Vijaya Musande

Bio: Vijaya Musande is an academic researcher from Jawaharlal Nehru Engineering College. The author has contributed to research in topics: Normalized Difference Vegetation Index & Feature extraction. The author has an hindex of 6, co-authored 20 publications receiving 88 citations. Previous affiliations of Vijaya Musande include Dr. Babasaheb Ambedkar Marathwada University & North Eastern Hill University.

Evaluation of Deep Learning CNN Model for Land Use Land Cover Classification and Crop Identification Using Hyperspectral Remote Sensing Images

Abstract: Deep learning convolutional neural network (CNN) is popular as being widely used for classification of unstructured data. Land use land cover (LULC) classification using remote sensing data can be used for crop identification also. Present study aims to examine the use of deep learning CNN for LULC classification on Indian Pines dataset and for crop identification on our study area dataset. In the present work, AVIRIS sensor’s Indian Pines standard dataset has been used for LULC classification. Study area from Phulambri, Aurangabad, MH, India, has been used for crop classification. Data have been gathered from EO-1 Hyperion sensor. The accuracy of CNN model depends on optimizer, activation function, filter size, learning rate and batch size. Deep learning CNN is evaluated by changing these parameters. It has been observed that deep learning CNN using optimized combination of parameters has provided 97.58% accuracy for the Indian Pines dataset, while 79.43% accuracy for our study area dataset. The empirical results demonstrate that CNN works well in practice for unstructured data as well as for small size dataset.

Wheat disease detection using image processing

Abstract: The most important factor in reduction of quality and quantity of crop is due to plant disease. Identifying plant disease is a key to prevent agricultural losses. The aim of this paper is to develop a software solution which automatically detect and classify plant disease. It includes four steps, first step image acquisition, second step is image preprocessing, third step is image segmentation and fourth step is feature extraction which consider color, shape and size. For classification we used here Neural Network based classifier.

Cotton Crop Discrimination Using Fuzzy Classification Approach

Abstract: Crop growth information represented through temporal remote sensing data is of great importance for specific agriculture crop discrimination. In this paper, the effect of various indices was empirically investigated using temporal images for cotton crop discrimination. Five spectral indices SR (Simple Ratio), NDVI (Normalized Difference Vegetation index), TNDVI (Transformed Normalized Difference Vegetation Index), SAVI (Soil-Adjusted Vegetation Index) and TVI (Triangular Vegetation Index) were investigated to identify cotton crop using temporal multi-spectral images. Data used for this study was AWIFS (coarser resolution) for soft classification and LISS-III (medium coarser) data for soft testing from Resourcesat-1 (IRS-P6) satellite. The mixed pixel (i.e. multiple classes within a single pixel) problem had been handled using soft computing techniques. Possibilistic fuzzy classification approach is used to handle mixed pixels for extracting single class of interest. The classification results with respect to various indices were compared in terms of image to image fuzzy overall classification accuracy. It was observed that temporal SAVI indices database with data set-2 outperformed other temporal indices database for cotton crop discrimination. Temporal SAVI indices database gave highest fuzzy overall accuracy of 93.12% with data set-2 in comparison to others.

Evaluation of CNN model by comparing with convolutional autoencoder and deep neural network for crop classification on hyperspectral imagery

Abstract: Identification of crops is an important topic in the agricultural domain. Hyperspectral remote sensing data are very useful for crop feature extraction and classification. Remote sensing data is an...

Document management system: A notion towards paperless office

Abstract: Paperless Document Management System is used to eliminate the losses that businesses suffer because of physical paper files and filing systems. This Paper addresses some of the technologies that are helping professionals shift toward a paperless business world. A DMS based on organizing digital documents to search and store documents and to reduce paper. Most of the workplace consists a variety of documents having a mixture of handwritten and printed text. The detection of such documents is a crucial task for OCR developers. This paper describes different steps for processing different documents using scanning, tagging, and indexing for effective data retrieval with OCR and Indexing techniques.

