Comparative Performance Evaluation of VGG-16 and Capsnet using Kannada MNIST

2021 ◽  
Vol 9 (8) ◽  
pp. 1190-1194
Author(s):  
Dr. Ramya C
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Character Recognition ◽  
Handwriting Recognition ◽  
Classification Problem ◽  
Training Data ◽  
Comparative Performance ◽  
Regional Languages ◽  
Real Time Application

Abstract: Handwriting recognition is an important problem in character recognition. It is much more difficult especially for regional languages such as Kannada. In this regard there has been a recent surge of interest in designing convolutional neural networks (CNNs) for this problem. However, CNNs typically require large amounts of training data and cannot handle input transformations. Capsule networks, which is referred to as capsNets proposed recently to overcome these shortcomings and posed to revolutionize deep learning solutions. Our particular interest in this work is to recognize kannada digit characters, and making capsnet robust to rotation and transformation. In this paper, we focus to achieve the following objectives :1. Explore whether or not capsnet is capable of providing a better fit for the digit images; 2. Adapt and incorporate capsNets for the problem of kannada MNIST digit classification problem at hand; 3. develop a real time application to take handwritten input from the user and recognize the digit; 4. Compare the capsnet with other models on various parameters. Keywords: Capsule Networks, Deep Learning, Convolutional Neural Networks (CNNs), Kannada MNIST, VGG-16

Uncertainty quantification in fault detection using convolutional neural networks

Geophysics ◽  
2021 ◽  
pp. 1-45
Author(s):  
Runhai Feng ◽  
Dario Grana ◽  
Niels Balling
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Reservoir Characterization ◽  
Epistemic Uncertainty ◽  
Confidence Regions ◽  
Training Data ◽  
Model Parameters ◽  
Sigmoid Function ◽  
Learning Tools

Segmentation of faults based on seismic images is an important step in reservoir characterization. With the recent developments of deep-learning methods and the availability of massive computing power, automatic interpretation of seismic faults has become possible. The likelihood of occurrence for a fault can be quantified using a sigmoid function. Our goal is to quantify the fault model uncertainty that is generally not captured by deep-learning tools. We propose to use the dropout approach, a regularization technique to prevent overfitting and co-adaptation in hidden units, to approximate the Bayesian inference and estimate the principled uncertainty over functions. Particularly, the variance of the learned model has been decomposed into aleatoric and epistemic parts. The proposed method is applied to a real dataset from the Netherlands F3 block with two different dropout ratios in convolutional neural networks. The aleatoric uncertainty is irreducible since it relates to the stochastic dependency within the input observations. As the number of Monte-Carlo realizations increases, the epistemic uncertainty asymptotically converges and the model standard deviation decreases, because the variability of model parameters is better simulated or explained with a larger sample size. This analysis can quantify the confidence to use fault predictions with less uncertainty. Additionally, the analysis suggests where more training data are needed to reduce the uncertainty in low confidence regions.

scholarly journals PulseNetOne: Fast Unsupervised Pruning of Convolutional Neural Networks for Remote Sensing

2020 ◽  
Vol 12 (7) ◽  
pp. 1092
Author(s):  
David Browne ◽  
Michael Giering ◽  
Steven Prestwich
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Data Augmentation ◽  
Recognition Task ◽  
Scene Recognition ◽  
Training Data ◽  
Learning Approach ◽  
Scene Classification

Scene classification is an important aspect of image/video understanding and segmentation. However, remote-sensing scene classification is a challenging image recognition task, partly due to the limited training data, which causes deep-learning Convolutional Neural Networks (CNNs) to overfit. Another difficulty is that images often have very different scales and orientation (viewing angle). Yet another is that the resulting networks may be very large, again making them prone to overfitting and unsuitable for deployment on memory- and energy-limited devices. We propose an efficient deep-learning approach to tackle these problems. We use transfer learning to compensate for the lack of data, and data augmentation to tackle varying scale and orientation. To reduce network size, we use a novel unsupervised learning approach based on k-means clustering, applied to all parts of the network: most network reduction methods use computationally expensive supervised learning methods, and apply only to the convolutional or fully connected layers, but not both. In experiments, we set new standards in classification accuracy on four remote-sensing and two scene-recognition image datasets.

