Left Images Research Articles

A Proposal for Lodging Judgment of Rice Based on Binocular Camera

Rice lodging is a crucial problem in rice production. Lodging during growing and harvesting periods can decrease rice yields. Practical lodging judgment for rice can provide effective reference information for yield prediction and harvesting. This article proposes a binocular camera-based lodging judgment method for rice in real-time. As a first step, the binocular camera and Inertial Measurement Unit (IMU) were calibrated. Secondly, Census and Grayscale Level cost features are constructed for stereo matching of left and right images. The Cross-Matching Cost Aggregation method is improved to compute the aggregation space in the LAB color space. Then, the Winner-Takes-All algorithm is applied to determine the optimal disparity for each pixel. A disparity map is constructed, and Multi-Step Disparity Refinement is applied to the disparity map to generate the final one. Finally, coordinate transformation obtains 3D world coordinates corresponding to pixels. IMU calculates the real-time pose of the binocular camera. A pose transformation is applied to the 3D world coordinates of the rice to obtain its 3D world coordinates in the horizontal state of the camera (pitch and roll angles are equal to 0). Based on the distance between the rice and the camera level, thresholding was used to determine whether the region to be detected belonged to lodging rice. The disparity map effect of the proposed matching algorithm was tested on the Middlebury Benchmark v3 dataset. The results show that the proposed algorithm is superior to the widely used Semi-Global Block Matching (SGBM) stereo-matching algorithm. Field images of rice were analyzed for lodging judgments. After the threshold judgment, the lodging region results were accurate and could be used to judge rice lodging. By combining the algorithms with binocular cameras, the research results can provide practical technical support for yield estimation and intelligent control of rice harvesters.

Ensemble of CNN models for classification of groundnut plant leaf disease detection

Plant diseases pose a significant threat to the world's nutrition and can have severe consequences for smallholder farmers who rely on a thriving groundnut crop for their livelihoods. Therefore, it is crucial to create an algorithm for early automated diagnosis of plant diseases. Soa comprehensive dataset of groundnut leaf images was created in collaboration with a pathologist, facilitating the automated identification of plant diseases. The field of image classification has found CNN to be quite effective. In this study, we create such a method for disease identification and classification by utilizing a tri-CNN architecture consisting of DenseNet169, Inception, and Xception —that have been pre-trained on the ImageNet dataset using two created non-linear equations on decision scores from the before mentioned base learners,the outlined ensemble methodology generates ultimate predictions for the test samples by incorporating the scores of four conventional metrics for evaluation, namely recall, precision, accuracy, and f1-score, obtained from the base learners. Hence mentioned CNN customized models are used to train our model for obtaining better results. The proposed approach evaluated on real world groundnut leaf dataset. The model that was put forth attained accuracy rates of 98.46 %.

An Effective Ensemble Convolutional Learning Model with Fine-Tuning for Medicinal Plant Leaf Identification

Accurate and efficient medicinal plant image classification is of utmost importance as these plants produce a wide variety of bioactive compounds that offer therapeutic benefits. With a long history of medicinal plant usage, different parts of plants, such as flowers, leaves, and roots, have been recognized for their medicinal properties and are used for plant identification. However, leaf images are extensively used due to their convenient accessibility and are a major source of information. In recent years, transfer learning and fine-tuning, which use pre-trained deep convolutional networks to extract pertinent features, have emerged as an extremely effective approach for image-identification problems. This study leveraged the power by three-component deep convolutional neural networks, namely VGG16, VGG19, and DenseNet201, to derive features from the input images of the medicinal plant dataset, containing leaf images of 30 classes. The models were compared and ensembled to make four hybrid models to enhance the predictive performance by utilizing the averaging and weighted averaging strategies. Quantitative experiments were carried out to evaluate the models on the Mendeley Medicinal Leaf Dataset. The resultant ensemble of VGG19+DensNet201 with fine-tuning showcased an enhanced capability in identifying medicinal plant images with an improvement of 7.43% and 5.8% compared with VGG19 and VGG16. Furthermore, VGG19+DensNet201 can outperform its standalone counterparts by achieving an accuracy of 99.12% on the test set. A thorough assessment with metrics such as accuracy, recall, precision, and the F1-score firmly established the effectiveness of the ensemble strategy.