Land-Use and Land-Cover Classification Using a Human Group-Based Particle Swarm Optimization Algorithm with an LSTM Classifier on Hybrid Pre-Processing Remote-Sensing Images

Abstract: Land-use and land-cover (LULC) classification using remote sensing imagery plays a vital role in many environment modeling and land-use inventories. In this study, a hybrid feature optimization algorithm along with a deep learning classifier is proposed to improve the performance of LULC classification, helping to predict wildlife habitat, deteriorating environmental quality, haphazard elements, etc. LULC classification is assessed using Sat 4, Sat 6 and Eurosat datasets. After the selection of remote-sensing images, normalization and histogram equalization methods are used to improve the quality of the images. Then, a hybrid optimization is accomplished by using the local Gabor binary pattern histogram sequence (LGBPHS), the histogram of oriented gradient (HOG) and Haralick texture features, for the feature extraction from the selected images. The benefits of this hybrid optimization are a high discriminative power and invariance to color and grayscale images. Next, a human group-based particle swarm optimization (PSO) algorithm is applied to select the optimal features, whose benefits are a fast convergence rate and ease of implementation. After selecting the optimal feature values, a long short-term memory (LSTM) network is utilized to classify the LULC classes. Experimental results showed that the human group-based PSO algorithm with a LSTM classifier effectively well differentiates the LULC classes in terms of classification accuracy, recall and precision. A maximum improvement of 6.03% on Sat 4 and 7.17% on Sat 6 in LULC classification is reached when the proposed human group-based PSO with LSTM is compared to individual LSTM, PSO with LSTM, and Human Group Optimization (HGO) with LSTM. Moreover, an improvement of 2.56% in accuracy is achieved, compared to the existing models, GoogleNet, Visual Geometric Group (VGG), AlexNet, ConvNet, when the proposed method is applied.

A review of imaging techniques for plant disease detection

Abstract: Agriculture is the basis of every economy worldwide. Crop production is one of the major factors affecting domestic market condition in any country. Agricultural production is also a major prerequisite of economic development, be it any part of any country. It plays a crucial role as it even provides raw material, employment and food to different citizens. A lot of issues are responsible for estimated crop production varying in different parts of the world. Some of these include overutilization of chemical fertilizers, presence of chemicals in water supply, uneven distribution of rainfall, different soil fertility and others. Other than these issues one of the commonly faced challenges across the globe equally includes destruction of the major part of production due to diseases. After providing effective resources to the fields, major section of the production is diminished by the presence of diseases in the plants grown. This leads to focus on effective ways of detection of disease in plants. Presence of various diseases in plant is a major concern among farmers. Plant diseases acts as a major threat to small scale farmers as they lead to major destruction in overall food supply. To provide effective measures for detection and avoidance of the destruction requires an early identification of type of plant disease present. In recent time major work is being done for the identification of plant disease presents in varied parts of the world affection varied crops. Major work is being done in the domain of identification of causing factors of these diseases. Some of the diseases are marked by the presence of viruses while some are resultant of fungal infection. This becomes a major issue when the causing factor is not traceable before it has already spread to major production section. This paper brings a review on effective use of different imaging techniques and computer vision approaches for the identification and classification of plant diseases. Detection of Plant disease is initiated with image acquisition followed by pre-processing while using the process of segmentation. It is further accompanied by different techniques used for feature extraction along with classification. In this Paper we present the Current Trends and Challenges for detection of plant disease using computer vision and advance imaging technique.

Applications of Computer Vision in Plant Pathology: A Survey

Abstract: The real-time decision support system can enhance the crop or plant growth, therefore, increasing their productivity, quality, and economic value. This also helps us in serving the nature by supervising the plant growth in balancing the environment. Computer vision techniques have proven to play an important role in the number of applications like medical, defense, agriculture, remote sensing, business analysis, etc. The use of digital image processing methods for simulating the visual capability of the human being has proven to be a dynamic feature in smart or precision agriculture. This concept has provided with the automatic preventing and monitoring of plants, cultivation, disease management, water management etc. to increase the crop productivity and quality. In this paper, we have surveyed the number of articles that adopt the concept of computer vision and soft computing methods for the identification and classification of diseases from the leaf of the plant. Our aim is to present the state of the art of the concepts, applications, and theories associated with the digital image processing and soft computing methodologies. The various outcomes have been discussed separately.