Hyperspectral image (HSI) classification is a most challenging task in hyperspectral remote sensing field due to unique characteristics of HSI data. It consists of huge number of bands with strong ...

Analysis of various optimizers on deep convolutional neural network model in the application of hyperspectral remote sensing image classification

Plant diseases are a principal threat to the safety of food. In agriculture sectors, it is the greatest challenge to identify plant diseases. The state-of-the-art Convolutional Neural Network (CNN) gives excellent results to solve image classification tasks in computer vision. Transfer Learning enables us to develop a deep CNN network in a most cost effective way. In this work, a Transfer Learning based CNN model was developed for the identification of plant diseases precisely. The dataset, we have used is consists of 70295 training images and 17572 validation images holding 38 different classes of plant leaves images. We have focused mainly on ResNet50 network, a popular CNN architecture as our pre-trained model in Transfer Learning. Additionally, several Transfer Learning architectures were experimented with few other popular pre-trained models (VGG16, VGG19, AlexNet) and compared with the proposed model. The proposed model has given the best performance of 99.80 % training accuracy.

Transfer Learning Based Plant Diseases Detection Using ResNet50

Alzheimer’s Disease (AD) is the most common cause of dementia globally. It steadily worsens from mild to severe, impairing one’s ability to complete any work without assistance. It begins to outstrip due to the population ages and diagnosis timeline. For classifying cases, existing approaches incorporate medical history, neuropsychological testing, and Magnetic Resonance Imaging (MRI), but efficient procedures remain inconsistent due to lack of sensitivity and precision. The Convolutional Neural Network (CNN) is utilized to create a framework that can be used to detect specific Alzheimer’s disease characteristics from MRI images. By considering four stages of dementia and conducting a particular diagnosis, the proposed model generates high-resolution disease probability maps from the local brain structure to a multilayer perceptron and provides accurate, intuitive visualizations of individual Alzheimer’s disease risk. To avoid the problem of class imbalance, the samples should be evenly distributed among the classes. The obtained MRI image dataset from Kaggle has a major class imbalance problem. A DEMentia NETwork (DEMNET) is proposed to detect the dementia stages from MRI. The DEMNET achieves an accuracy of 95.23%, Area Under Curve (AUC) of 97% and Cohen’s Kappa value of 0.93 from the Kaggle dataset, which is superior to existing methods. We also used the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset to predict AD classes in order to assess the efficacy of the proposed model.

/pdf/demnet-a-deep-learning-model-for-early-diagnosis-of-46kt1xnwz3.pdf

DEMNET: A Deep Learning Model for Early Diagnosis of Alzheimer Diseases and Dementia From MR Images

The high mortality rate associated with brain tumors requires early detection in the early stages to treat and reduce mortality. Due to the complexity of brain tissue, manual diagnosis of the brain and tumor tissues is very time‐consuming and operator dependent. Furthermore, there is a need for experts who can review the images to detect these effects, rendering traditional methods inefficient in their presence. Therefore, the use of automated procedures for the careful examination of tumors can prove useful. In this study, a new metaheuristic‐based system is presented for the early detection of brain tumors. The proposed method implements three main steps, namely tumor segmentation, feature extraction, and classification based on a deep belief network. An improved version of the seagull optimization algorithm is adopted for optimal selection of the features and classification of the images. The simulation results of the proposed method are compared with a few existing methods. The final results demonstrate that the proposed method exhibits superior performance in terms of the CDR, FAR, and FRR indices compared with the other methods.

Brain tumor diagnosis based on metaheuristics and deep learning

New brain tumor classification method based on an improved version of whale optimization algorithm

In this era of fast growing technologies, there is a huge demand among the people for a secure lifestyle and travelling. In the past decade, the number of vehicles on road has been increased. Tracking of individual vehicle becomes a very challenging task with the massive growth in the vehicular sector every day. This paper suggests an automated vehicle tracking system for the fast moving vehicles with the help of the surveillance cameras on the roadside. The process of getting CCTV footage in the real time background is very tedious process. To cater to this problem, an efficient deep learning model such as You Only Look Once (YOLO) is used for object detection. The proposed work consists of four main steps. In the first step, video footage is converted into images and the car is detected from each of the frames. In the next step, license plate is detected from the detected cars. In the final step, the number plate characters reading are recognized from the detected number plates. The proposed deep learning model uses ImageAI library to make the training process easier. Tamil Nadu license plate images are used to analyse the performance of the model. The accuracy of 97% is achieved for car detection, accuracy of 98% is achieved for number plate localization and accuracy of 90% achieved for character recognition.

https://iopscience.iop.org/article/10.1088/1757-899X/1084/1/012027/pdf

Automatic number plate recognition using deep learning

In the current scenario, the human population is getting increased exponentially still the cultivation land available for farming remains the same, compelling agriculturists to exhibit new methodologies that increase the yield of crops to feed the growing population. In this regard, maintaining the health of crops is very crucial. So, the early identification of disease in plants is very important to detect the disease and increase the yield. This work explores a computer vision techniques called CNN to identify black rot, measles and blight in grape plants. Three different CNN architectures are compared for this task. The performance of three different CNN architectures are measured with three different optimizers for disease classifying application.

Performance Analysis of Different CNN Architecture with Different Optimisers for Plant Disease Classification

Diagnosing the brain tumor from Magnetic Resonance Imaging (MRI) in Computer-Aided Diagnosis (CAD) applications is one of the challenging task in medical image processing. Traditionally many segmentation methods are used to address this issue. This paper introduces a segmentation method along with image fusion. Here a Discrete Wavelet Transform (DWT) method is chosen, for image fusion followed by segmentation using Support Vector Machine (SVM) for detecting the abnormality region. The types of MRI images considered here include T1-weighted (T1-w), T2-weighted (T2-w) and FLAIR images. The various fusion combinations are T1-w and T2-w, T1-w and FLAIR, T2-w and FLAIR. Experimental results suggest that on an average, fusion-based segmented result is superior to non-fusion-based segmented result.

Fusion-Based Segmentation Technique for Improving the Diagnosis of MRI Brain Tumor in CAD Applications

Fault identification of Fabrics is an important job in regular inspection method in fabric industry. Fault identification systems include three phases. In an early stage image preprocessing has been carried by using Butterworth Low pass Filter to remove the hairiness noise in an image. Beside with perform Equalization to adjust pixel intensities to enhance contrast. After completion of preprocessing, Haralick defined texture attributes are obtained from the preprocessed data with the help of Gray Level Co-occurrence Matrix (GLCM). The Gray level spatial dependency matrix characterizes the allocation of co-occurring pixels in an image data at a given distance, position angle between pair of pixels. Then extracted features are used to train neural network classifier to identify the fabric defect using Back Propagation technique along with gradient descent learning algorithm. The performance of the Network is analyzed through different learning rate of the learning algorithm.

V Gnanaprakash

Papers

Automatic number plate recognition using deep learning

Performance Analysis of Different CNN Architecture with Different Optimisers for Plant Disease Classification

Fusion-Based Segmentation Technique for Improving the Diagnosis of MRI Brain Tumor in CAD Applications

Fault identification in woven fabric using Back propagation neural network