Free and open-source software for object detection, size, and colour determination for use in plant phenotyping

BackgroundObject detection, size determination, and colour detection of images are tools commonly used in plant science. Key examples of this include identification of ripening stages of fruit such as tomatoes and the determination of chlorophyll content as an indicator of plant health. While methods exist for determining these important phenotypes, they often require proprietary software or require coding knowledge to adapt existing code.ResultsWe provide a set of free and open-source Python scripts that, without any adaptation, are able to perform background correction and colour correction on images using a ColourChecker chart. Further scripts identify objects, use an object of known size to calibrate for size, and extract the average colour of objects in RGB, Lab, and YUV colour spaces. We use two examples to demonstrate the use of these scripts. We show the consistency of these scripts by imaging in four different lighting conditions, and then we use two examples to show how the scripts can be used. In the first example, we estimate the lycopene content in tomatoes (Solanum lycopersicum) var. Tiny Tim using fruit images and an exponential model to predict lycopene content. We demonstrate that three different cameras (a DSLR camera and two separate mobile phones) are all able to model lycopene content. The models that predict lycopene or chlorophyll need to be adjusted depending on the camera used. In the second example, we estimate the chlorophyll content of basil (Ocimum basilicum) using leaf images and an exponential model to predict chlorophyll content.ConclusionA fast, cheap, non-destructive, and inexpensive method is provided for the determination of the size and colour of plant materials using a rig consisting of a lightbox, camera, and colour checker card and using free and open-source scripts that run in Python 3.8. This method accurately predicted the lycopene content in tomato fruit and the chlorophyll content in basil leaves.

Cost-effective identification of the field maturity of tobacco leaves based on deep semi-supervised active learning and smartphone photograph

As a key technology for tobacco leaf harvesting, automatic identification of the field maturity of tobacco leaves is an important issue in the tobacco industry. For years, researchers have been exploring machine learning methods to perform the identification task, with traditional supervised learning (SL) schemes being studied in depth. However, the actual use of an SL algorithm is always costly and cumbersome, as it requires a large amount of labor and time to collect and label enough tobacco leaf samples. Therefore, a cost-effective algorithm solution is desired by the industry. To this end, we investigate the efficacy and efficiency of semi-supervised learning (SSL) scheme for this task, attempting to significantly reduce the labeling cost and provide a flexible way to control the cost. Considering the advantages of smartphones in terms of availability and economy, we use smartphone photography as an image acquisition tool, thereby building a tobacco leaf maturity dataset containing more than 7000 tobacco leaf images of three field maturity categories (unripe, ripe and overripe) of three stem positions (bottom, middle and top). According to the fact that the maturity of the unripe, ripe and overripe leaves increases sequentially, we propose a maturity structure constraint (MSC) to make the identification model converge to a confident space and be generalizable. Furthermore, we propose a sample selection method based on self-supervised representation learning, which can effectively select high-quality samples for the identification network. Finally, we design an SSL algorithm framework called maturity structure constraint based semi-supervised learning (MSC-SSL) for the identification task. Experimental results show that our SSL framework is capable to significantly reduce the sample usage and improve the identification accuracy. It achieves the accuracies of 91.92% (bottom position/with 33.16% training samples), 87.06% (middle position/with 27.57% training samples) and 87.64% (top position/with 28.02% training samples) when auto stopped, as compared to the SSL benchmarks of 87.37% and 90.40%, 83.53% and 85.10%, 81.65% and 84.64%, respectively. Furthermore, our method can match or exceed the accuracy of the SL scheme using only about 25% of the labeled samples required by the SL scheme.

Effects of an Impaired Fasting Glucose on the Left Atrial Strain Evaluated by Speckle Tracking Echocardiography.