scholarly journals Hybridizing Evolutionary Computation and Deep Neural Networks: An Approach to Handwriting Recognition Using Committees and Transfer Learning

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-16 ◽  
Author(s):  
Alejandro Baldominos ◽  
Yago Saez ◽  
Pedro Isasi
Keyword(s):  
Neural Networks ◽  
Evolutionary Computation ◽  
Transfer Learning ◽  
Convolutional Neural Networks ◽  
Character Recognition ◽  
Deep Neural Networks ◽  
Handwriting Recognition ◽  
Computational Time ◽  
Learning Models ◽  
Expensive Process

Neuroevolution is the field of study that uses evolutionary computation in order to optimize certain aspect of the design of neural networks, most often its topology and hyperparameters. The field was introduced in the late-1980s, but only in the latest years the field has become mature enough to enable the optimization of deep learning models, such as convolutional neural networks. In this paper, we rely on previous work to apply neuroevolution in order to optimize the topology of deep neural networks that can be used to solve the problem of handwritten character recognition. Moreover, we take advantage of the fact that evolutionary algorithms optimize a population of candidate solutions, by combining a set of the best evolved models resulting in a committee of convolutional neural networks. This process is enhanced by using specific mechanisms to preserve the diversity of the population. Additionally, in this paper, we address one of the disadvantages of neuroevolution: the process is very expensive in terms of computational time. To lessen this issue, we explore the performance of topology transfer learning: whether the best topology obtained using neuroevolution for a certain domain can be successfully applied to a different domain. By doing so, the expensive process of neuroevolution can be reused to tackle different problems, turning it into a more appealing approach for optimizing the design of neural networks topologies. After evaluating our proposal, results show that both the use of neuroevolved committees and the application of topology transfer learning are successful: committees of convolutional neural networks are able to improve classification results when compared to single models, and topologies learned for one problem can be reused for a different problem and data with a good performance. Additionally, both approaches can be combined by building committees of transferred topologies, and this combination attains results that combine the best of both approaches.

scholarly journals Pashtu Numerals Recognition through Convolutional Neural Networks

2019 ◽  
pp. 91-96
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Recognition Accuracy ◽  
Research Use ◽  
Optical Character ◽  
Classification Tasks ◽  
Scanned Images

In the proposed paper we introduce a new Pashtu numerals dataset having handwritten scanned images. We make the dataset publically available for scientific and research use. Pashtu language is used by more than fifty million people both for oral and written communication, but still no efforts are devoted to the Optical Character Recognition (OCR) system for Pashtu language. We introduce a new method for handwritten numerals recognition of Pashtu language through the deep learning based models. We use convolutional neural networks (CNNs) both for features extraction and classification tasks. We assess the performance of the proposed CNNs based model and obtained recognition accuracy of 91.45%.

scholarly journals Recognizing Ancient Characters from Tamil Palm Leaf Manuscripts using Convolution Based Deep Learning

2019 ◽  
Vol 8 (3) ◽  
pp. 6873-6880
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Image Processing ◽  
Pattern Recognition ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Convolutional Network ◽  
Palm Leaf

Palm leaf manuscripts has been one of the ancient writing methods but the palm leaf manuscripts content requires to be inscribed in a new set of leaves. This study has provided a solution to save the contents in palm leaf manuscripts by recognizing the handwritten Tamil characters in manuscripts and storing them digitally. Character recognition is one of the most essential fields of pattern recognition and image processing. Generally Optical character recognition is the method of e-translation of typewritten text or handwritten images into machine editable text. The handwritten Tamil character recognition has been one of the challenging and active areas of research in the field of pattern recognition and image processing. In this study a trial was made to identify Tamil handwritten characters without extraction of feature using convolutional neural networks. This study uses convolutional neural networks for recognizing and classifying the Tamil palm leaf manuscripts of characters from separated character images. The convolutional neural network is a deep learning approach for which it does not need to retrieve features and also a rapid approach for character recognition. In the proposed system every character is expanded to needed pixels. The expanded characters have predetermined pixels and these pixels are considered as characteristics for neural network training. The trained network is employed for recognition and classification. Convolutional Network Model development contains convolution layer, Relu layer, pooling layer, fully connected layer. The ancient Tamil character dataset of 60 varying class has been created. The outputs reveal that the proposed approach generates better rates of recognition than that of schemes based on feature extraction for handwritten character recognition. The accuracy of the proposed approach has been identified as 97% which shows that the proposed approach is effective in terms of recognition of ancient characters.

