DUICM Deep Underwater Image Classification Mobdel using Convolutional Neural Networks

2020 ◽  
Vol 12 (3) ◽  
pp. 88-100
Author(s):  
Manimaran Aridoss ◽  
Chandramohan Dhasarathan ◽  
Ankur Dumka ◽  
Jayakumar Loganathan
Keyword(s):  
Neural Network ◽  
Image Classification ◽  
Light Propagation ◽  
Learning Algorithm ◽  
Activation Function ◽  
Classification Model ◽  
Low Contrast ◽  
Underwater Image ◽  
Operating Environments ◽  
Absorption And Dispersion

Classification of underwater images is a challenging task due to wavelength-dependent light propagation, absorption, and dispersion distort the visibility of images, which produces low contrast and degraded images in difficult operating environments. Deep learning algorithms are suitable to classify the turbid images, for that softmax activation function used for classification and minimize cross-entropy loss. The proposed deep underwater image classification model (DUICM) uses a convolutional neural network (CNN), a machine learning algorithm, for automatic underwater image classification. It helps to train the image and apply the classification techniques to categorise the turbid images for the selected features from the Benchmark Turbid Image Dataset. The proposed system was trained with several underwater images based on CNN models, which are independent to each sort of underwater image formation. Experimental results show that DUICM provides better classification accuracy against turbid underwater images. The proposed neural network model is validated using turbid images with different characteristics to prove the generalization capabilities.

scholarly journals Bare Skin Image Classification using Convolution Neural Network

2022 ◽  
Vol 12 (1) ◽  
pp. 138-145
Author(s):  
Jaya Gupta ◽  
◽  
Sunil Pathak ◽  
Gireesh Kumar
Keyword(s):  
Neural Network ◽  
Image Classification ◽  
Satellite Image ◽  
Activation Function ◽  
Convolution Neural Network ◽  
Classification Model ◽  
Significant Research ◽  
Research Problems ◽  
Facial Expression Classification ◽  
Expression Classification

Image classification is critical and significant research problems in computer vision applications such as facial expression classification, satellite image classification, and plant classification based on images. Here in the paper, the image classification model is applied for identifying the display of daunting pictures on the internet. The proposed model uses Convolution neural network to identify these images and filter them through different blocks of the network, so that it can be classified accurately. The model will work as an extension to the web browser and will work on all websites when activated. The extension will be blurring the images and deactivating the links on web pages. This means that it will scan the entire web page and find all the daunting images present on that page. Then we will blur those images before they are loaded and the children could see them. Keywords— Activation Function, CNN, Images Classification , Optimizers, VGG-19

scholarly journals Role of Restored Underwater Images in Underwater Imaging Applications

2021 ◽  
Vol 4 (4) ◽  
pp. 96
Author(s):  
Jarina Raihan A ◽  
Pg Emeroylariffion Abas ◽  
Liyanage C De Silva
Keyword(s):  
Machine Learning ◽  
Image Classification ◽  
Feature Detection ◽  
Sea Water ◽  
Learning Algorithm ◽  
Underwater Imaging ◽  
Underwater Image ◽  
Common Problems ◽  
Restoration Method

Underwater images are extremely sensitive to distortion occurring in an aquatic underwater environment, with absorption, scattering, polarization, diffraction and low natural light penetration representing common problems caused by sea water. Because of these degradation of quality, effectiveness of the acquired images for underwater applications may be limited. An effective method of restoring underwater images has been demonstrated, by considering the wavelengths of red, blue, and green lights, attenuation and backscattering coefficients. The results from the underwater restoration method have been applied to various underwater applications; particularly, edge detection, Speeded Up Robust Feature detection, and image classification that uses machine learning. It has been shown that more edges and more SURF points can be detected as a result of using the method. Applying the method to restore underwater images in image classification tasks on underwater image datasets gives accuracy of up to 89% using a simple machine-learning algorithm. These results are significant as it demonstrates that the restoration method can be implemented on underwater system for various purposes.