Background and Objectives: Similar to diabetes, the presence of left ventricular (LV) diastolic function (DD) has been reported in various studies which were conducted with people with a diagnosis of an impaired fasting blood glucose (FBG). This study aimed to examine the effects of the fasting blood glucose (FBG) levels on the left atrial strain (LAS) estimated by two-dimensional echocardiography speckle tracking analyses in patients without known diabetes. Material and Methods: The study included 148 participants (74 female and 74 male) without a history of diabetes mellitus or chronic disease. The patients were divided into two groups as follows: individuals with an FBG < 100 mg/dL and those with an FBG between 100 and 125 mg/dL after at least 8 h of overnight fasting. According to these FBG levels, speckle tracking echocardiography (STE) measures were compared. Results: There was a significant decrease in the LA reservoir (52.3 ± 15 vs. 44.5 ± 10.7; p = 0.001) and conduit strain (36.9 ± 11.7 vs. 28.4 ± 9.7; p = 0.001) in the impaired FBG group. When the STE findings of both ventricles were compared, no significant difference was observed between the groups in right and left ventricular strain imaging. Conclusions: In the earliest stage of LVDD, changes in atrial functional parameters become particularly evident. Echocardiographic analyses of these parameters can help to diagnose and determine the degree of LVDD while the morphological parameters are still normal. The addition of LAS imaging to routine transthoracic echocardiography (TTE) studies in patients with an impaired FBG but without a DM diagnosis may be helpful in demonstrating subclinical LVDD or identifying patients at risk for LVDD in this patient group.

Suitability of curvature as a feature for image-based pattern recognition: a case study on leaf image classification based on machine learning

Suitability of curvature as a feature for image-based pattern recognition: a case study on leaf image classification based on machine learning

Position measurement technology of boom-type roadheader based on binocular vision

Positioning of underground mining equipment in coal mines is a primary challenge in the intelligent development of tunnel excavation. Accurate and reliable position measurement plays a crucial role in improving excavation efficiency. However, the stability and accuracy of traditional measurement methods are difficult to guarantee due to factors such as vibration, magnetic interference, and the absence of GPS signals in coal mine environments. To address the problem of unstable measurement of the boom-type roadheader‘s position, this paper proposes a binocular vision-based measurement technique that utilizes four light spots as characteristic points. By processing the target images captured by the binocular camera and combining the minimum bounding rectangle and ellipse fitting of the spot regions, the method successfully obtains the four light spot characteristics. Subsequently, precise matching and stereo distance measurement of the target in the left and right images enable the determination of the boom-type roadheader’s posi-tion information. A positioning platform based on binocular vision is built and experimentally evaluated. The results demonstrate that this method can achieve accurate spot extraction and stable measurement of the machine’s position, even in complex backgrounds such as mixed lighting and low illumination. The planar measurement errors within a distance range of 50 m are all within ±25 mm, which basically meets the required construction precision for tunnel excavation.

Detection of breakage and impurity ratios for raw sugarcane based on estimation model and MDSC-DeepLabv3.

Broken cane and impurities such as top, leaf in harvested raw sugarcane significantly influence the yield of the sugar manufacturing process. It is crucial to determine the breakage and impurity ratios for assessing the quality and price of raw sugarcane in sugar refineries. However, the traditional manual sampling approach for detecting breakage and impurity ratios suffers from subjectivity, low efficiency, and result discrepancies. To address this problem, a novel approach combining an estimation model and semantic segmentation method for breakage and impurity ratios detection was developed. A machine vision-based image acquisition platform was designed, and custom image and mass datasets of cane, broken cane, top, and leaf were created. For cane, broken cane, top, and leaf, normal fitting of mean surface densities based on pixel information and measured mass was conducted. An estimation model for the mass of each class and the breakage and impurity ratios was established using the mean surface density and pixels. Furthermore, the MDSC-DeepLabv3+ model was developed to accurately and efficiently segment pixels of the four classes of objects. This model integrates improved MobileNetv2, atrous spatial pyramid pooling with deepwise separable convolution and strip pooling module, and coordinate attention mechanism to achieve high segmentation accuracy, deployability, and efficiency simultaneously. Experimental results based on the custom image and mass datasets showed that the estimation model achieved high accuracy for breakage and impurity ratios between estimated and measured value with R2 values of 0.976 and 0.968, respectively. MDSC-DeepLabv3+ outperformed the compared models with mPA and mIoU of 97.55% and 94.84%, respectively. Compared to the baseline DeepLabv3+, MDSC-DeepLabv3+ demonstrated significant improvements in mPA and mIoU and reduced Params, FLOPs, and inference time, making it suitable for deployment on edge devices and real-time inference. The average relative errors of breakage and impurity ratios between estimated and measured values were 11.3% and 6.5%, respectively. Overall, this novel approach enables high-precision, efficient, and intelligent detection of breakage and impurity ratios for raw sugarcane.

