scholarly journals An Image Segmentation Technique -OEM for Plant Leaf Disease

2020 ◽  
Vol 8 (5) ◽  
pp. 2842-2846
Keyword(s):  
Image Segmentation ◽  
Vital Role ◽  
Test Image ◽  
Plant Leaf ◽  
Leaf Disease ◽  
Object Based ◽  
Proposed Model ◽  
The Matrix ◽  
Inhomogeneous Object ◽  
Watershed Method

Image segmentation plays a vital role in identifying plant leaf diseases. Hence it is considered as categorizing of a test image as set of non-continuous regions which are varied according to the features and its characteristics of the image along its properties in terms of homogeneous and computation on the grey level, texture and color component to provide easy image analysis. Familiar existing techniques for leaf disease segmentation use watershed method, thresholding and region based method. One applying these techniques, particular lesion represents a varied shape, texture and Color properties which makes the complex in the segmentation. In addition, these methods face several challenges such as inhomogeneous object detection and fragmentation. To combat those challenges, a segmentation model named as Object Evolution Mapping (OEM) has been proposed in this paper. It is developed for discretized representation of the inhomogeneous object based on the weight probability with specified limits. The disease affected area is considered as object, as affected region may appear in varied shape and texture, the proposed model strongly correlate those changes through error correction process. Furthermore abstraction building has been carried out by the objective function on the matrix for the determine the correlation of the pixel based on the shape and texture interpretation on the image. It extracts the inhomogeneous objects accurately by traversing the horizontally and vertically. Finally changes between the object is computed accurately on the each positions as pipeline procedure. Experimental results show that proposed OEM model provides the good result in terms execution time and accuracy on comparing it with existing approaches

scholarly journals A Deep Learning-Based Approach in Classification and Validation of Tomato Leaf Disease

2021 ◽  
Vol 38 (3) ◽  
pp. 699-709
Author(s):  
Shivali Amit Wagle ◽  
Harikrishnan R
Keyword(s):  
Deep Learning ◽  
Tomato Plant ◽  
Vital Role ◽  
Disease Classification ◽  
Learning Models ◽  
Plant Leaf ◽  
The Past ◽  
Leaf Disease ◽  
Number Of Classes

Deep learning models are playing a vital role in classification goals that can have propitious results. In the past few years, many models are being used for this purpose of plant disease classification. This work has assisted in the process of identification and classification of a plant leaf disease. In this paper, the Tomato plant leaf images are taken from the PlantVillage Database consisting of one healthy and eight disease classes. The disease classes are selected based on the occurrence of the disease in India. The deep learning models of AlexNet, VGG16, GoogLeNet, MobileNetv2, and SqueezeNet are used in this work for the classification of Tomato plant leaf as healthy or diseased and further which disease class it belongs to. The models used here are all the pre-trained models, so transfer learning is used to fit the total number of classes that need to be classified by the network model. VGG16 model outperformed giving 99.17% accuracy compared to AlexNet, GoogLeNet, MobileNetv2, and SqueezeNet. The work concludes with the model’s validation results on the set of images captured at Krishi Vigyan Kendra Narayangaon (KVKN), India.

scholarly journals Computer Vision-based Plant Leaf Disease Recognition using Deep Learning

2020 ◽  
Vol 9 (5) ◽  
pp. 622-626
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Leaf Spot ◽  
Vital Role ◽  
Cercospora Leaf Spot ◽  
Science And Engineering ◽  
Plant Leaf ◽  
Agricultural Improvement ◽  
Leaf Disease ◽  
Learning Techniques

Computer vision-based applications play a vital role in the era of computer science and engineering. Now-a-days peoples are facing different problems in agricultural fields to improve their cultivation. So, a better approach is proposed for plant leaf disease recognition using deep learning techniques for agricultural improvement. This research is very much helpful for the farmers to identify the leaf diseases of a plant. This proposed system has three subsections. One is feature extraction, second is trained networking generation and the third one is classification. This system first takes an image as the input and extracts the features from the image using K-means clustering. Secondly, it generates a trained network using Convolutional Neural Networks (CNNs). Then compare the original leaf image with the generated trained database in the classification section and recognition of the disease of the plant. Different techniques are used in this system for properly recognized the diseases. After analyzed the 3000 trained images, three types of leaf diseases are properly recognized by this system, which are Cercospora Leaf Spot, Mosaic virus, and Alternaria Leaf Spot. The overall accuracy of this system is very good and which is up to 95.26%.