Signal processing algorithm for neural networks with integrodifferential splines as an activation function and its particular case of image classification

2021 ◽  
Author(s):  
T.K. Biryukova
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Image Classification ◽  
Activation Function ◽  
Experimental Comparison ◽  
Training Time ◽  
Operation Speed ◽  
The Neural Network ◽  
Linear Algebraic Equations ◽  
Network Operation

Classic neural networks suppose trainable parameters to include just weights of neurons. This paper proposes parabolic integrodifferential splines (ID-splines), developed by author, as a new kind of activation function (AF) for neural networks, where ID-splines coefficients are also trainable parameters. Parameters of ID-spline AF together with weights of neurons are vary during the training in order to minimize the loss function thus reducing the training time and increasing the operation speed of the neural network. The newly developed algorithm enables software implementation of the ID-spline AF as a tool for neural networks construction, training and operation. It is proposed to use the same ID-spline AF for neurons in the same layer, but different for different layers. In this case, the parameters of the ID-spline AF for a particular layer change during the training process independently of the activation functions (AFs) of other network layers. In order to comply with the continuity condition for the derivative of the parabolic ID-spline on the interval (x x0, n) , its parameters fi (i= 0,...,n) should be calculated using the tridiagonal system of linear algebraic equations: To solve the system it is necessary to use two more equations arising from the boundary conditions for specific problems. For exam- ple the values of the grid function (if they are known) in the points (x x0, n) may be used for solving the system above: f f x0 = ( 0) , f f xn = ( n) . The parameters Iii+1 (i= 0,...,n−1 ) are used as trainable parameters of neural networks. The grid boundaries and spacing of the nodes of ID-spline AF are best chosen experimentally. The optimal selection of grid nodes allows improving the quality of results produced by the neural network. The formula for a parabolic ID-spline is such that the complexity of the calculations does not depend on whether the grid of nodes is uniform or non-uniform. An experimental comparison of the results of image classification from the popular FashionMNIST dataset by convolutional neural 0, x< 0 networks with the ID-spline AFs and the well-known ReLUx( ) =AF was carried out. The results reveal that the usage x x, ≥ 0 of the ID-spline AFs provides better accuracy of neural network operation than the ReLU AF. The training time for two convolutional layers network with two ID-spline AFs is just about 2 times longer than with two instances of ReLU AF. Doubling of the training time due to complexity of the ID-spline formula is the acceptable price for significantly better accuracy of the network. Wherein the difference of an operation speed of the networks with ID-spline and ReLU AFs will be negligible. The use of trainable ID-spline AFs makes it possible to simplify the architecture of neural networks without losing their efficiency. The modification of the well-known neural networks (ResNet etc.) by replacing traditional AFs with ID-spline AFs is a promising approach to increase the neural network operation accuracy. In a majority of cases, such a substitution does not require to train the network from scratch because it allows to use pre-trained on large datasets neuron weights supplied by standard software libraries for neural network construction thus substantially shortening training time.

scholarly journals A Study of Image Classification of Remote Sensing Based on Back-Propagation Neural Network with Extended Delta Bar Delta

2015 ◽  
Vol 2015 ◽  
pp. 1-10 ◽  
Author(s):  
Shi Liang Zhang ◽  
Ting Cheng Chang
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Image Classification ◽  
Back Propagation ◽  
Remote Sensing Image ◽  
Geographic Information ◽  
Classification Algorithm ◽  
Classification Model ◽  
Landsat 8 ◽  
Advantages And Disadvantages

This paper proposes a model to extract feature information quickly and accurately identifying what cannot be achieved through traditional methods of remote sensing image classification. First, process the selected Landsat-8 remote sensing data, including radiometric calibration, geometric correction, optimal band combination, and image cropping. Add the processed remote sensing image to the normalized geographic auxiliary information, digital elevation model (DEM), and normalized difference vegetation index (NDVI), working together to build a neural network that consists of three levels based on the structure of back-propagation neural and extended delta bar delta (BPN-EDBD) algorithm, determining the parameters of the neural network to constitute a good classification model. Then determine classification and standards via field surveys and related geographic information; select training samples BPN-EDBD for algorithm learning and training and, if necessary, revise and improve its parameters using the BPN-EDBD classification algorithm to classify the remote sensing image after pretreatment and DEM data and NDVI as input parameters and output classification results, and run accuracy assessment. Finally, compare with traditional supervised classification algorithms, while adding different auxiliary geographic information to compare classification results to study the advantages and disadvantages of BPN-EDBD classification algorithm.

scholarly journals Research on improved wavelet convolutional wavelet neural networks