Abstract 11914: Diagnostic and Prognostic Role of Left Ventricular Strain Imaging in Adults With Coarctation of Aorta

Introduction: The relative diagnostic and prognostic performance of left ventricular global longitudinal strain (LVGLS) as compared to LV ejection fraction (LVEF), and the role of LVGLS for detecting early stages of LV systolic dysfunction in adults with repaired coarctation of aorta (COA) is unknown. Objective: The purpose of this study was to address these knowledge gaps. Methods: Retrospective cohort study of adults with repaired COA that underwent transthoracic echocardiogram (2003-2020). LV systolic function was assessed using LVEF (derived from volumetric analysis) and LVGLS (derived from speckle-tracking echocardiography). Results: Of the 795 patients (age 36±14 years), mean LVEF and LVGLS were 62±11%, and 21±4%, respectively. The prevalence of LV systolic dysfunction was higher when assessed using LVGLS as compared to LVEF (20% versus 6%, p&lt;0.001). Of 795 patients, 94 (12%) patients died, of which 75 (9%) died from cardiovascular causes. LVGLS provided more robust prognostic power in predicting all-cause mortality as compared to LVEF as evidenced by a higher C -statistic (0.743, 95%CI 0.730-0.755 versus 0.782, 95% CI 0.771-0.792, p&lt;0.001). Furthermore, patients with normal LVEF in the setting of reduced LVGLS had a higher risk of all-cause mortality (as compared to patients with normal LVGLS and LVEF) and were at risk for temporal decline in LVEF during follow-up. Conclusions: These findings suggest that the use of LVGLS for risk stratification can help identify high-risk patients, and provide opportunities for interventions, which would, in turn, improve clinical outcomes. Further studies are required to empirically test these postulates.

Diagnostic and Prognostic Role of Left Ventricular Strain Imaging in Adults with Coarctation of aorta

The relative diagnostic and prognostic performance of left ventricular (LV) global longitudinal strain (LVGLS) compared with LV ejection fraction (LVEF) and the role of LVGLS for detecting the early stages of LV systolic dysfunction in adults with repaired coarctation of the aorta are unknown. This study aimed to address these knowledge gaps. We used a retrospective cohort study of adults with repaired coarctation of the aorta who underwent transthoracic echocardiogram (2003 to 2020). LV systolic function was assessed using LVEF (derived from volumetric analysis) and LVGLS (derived from speckle-tracking echocardiography). Of the 795 patients (age 36 ± 14years), the mean LVEF and LVGLS were 62 ± 11% and 21 ± 4%, respectively. The prevalence of LV systolic dysfunction was higher when assessed using LVGLS than using LVEF (20% vs 6%, p <0.001). Of 795 patients, 94 (12%) patients died, of which 75 (9%) died from cardiovascular causes. LVGLS provided more robust prognostic power in predicting the all-cause mortality than LVEF, as evidenced by a higher C-statistic (0.743, 95% confidence interval 0.730 to 0.755 vs 0.782, 95% confidence interval 0.771 to 0.792, p <0.001). Furthermore, patients with normal LVEF in the setting of reduced LVGLS had a higher risk of all-cause mortality (than patients with normal LVGLS and LVEF) and were at risk for a temporal decrease in LVEF during follow-up. These findings suggest that the use of LVGLS for risk stratification can help identify high-risk patients and provide opportunities for interventions, which would, in turn, improve clinical outcomes. Further studies are required to empirically test these postulates.

Artificial Intelligence Framework for Sugarcane Diseases Classification using Convolutional neural Network

In many regions of the world, plant disorders have long been a threat to crop development and agricultural production, negatively affecting the availability of food for people. The best organised sector of agriculture is sugarcane cultivation. It is the first crop that farmers grow because of the ideal conditions for its development. It is closely related to the sugar sector and has a significant impact on the economy of several countries. Of all the crops grown for commercial purposes, sugarcane has the highest production value. In contrast, a different type of diseases can affect the quality and productivity of the crop. Growers can detect some of them by visual inspection of the leaves. Unfortunately, the majority of infections go undetected, causing farmers to suffer significant losses. To reduce the damage caused by an infestation, it is important to determine the type of infestation. So, we proposed a Deep Learning (DL) model that uses images of diseased leaves to train the model to recognise a specific disease affecting the sugarcane plant. In this work, we have used bacterial blight, red rot, red rust and healthy leaf images. The method used two convolutional neural networks to classify the 851 sugarcane leaf images. As a result, Resnet50 achieved the highest accuracy of and 99.70% for binary classification (normal and abnormal images). The trained model achieved its goal by identifying photos of sugarcane and classifying them into classes of healthy and diseased leaves. As a result, this research provides a proposal for using deep learning algorithms to help farmers detect and categorise sugarcane infections. Finally, we have applied an DL visualization technique such as gradient class activation map, occlusion sensitivity, and local interpretable model-agnostic to differentiate and understanding the classification process by highlighting area that is more used for the classification.