scholarly journals Telugu and Hindi Script Recognition using Deep learning Techniques

2019 ◽  
Vol 8 (11) ◽  
pp. 1758-1764 ◽  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Character Recognition ◽  
Research Work ◽  
Indian Languages ◽  
Digital Form ◽  
Training Time ◽  
Learning Techniques ◽  
Handwritten Document

The need for offline handwritten character recognition is intense, yet difficult as the writing varies from person to person and also depends on various other factors connected to the attitude and mood of the person. However, we are able to achieve it by converting the handwritten document into digital form. It has been advanced with introducing convolutional neural networks and is further productive with pre-trained models which have the capacity of decreasing the training time and increasing accuracy of character recognition. Research in recognition of handwritten characters for Indian languages is less when compared to other languages like English, Latin, Chinese etc., mainly because it is a multilingual country. Recognition of Telugu and Hindi characters are more difficult as the script of these languages is mostly cursive and are with more diacritics. So the research work in this line is to have inclination towards accuracy in their recognition. Some research has already been started and is successful up to eighty percent in offline hand written character recognition of Telugu and Hindi. The proposed work focuses on increasing accuracy in less time in recognition of these selected languages and is able to reach the expectant values.

scholarly journals Nonlinear Chen-Lee Chaotic System Based Deep Convolutional Generative Adversarial Nets for Chatter Diagnosis

2021 ◽  
Author(s):  
Ping-Huan Kuo ◽  
Po-Chien Luan ◽  
Yung-Ruen Tseng ◽  
Her-Terng Yau
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Chaotic System ◽  
Original Data ◽  
Training Data ◽  
Original Training ◽  
Chatter Detection ◽  
Learning Models ◽  
Training Strategy

Abstract Chatter has a direct effect on the precision and life of machine tools and its detection is a crucial issue in all metal machining processes. Traditional methods focus on how to extract discriminative features to help identify chatter. Nowadays, deep learning models have shown an extraordinary ability to extract data features which are their necessary fuel. In this study deep learning models have been substituted for more traditional methods. Chatter data are rare and valuable because the collecting process is extremely difficult. To solve this practical problem an innovative training strategy has been proposed that is combined with a modified convolutional neural network and deep convolutional generative adversarial nets. This improves chatter detection and classification. Convolutional neural networks can be effective chatter classifiers, and adversarial networks can act as generators that produce more data. The convolutional neural networks were trained using original data as well as by forged data produced by the generator. Original training data were collected and preprocessed by the Chen-Lee chaotic system. The adversarial training process used these data to create the generator and the generator could produce enough data to compensate for the lack of training data. The experimental results were compared with without a data generator and data augmentation. The proposed method had an accuracy of 95.3% on leave-one-out cross-validation over ten runs and surpassed other methods and models. The forged data were also compared with original training data as well as data produced by augmentation. The distribution shows that forged data had similar quality and characteristics to the original data. The proposed training strategy provides a high-quality deep learning chatter detection model.

scholarly journals Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN)

Sensors ◽  
2020 ◽  
Vol 20 (12) ◽  
pp. 3344 ◽  
Author(s):  
Savita Ahlawat ◽  
Amit Choudhary ◽  
Anand Nayyar ◽  
Saurabh Singh ◽  
Byungun Yoon
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Recognition Accuracy ◽  
Handwriting Recognition ◽  
Computational Cost ◽  
Handwritten Digit Recognition ◽  
Digit Recognition ◽  
Handwritten Digit