2020 ◽  
Author(s):  
Jing-Wei Liu ◽  
Fang-Ling Zuo ◽  
Ying-Xiao Guo ◽  
Tian-Yue Li ◽  
Jia-Ming Chen
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
High Performance ◽  
Learning Algorithm ◽  
Wavelet Neural Network ◽  
Deep Learning Algorithm ◽  
Main Work ◽  
Good Ability ◽  
Fully Connected

AbstractConvolutional neural network (CNN) is recognized as state of the art of deep learning algorithm, which has a good ability on the image classification and recognition. The problems of CNN are as follows: the precision, accuracy and efficiency of CNN are expected to be improved to satisfy the requirements of high performance. The main work is as follows: Firstly, wavelet convolutional neural network (wCNN) is proposed, where wavelet transform function is added to the convolutional layers of CNN. Secondly, wavelet convolutional wavelet neural network (wCwNN) is proposed, where fully connected neural network (FCNN) of wCNN and CNN are replaced by wavelet neural network (wNN). Thirdly, image classification experiments using CNN, wCNN and wCwNN algorithms, and comparison analysis are implemented with MNIST dataset. The effect of the improved methods are as follows: (1) Both precision and accuracy are improved. (2) The mean square error and the rate of error are reduced. (3) The complexitie of the improved algorithms is increased.

SAR Image Classification Based on Brushlet and Self-Adaptive Ridgelet Neural Network

2013 ◽  
Vol 347-350 ◽  
pp. 3024-3028
Author(s):  
Nan Zheng ◽  
Hai Feng Tan
Keyword(s):  
Neural Network ◽  
Image Classification ◽  
Classification Model ◽  
Image Texture ◽  
Sar Image ◽  
Wavelet Network ◽  
Network Training ◽  
Long Time ◽  
Direction Information ◽  
Self Adaptive

Aiming at the defect that BP neural network classification model takes a long time for network training and the condition that wavelet network model lacks of direction information description, the paper presents a method for SAR image classification based on Brushlet and self-adaptive ridgelet neural network. The method extracts the energy and phase feature of SAR image texture through the Brushlet transformation, and inputs the feature vector that describes the energy and phase information into self-adaptive ridgelet neural network for training and classification. The contrast experiment indicates that the classification method proposed in this paper is rapid and accurate, and outperforms the traditional methods.

Relating the Slope of the Activation Function and the Learning Rate Within a Recurrent Neural Network

1999 ◽  
Vol 11 (5) ◽  
pp. 1069-1077 ◽  
Author(s):  
Danilo P. Mandic ◽  
Jonathon A. Chambers
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Recurrent Neural Network ◽  
Recurrent Neural Networks ◽  
Degrees Of Freedom ◽  
Learning Algorithm ◽  
Activation Function ◽  
Learning Rate ◽  
Optimization Task ◽  
Nonlinear Activation Function

A relationship between the learning rate η in the learning algorithm, and the slope β in the nonlinear activation function, for a class of recurrent neural networks (RNNs) trained by the real-time recurrent learning algorithm is provided. It is shown that an arbitrary RNN can be obtained via the referent RNN, with some deterministic rules imposed on its weights and the learning rate. Such relationships reduce the number of degrees of freedom when solving the nonlinear optimization task of finding the optimal RNN parameters.

scholarly journals CNN based Image Classification Model

2019 ◽  
Vol 8 (11S) ◽  
pp. 1106-1114
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Image Classification ◽  
Error Rates ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
The Internet ◽  
Network Algorithms ◽  
Media Companies ◽  
Automatic Tagging

Images are the fastest growing content, they contribute significantly to the amount of data generated on the internet every day. Image classification is a challenging problem that social media companies work on vigorously to enhance the user’s experience with the interface. The recent advances in the field of machine learning and computer vision enables personalized suggestions and automatic tagging of images. Convolutional neural network is a hot research topic these days in the field of machine learning. With the help of immensely dense labelled data available on the internet the networks can be trained to recognize the differentiating features among images under the same label. New neural network algorithms are developed frequently that outperform the state-of-art machine learning algorithms. Recent algorithms have managed to produce error rates as low as 3.1%. In this paper the architecture of important CNN algorithms that have gained attention are discussed, analyzed and compared and the concept of transfer learning is used to classify different breeds of dogs..

Sign in / Sign up

Export Citation Format

Share Document