Soil Moisture based Automatic Irrigation System to Improve Water Productivity

2020 ◽  
Vol 7 (04) ◽  
Author(s):  
PRADEEP H K ◽  
JASMA BALASANGAMESHWARA ◽  
K RAJAN ◽  
PRABHUDEV JAGADEESH
Keyword(s):  
Soil Moisture ◽  
Soil Moisture Content ◽  
Irrigation System ◽  
Water Productivity ◽  
Vital Role ◽  
Agricultural Water Management ◽  
Water Management System ◽  
Proposed Model ◽  
Crop Growth Stage ◽  
Experimental Findings

Irrigation automation plays a vital role in agricultural water management system. An efficient automatic irrigation system is crucial to improve crop water productivity. Soil moisture based irrigation is an economical and efficient approach for automation of irrigation system. An experiment was conducted for irrigation automation based on the soil moisture content and crop growth stage. The experimental findings exhibited that, automatic irrigation system based on the proposed model triggers the water supply accurately based on the real-time soil moisture values.

scholarly journals A Semi-Automated Object-Based Gully Networks Detection Using Different Machine Learning Models: A Case Study of Bowen Catchment, Queensland, Australia

Sensors ◽  
2019 ◽  
Vol 19 (22) ◽  
pp. 4893 ◽  
Author(s):  
Hejar Shahabi ◽  
Ben Jarihani ◽  
Sepideh Tavakkoli Piralilou ◽  
David Chittleborough ◽  
Mohammadtaghi Avand ◽  
...  
Keyword(s):  
Machine Learning ◽  
Image Segmentation ◽  
Vegetation Index ◽  
Scale Parameter ◽  
Slope Aspect ◽  
Support Vector ◽  
Topographic Wetness Index ◽  
Slope Length ◽  
Optimal Scale ◽  
Object Based

Gully erosion is a dominant source of sediment and particulates to the Great Barrier Reef (GBR) World Heritage area. We selected the Bowen catchment, a tributary of the Burdekin Basin, as our area of study; the region is associated with a high density of gully networks. We aimed to use a semi-automated object-based gully networks detection process using a combination of multi-source and multi-scale remote sensing and ground-based data. An advanced approach was employed by integrating geographic object-based image analysis (GEOBIA) with current machine learning (ML) models. These included artificial neural networks (ANN), support vector machines (SVM), and random forests (RF), and an ensemble ML model of stacking to deal with the spatial scaling problem in gully networks detection. Spectral indices such as the normalized difference vegetation index (NDVI) and topographic conditioning factors, such as elevation, slope, aspect, topographic wetness index (TWI), slope length (SL), and curvature, were generated from Sentinel 2A images and the ALOS 12-m digital elevation model (DEM), respectively. For image segmentation, the ESP2 tool was used to obtain three optimal scale factors. On using object pureness index (OPI), object matching index (OMI), and object fitness index (OFI), the accuracy of each scale in image segmentation was evaluated. The scale parameter of 45 with OFI of 0.94, which is a combination of OPI and OMI indices, proved to be the optimal scale parameter for image segmentation. Furthermore, segmented objects based on scale 45 were overlaid with 70% and 30% of a prepared gully inventory map to select the ML models’ training and testing objects, respectively. The quantitative accuracy assessment methods of Precision, Recall, and an F1 measure were used to evaluate the model’s performance. Integration of GEOBIA with the stacking model using a scale of 45 resulted in the highest accuracy in detection of gully networks with an F1 measure value of 0.89. Here, we conclude that the adoption of optimal scale object definition in the GEOBIA and application of the ensemble stacking of ML models resulted in higher accuracy in the detection of gully networks.