Traditional systems of handwriting recognition have relied on handcrafted features and a large amount of prior knowledge. Training an Optical character recognition (OCR) system based on these prerequisites is a challenging task. Research in the handwriting recognition field is focused around deep learning techniques and has achieved breakthrough performance in the last few years. Still, the rapid growth in the amount of handwritten data and the availability of massive processing power demands improvement in recognition accuracy and deserves further investigation. Convolutional neural networks (CNNs) are very effective in perceiving the structure of handwritten characters/words in ways that help in automatic extraction of distinct features and make CNN the most suitable approach for solving handwriting recognition problems. Our aim in the proposed work is to explore the various design options like number of layers, stride size, receptive field, kernel size, padding and dilution for CNN-based handwritten digit recognition. In addition, we aim to evaluate various SGD optimization algorithms in improving the performance of handwritten digit recognition. A network’s recognition accuracy increases by incorporating ensemble architecture. Here, our objective is to achieve comparable accuracy by using a pure CNN architecture without ensemble architecture, as ensemble architectures introduce increased computational cost and high testing complexity. Thus, a CNN architecture is proposed in order to achieve accuracy even better than that of ensemble architectures, along with reduced operational complexity and cost. Moreover, we also present an appropriate combination of learning parameters in designing a CNN that leads us to reach a new absolute record in classifying MNIST handwritten digits. We carried out extensive experiments and achieved a recognition accuracy of 99.87% for a MNIST dataset.

Classification of Breast Masses on Ultrasound Shear Wave Elastography using Convolutional Neural Networks

2020 ◽  
Vol 42 (4-5) ◽  
pp. 213-220 ◽  
Author(s):  
Tomoyuki Fujioka ◽  
Leona Katsuta ◽  
Kazunori Kubota ◽  
Mio Mori ◽  
Yuka Kikuchi ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Shear Wave ◽  
Convolutional Neural Networks ◽  
Test Data ◽  
Diagnostic Performance ◽  
Shear Wave Elastography ◽  
Training Data ◽  
Breast Masses ◽  
Malignant Breast

We aimed to use deep learning with convolutional neural networks (CNNs) to discriminate images of benign and malignant breast masses on ultrasound shear wave elastography (SWE). We retrospectively gathered 158 images of benign masses and 146 images of malignant masses as training data for SWE. A deep learning model was constructed using several CNN architectures (Xception, InceptionV3, InceptionResNetV2, DenseNet121, DenseNet169, and NASNetMobile) with 50, 100, and 200 epochs. We analyzed SWE images of 38 benign masses and 35 malignant masses as test data. Two radiologists interpreted these test data through a consensus reading using a 5-point visual color assessment (SWEc) and the mean elasticity value (in kPa) (SWEe). Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated. The best CNN model (which was DenseNet169 with 100 epochs), SWEc, and SWEe had a sensitivity of 0.857, 0.829, and 0.914 and a specificity of 0.789, 0.737, and 0.763 respectively. The CNNs exhibited a mean AUC of 0.870 (range, 0.844–0.898), and SWEc and SWEe had an AUC of 0.821 and 0.855. The CNNs had an equal or better diagnostic performance compared with radiologist readings. DenseNet169 with 100 epochs, Xception with 50 epochs, and Xception with 100 epochs had a better diagnostic performance compared with SWEc ( P = 0.018–0.037). Deep learning with CNNs exhibited equal or higher AUC compared with radiologists when discriminating benign from malignant breast masses on ultrasound SWE.

scholarly journals Handwriting Recognition using Deep Learning based Convolutional Neural Network

2019 ◽  
Vol 8 (4) ◽  
pp. 4826-4828
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Convolutional Neural Networks ◽  
Input Data ◽  
Recognition Accuracy ◽  
Handwriting Recognition ◽  
Indian Language ◽  
Character Set

Handwriting is a learned skill that had been an excellent means of communication and documentation for thousands of years. The simple way to communicate with the computers is through either speech or handwriting. Speech has some limitation; hence input through handwriting is recommended. It is difficult to input data for computers for Indian language scripts because of their com-plex character set. This paper focuses on exploring convolutional neural networks (CNN) which is deep learning based for the recognition of handwritten script. The proposed method has shown 99% for handwritten English numerals and promising recognition accuracy for Kannada numerals.

Sign in / Sign up

Export Citation Format

Share Document