Tomato Plant Leaf Disease Detection Using Convolutional Neural Network

Our country is growing country, India is mostly depended on the agriculture field, and Agriculture is pillar of our country’s economy. Because of this India has to improve in agriculture filed, in many of situations’ farmer face difficulties to detect crop disease in a case large area farm, or late in detection of crop disease in such cases farmer lose their all crop and face the huge loss, to avoid this, in agricultural field is detection of plant diseases is very important. And it is very difficult tasks. In regular normal procedure it requires a more time period and trained person to detect accurate plant disease. In this paper, we proposed effective way for plant disease detection using computer science and machine learning model. Disease transmission from unhealthy plant to all other healthy plants in farm is one of the major damages to crop farm. And these diseases spread like forest fire and have the possible to impact the whole operation if not identified in early on. Now Plant disease detection methods helps to identify infected plants in a very early stage and also help us to identify plant disease in a wide range of area of crops in a cost-effective manner. The aim of this project model is to implement machine learning models, in our proposed system we take a plant leaf image on that leaf images we predict the plant disease using Convolution Neural Networks (CNN) model, in that we build a such a model to predict the plant disease with maximum accuracy and it is for plant disease detection for tomato plant. This machine learning model is analyzing different image metrics pixels data to determine the best performance of network. For that dataset were used around 7around 8016 images we going to use to train the model. We going to use 14 layers CNN models to get better accuracy results. Model consist various layers like convolution, pooling, flatten and dense. Early two layers that is preprocessing and augmentation of images Finally, we get the result of which disease that plant have.

Three-dimensional reconstruction of cotton plant with internal canopy occluded structure recovery

The inner leaves of crop canopies are obscured by outer branches and leaves, leading to information loss and observation difficulty of the occluded canopy structure using modern crop monitoring techniques. It has restricted the development of phenotypic analysis and precision agriculture. In this paper, we propose a neural network approach to reconstruct the occluded structure of crop canopies with an RGB-D sensor. Taking the cotton plant as the object of study, we propose a novel Cascade Leaf Segmentation and Completion Network (CLSCN) to reconstruct the occluded leaf images and propose a Fragmental Leaf Point–cloud Reconstruction Algorithm (FLPRA) to complete the missing point clouds. By combining the Instance Segmentation Network (ISN), Generative Adversarial Network (GAN) and Point-cloud Reconstruction Algorithm (PRA), the three-dimensional models of cotton plants with both completed internal and external structures of the canopy are smoothly reconstructed. Firstly, we collect a large number of leaf images and point clouds of cotton plants using an RGB-D sensor with the top view and construct a manually labeled cotton leaf dataset for training and evaluation. Secondly, a network named CLSCN is cascading constructed with an Instance Segmentation Network (ISN) and a Generative Adversarial Network (GAN), and the two parts of CLSCN are separately trained with our constructed dataset to output complete cotton leaves. Thirdly, with the fusion of the completed RGB images output by cascaded network segmentation and the point clouds captured by RGB-D sensor, the proposed FLPRA is used to filter, reconstruct, fuse and register the cotton canopy leaf point clouds, and to obtain the whole cotton canopy point-clouds with inner occluded structure recovery. Finally, the CLSCN and FLPRA are validated using the validation dataset of cotton leaf. The test results indicate that the front-end ISN of the proposed CLSCN can generate high-quality cotton leaf masks, with FID scores less than 35 and mIoU up to 84.65%. Additionally, the back-end GAN of CLSCN can complete the occluded leaves with an accuracy of over 94%. The reconstruction accuracy of the final three-dimensional model of the cotton canopy is as high as 82.70%. Therefore, the proposed neural network and algorithm effectively solve the problem of incomplete canopy point cloud caused by the occlusion of outer leaves and provide an effective way to recover the complete three-dimensional structure of crop canopy with internal occlusion. It is a meaningful theoretical and technical support to realize real-time crop status observation and precise field management in agriculture production.