scholarly journals Image Segmentation and Object-Based Image Analysis for Environmental Monitoring: Recent Areas of Interest, Researchers’ Views on the Future Priorities

2020 ◽  
Vol 12 (11) ◽  
pp. 1772
Author(s):  
Brian Alan Johnson ◽  
Lei Ma
Keyword(s):  
Remote Sensing ◽  
Image Analysis ◽  
Image Segmentation ◽  
Online Survey ◽  
Accuracy Assessment ◽  
Learning Approaches ◽  
Special Issue ◽  
Object Based Image Analysis ◽  
Object Based ◽  
Wide Range

Image segmentation and geographic object-based image analysis (GEOBIA) were proposed around the turn of the century as a means to analyze high-spatial-resolution remote sensing images. Since then, object-based approaches have been used to analyze a wide range of images for numerous applications. In this Editorial, we present some highlights of image segmentation and GEOBIA research from the last two years (2018–2019), including a Special Issue published in the journal Remote Sensing. As a final contribution of this special issue, we have shared the views of 45 other researchers (corresponding authors of published papers on GEOBIA in 2018–2019) on the current state and future priorities of this field, gathered through an online survey. Most researchers surveyed acknowledged that image segmentation/GEOBIA approaches have achieved a high level of maturity, although the need for more free user-friendly software and tools, further automation, better integration with new machine-learning approaches (including deep learning), and more suitable accuracy assessment methods was frequently pointed out.

scholarly journals Plant Leaf Disease Recognition Using Depth-Wise Separable Convolution-Based Models

Symmetry ◽  
2021 ◽  
Vol 13 (3) ◽  
pp. 511
Author(s):  
Syed Mohammad Minhaz Hossain ◽  
Kaushik Deb ◽  
Pranab Kumar Dhar ◽  
Takeshi Koshiba
Keyword(s):  
State Of The Art ◽  
Computational Cost ◽  
Region Of Interest ◽  
Number Of Clusters ◽  
Plant Leaf ◽  
Leaf Disease ◽  
Automatic Initialization ◽  
Adequate Accuracy ◽  
Model Size ◽  
High Computational Cost

Proper plant leaf disease (PLD) detection is challenging in complex backgrounds and under different capture conditions. For this reason, initially, modified adaptive centroid-based segmentation (ACS) is used to trace the proper region of interest (ROI). Automatic initialization of the number of clusters (K) using modified ACS before recognition increases tracing ROI’s scalability even for symmetrical features in various plants. Besides, convolutional neural network (CNN)-based PLD recognition models achieve adequate accuracy to some extent. However, memory requirements (large-scaled parameters) and the high computational cost of CNN-based PLD models are burning issues for the memory restricted mobile and IoT-based devices. Therefore, after tracing ROIs, three proposed depth-wise separable convolutional PLD (DSCPLD) models, such as segmented modified DSCPLD (S-modified MobileNet), segmented reduced DSCPLD (S-reduced MobileNet), and segmented extended DSCPLD (S-extended MobileNet), are utilized to represent the constructive trade-off among accuracy, model size, and computational latency. Moreover, we have compared our proposed DSCPLD recognition models with state-of-the-art models, such as MobileNet, VGG16, VGG19, and AlexNet. Among segmented-based DSCPLD models, S-modified MobileNet achieves the best accuracy of 99.55% and F1-sore of 97.07%. Besides, we have simulated our DSCPLD models using both full plant leaf images and segmented plant leaf images and conclude that, after using modified ACS, all models increase their accuracy and F1-score. Furthermore, a new plant leaf dataset containing 6580 images of eight plants was used to experiment with several depth-wise separable convolution models.

Sign in / Sign up

Export Citation Format

Share Document