fuzzy C-Means (CFCM) algorithm to differentiate the suspicious region from the normal region. The evaluation is conducted against the diseases affected in the rice crop and apple trees. The performance evaluation proves that the proposed design achieves the best performance results compared to the other filters and the segmentation techniques.
Google Colaboratory more commonly referred to as “Google Colab” or just simply “Colab” is a research project for prototyping machine learning models on powerful hardware options such as GPUs and TPUs. It provides a serverless Jupyter notebook environment for interactive development. Google Colab is free to use like other G Suite products.
In image-based intelligent identification of crop diseases, leaf image segmentation is a key step. Although the K-means is a commonly used algorithm between a number of segmented methods, which needs to set the clustering number in advance, so as to make a manual influence on the image segmentation quality. This paper studies an improved K-means algorithm based on the adaptive clustering number for the segmentation of tomato leaf images. The whole experiment images were acquired from the tomato we grew. The white paper background images were used for designing algorithm and the natural background images were the algorithm validated data. Through a series of pretreatment experiments, the value of the clustering number in this algorithm was automatically determined by calculating the DaviesBouldin index, and the initial clustering center was given to prevent the clustering calculation from falling into a local optimum. Finally, we verified the accuracy of segmentation by two kinds of objective assessment measures, the clustering F1 measure and Entropy. Compared with the traditional K-means algorithm, DBSCAN algorithm, Mean Shift algorithm and ExG-ExR color indices method, the proposed algorithm can successfully segment the tomato leaf images more precisely and efficiently.
Real-time detection of apples in orchards is one of the most important methods for judging growth stages of apples and estimating yield. The size, colour, cluster density, and other growth characteristics of apples change as they grow. Traditional detection methods can only detect apples during a particular growth stage, but these methods cannot be adapted to different growth stages using the same model. We propose an improved YOLO-V3 model for detecting apples during different growth stages in orchards with fluctuating illumination, complex backgrounds, overlapping apples, and branches and leaves. Images of young apples, expanding apples, and ripe apples are initially collected. These images are subsequently augmented using rotation transformation, colour balance transformation, brightness transformation, and blur processing. The augmented images are used to create training sets. The DenseNet method is used to process feature layers with low resolution in the YOLO-V3 network. This effectively enhances feature propagation, promotes feature reuse, and improves network performance. After training the model, the performance of the trained model is tested on a test dataset. The test results show that the proposed YOLOV3-dense model is superior to the original YOLO-V3 model and the Faster R-CNN with VGG16 net model, which is the state-of-art fruit detection model. The average detection time of the model is 0.304s per frame at 3000 × 3000 resolution, which can provide real-time detection of apples in orchards. Moreover, the YOLOV3-dense model can effectively provide apple detection under overlapping apples and occlusion conditions, and can be applied in the actual environment of orchards.
Aims Taxon identification is an important step in many plant ecological studies. Its efficiency and reproducibility might greatly benefit from partly automating this task. Image-based identification systems exist, but mostly rely on hand-crafted algorithms to extract sets of features chosen a priori to identify species of selected taxa. In consequence, such systems are restricted to these taxa and additionally require involving experts that provide taxonomical knowledge for developing such customized systems. The aim of this study was to develop a deep learning system to learn discriminative features from leaf images along with a classifier for species identification of plants. By comparing our results with customized systems like LeafSnap we can show that learning the features by a convolutional neural network (CNN) can provide better feature representation for leaf images compared to hand-crafted features. Methods We developed LeafNet, a CNN-based plant identification system. For evaluation, we utilized the publicly available LeafSnap, Flavia and Foliage datasets. Results Evaluating the recognition accuracies of LeafNet on the LeafSnap, Flavia and Foliage datasets reveals a better performance of LeafNet compared to hand-crafted customized systems. Conclusions Given the overall species diversity of plants, the goal of a complete automatisation of visual plant species identification is unlikely to be met solely by continually gathering assemblies of customized, specialized and hand-crafted (and therefore expensive) identification systems. Deep Learning CNN approaches offer a self-learning state-of-the-art alternative that allows adaption to different taxa just by presenting new training data instead of developing new software systems.
Crop leaf segmentation was one important research content in agricultural machine vision applications. In order to study and solve the segmentation problem of occlusive leaves, an improved watershed algorithm was proposed in this paper. Firstly, the color threshold component (G−R)/(G+R) was used to extract the green component of the cotton leaf image and remove the shadow and invalid background. Then the lifting wavelet algorithm and Canny operator were applied to extract the edge of the pre-processed image to extract cotton leaf region and enhance the leaf edge. Finally, the image of the leaf was labeled with morphological methods to improve the traditional watershed algorithm. By comparing the cotton leaf area segmented using the proposed algorithm with the manually extracted cotton leaf area, successful rates for all the images were higher than 97 %. The results not only demonstrated the effectiveness of the algorithm, but also laid the foundation for the construction of cotton growth monitoring system.
In this paper, we presented two segmentation methods. Edge based and color based detection methods were used to segment images of orange fruits obtained under natural lighting conditions. Twenty digitized images of orange fruits were randomly selected from the Internet in order to find an orange in each image and to determine its location. We compared the results of both segmentation results and the color based segmentation outperforms the edge based segmentation in all aspects. The MATLAB image processing toolbox is used for the computation and comparison results are shown in the segmented image results.
Insects in vegetable soybean undermine the quality and safety of soybean products. Thus, a non-destructive technique of detecting insect-damaged vegetable soybean must be developed. An efficient detection method based on a hyperspectral image was proposed by selecting the region of interest (ROI) through automatic threshold segmentation and optimal wavelength selection using the fuzzy-rough set model. For the 362 samples of beans, three image features (i.e., entropy, energy, and mean) of the ROI were extracted as classification features, whose spectral region covered 400–1000 nm and contained 94 wavelengths. Three or less optimal wavelengths were then selected using a fuzzy-rough set model based on the thermal charge algorithm (FRSTCA). Support vector data description (SVDD) was used to develop classification models for the insect-damaged soybean. For the prediction samples of the beans, the classification results indicated that the normal samples were 100.0% correctly classified using the automatic extracting ROI method based on automatic threshold segmentation. The classification accuracy for the insect-damaged samples was 91.7%, and a 98.8% overall classification accuracy was achieved with the FRSTCA selecting two wavelengths.
PyTorch: an imperative style, high-performance deep learning library
- Paszke