Abstract 124: Vertebral Artery Web as a Rare Cause of Ischemic Stroke in a young male

Introduction Vertebral artery web has been rarely identified compared to the frequently reported, carotid artery web as etiology of ischemic stroke. Here we present a young patient with symptomatic vertebral artery web. Methods Case Report Results 35‐year‐old male presented with persistent, intermittent, bilateral visual scintillations lasting 30‐60 seconds for one month. Neurological examination positive for bi nasal superior quadrantanopia. Computed tomography (CT) of head showed patchy hypo density in right posterior circulation artery (PCA) territory. Magnetic resonance imaging (MRI) showed restriction diffusion over bilateral PCA territories right greater than left (image A). MR Angiogram head and neck showed abnormal contour within right vertebral artery in V2 segment compatible with dissection (image B). Patient’s hypercoaguable, inflammatory and rheumatological markers were unremarkable. The patient was started on aspirin 81 mg daily and Plavix 75 mg daily for three weeks followed by aspirin monotherapy. Repeat CT angiogram 11 months later still showed right V1/V2 junction irregularity (image C). DSA performed one month later revealed right cervical vertebral artery web with mild stagnation of blood flow (image D). Patient had no recurrence of symptoms and was continued on aspirin. Conclusion Ischemic stroke is rare in young adults. According to recent studies, prevalence of stroke in young adults’ ranges from 10‐15% of entire population stroke burden. Our case describes a young patient with posterior circulation stroke caused by a vertebral artery web which was confirmed with DSA. Vertebral artery web has limited scientific documentation throughout the literature. A literature review performed by B.J.A. Pereira et al. demonstrated that only 7.3% of vessel webs were found in the vertebral artery, compared to 91.66% in the carotid artery (3). Because of this, a review of medical literature showed limited case reports on treatment and surgical options for vertebral webs causing posterior circulation stroke. Lenck et al. first reported 3 patients with vertebral webs diagnosed by DSA and having MRI show ischemic strokes in the vascular territory were treated with endovascular stenting and had no recurrence of an ischemic event (4). A literature review reported by Pereira demonstrated that out of 23 vessel webs, 13 were treated with supportive care (including antiplatelets or anticoagulation), eight were treated with angioplasty and stenting (which included the vertebral artery web case), and two were treated with surgery (3). In other literature, Lizhang et al (2019) diagnosed an incidental vertebral artery web on DSA for anterior circulation TIA and was treated successfully with DAPT therapy and atorvastatin 20 mg (5).

Mobile app-based tomato disease identification with fine-tuned convolutional neural networks

Rapid detection and diagnosis of plant diseases is crucial for healthy crop growth and maintaining harvest quality. Many diseases, such as bacterial spot, late blight, and leaf mould, can affect tomato cultivation. In this paper, a mobile app-based system for intelligent disease detection on tomato leaves is developed using convolutional neural networks (CNNs). The study uses transfer learning approaches to fine-tune well-known CNN architectures like AlexNet, ResNet-50, SqueezeNet-1.1, VGG19, and DenseNet-121 on a dataset made up of images of tomato leaf from the PlantVillage dataset as well as self-captured images. Over 95% accuracy is attained by all trained CNN models, with DenseNet-121 leading the pack with a stellar 99.85%. Consequently, DenseNet-121 is proposed for use with a user-friendly mobile application to detect disease in tomato leaves. A robust user interface in English and two important Indian languages makes this application more accessible to a wider user base.

CUDU-Net: Collaborative up-sampling decoder U-Net for leaf vein segmentation

Leaf vein is a common visual pattern in nature which provides potential clues for species identification, health evaluation, and variety selection of plants. However, as a critical step in leaf vein pattern analysis, segmenting vein from leaf image remains unaddressed due to its hierarchical curvilinear structure and busy background. In this study, we for the first time design a deep model which is tailored to address the segmentation of overall leaf vein structure. The proposed deep model, termed Collaborative Up-sampling Decoder U-Net (CUDU-Net), is an improved U-Net structure consisting of a fine-tuned ResNet extractor and a collaborative up-sampling decoder. The ResNet extractor utilizes residual module to explore high-dimensional features that are representative and abstract in the hidden layers of the network. The core of CUDU-Net is the collaborative up-sampling decoder which utilizes the complementarity of the bilinear-interpolation and deconvolution, to enhance the decoding capability of the model. The bilinear-interpolation can recovery key veins while the deconvolution actively learns to supplement more fine-grained features of the tertiary veins. In addition, we embed the strip pooling in the skip-connection to distill the vein-related semantics for performance boosting. Two leaf vein segmentation datasets, termed SoyVein500 and CottVein20, are built for model validation and generalization ability test. The extensive experimental results show that our proposed CUDU-Net outperforms the state-of-the-art methods in both segmentation accuracy and generalization ability.

Impact of Polluted Soil on Herbivory of Leaves and Pneumatophore Growth of Black Mangroves (Laguncularia racemosa) at Eagle Island, River State, Nigeria

Mangroves are ecosystem along the shoreline of Nigerian coast and area of active oil exploration in Nigeria. This study is on the impact of pollution on herbivory and pneumatophore growth in black mangrove at Eagle Island. Leave herbivory, pneumatophore growth, THC and heavy metal concentration in soil, root and leave were determined. The sample site was divided into: plot A (high muddiness), plot B (low muddiness), plot C (slight muddiness) and Control (little or no pollution). Random sampling was used in obtaining leaves, soil and pneumatophore from each plot. Pneumatophore height was taken with meter rule and the weight with weighing balance. The leaf image was taken using a digital handy scanner and was uploaded in a software called Image J to measure the area consumed. EPA Method 418 was used to test for Total Hydrocarbon Content (THC). Heavy metals (Cadmium, Lead, Zinc) were determined using AAS- Atomic Absorption Spectrometric method. Results revealed that control plot had highest leaf consumption (2.200±0.33cm2) compared to other plots. The heavy metals and THC concentrations in different plant parts (leaves and roots) revealed that THC was high in leaves (250.88±95.33mg/kg), while heavy metals were high in root The pneumatophores were taller and heavier in Plot A compared to Plots B and C. This study shows that pollution affects herbivory and pneumatophores growth in mangroves forest. Mitigation measures should be taken to prevent these pollutants.

Identification of wheat plant disease using hybrid model of pre-processing with CNN

Diagnosis is given top priority in terms of farm resource allocation, because it directly affects the GDP of the country. Crop analysis at an early stage is important for verifying the efficient crop output. Computer vision has a number of intriguing and demanding concerns, including disease detection. After China, India is the world’s second-largest creator of wheat. However, there exist algorithms that can accurately identify the most prevalent illnesses of wheat leaves. To help farmers keep track on a large area of wheat plantation, leaf image and data processing techniques have recently been deployed extensively and in pricey systems. In this study, a hybrid pre-processing practice is used to remove undesired distortions while simultaneously enhancing the images. Fuzzy C-Means (FCM) is used to segment the affected areas from the pre-processed images. The data is then incorporated into a disease classification model using a Convolutional Neural Network (CNN). It was tested using Kaggle data and several metrics to see how efficient the suggested approach was. This study demonstrates that the traditional Long-Short Term Memory (LSTM) technique achieved 91.94% accuracy on the input images, but the hybrid pre-processing model with CNN achieved 95.06 percent accuracy.

Machine Learning and Fuzzy C-Means Clustering for the Identification of Tomato Diseases

Diseases in tomato plants can cause economic losses in the agricultural industry. Identification of tomato plant diseases is important to choosing the right action to control their spread. In this research, we propose an approach to identify tomato plant diseases using a machine learning algorithm and lab colour space-based image segmentation using the fuzzy c-means (FCM) clustering algorithm. The segmentation method aims to separate the infected area, leaf image, and background in the tomato plant image. In the first step, the tomato image is represented in the Lab colour space, which allows for combining information on brightness (L), red-green colour components (a), and yellow-blue colour components (b). Then, the FCM algorithm is applied to segment the image. The segmentation results are then evaluated through an identification process using machine learning techniques such as k-Nearest Neighbors (kNN), Random Forest (RF), Support Vector Machine (SVM), and Naïve Bayes (NB) to measure the level of accuracy. The dataset used in this research is tomato images, which include various plant diseases obtained from the Kaggle dataset. The performance results of the proposed method show that the segmentation approach based on Lab colour space with the FCM clustering algorithm is able to identify infected areas well. The accuracy value of each machine learning method used is kNN of 85.40%, RF of 88.87%, SVM of 80.73%, and NB of 74.60%. The proposed method shows success in accurately identifying types of tomato plant diseases and obtains improvements compared to without using segmentation.