scholarly journals Large-Scale Printed Chinese Character Recognition for ID Cards Using Deep Learning and Few Samples Transfer Learning

2021 ◽  
Author(s):  
Yi-Quan Li ◽  
Hao-Sen Chang ◽  
Daw-Tung Lin
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Transfer Learning ◽  
Character Recognition ◽  
Large Scale ◽  
Data Augmentation ◽  
Training Data ◽  
Fine Tuning ◽  
Training Dataset ◽  
Model Parameters

In the field of computer vision, large-scale image classification tasks are both important and highly challenging. With the ongoing advances in deep learning and optical character recognition (OCR) technologies, neural networks designed to perform large-scale classification play an essential role in facilitating OCR systems. In this study, we developed an automatic OCR system designed to identify up to 13,070 large-scale printed Chinese characters by using deep learning neural networks and fine-tuning techniques. The proposed framework comprises four components, including training dataset synthesis and background simulation, image preprocessing and data augmentation, the process of training the model, and transfer learning. The training data synthesis procedure is composed of a character font generation step and a background simulation process. Three background models are proposed to simulate the factors of the background noise and anti-counterfeiting patterns on ID cards. To expand the diversity of the synthesized training dataset, rotation and zooming data augmentation are applied. A massive dataset comprising more than 19.6 million images was thus created to accommodate the variations in the input images and improve the learning capacity of the CNN model. Subsequently, we modified the GoogLeNet neural architecture by replacing the FC layer with a global average pooling layer to avoid overfitting caused by a massive amount of training data. Consequently, the number of model parameters was reduced. Finally, we employed the transfer learning technique to further refine the CNN model using a small number of real data samples. Experimental results show that the overall recognition performance of the proposed approach is significantly better than that of prior methods and thus demonstrate the effectiveness of proposed framework, which exhibited a recognition accuracy as high as 99.39% on the constructed real ID card dataset.

scholarly journals Transfer Learning for Inference of Metastatic Origin from Whole Slide Histology

2021 ◽  
Author(s):  
Geoffrey F. Schau ◽  
Hassan Ghani ◽  
Erik A. Burlingame ◽  
Guillaume Thibault ◽  
Joe W. Gray ◽  
...  
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Primary Tumor ◽  
Large Scale ◽  
Metastatic Cancer ◽  
Clinical Diagnostics ◽  
Training Data ◽  
Fine Tuning ◽  
Learning Approach ◽  
Whole Slide Images

AbstractAccurate diagnosis of metastatic cancer is essential for prescribing optimal control strategies to halt further spread of metastasizing disease. While pathological inspection aided by immunohistochemistry staining provides a valuable gold standard for clinical diagnostics, deep learning methods have emerged as powerful tools for identifying clinically relevant features of whole slide histology relevant to a tumor’s metastatic origin. Although deep learning models require significant training data to learn effectively, transfer learning paradigms provide mechanisms to circumvent limited training data by first training a model on related data prior to fine-tuning on smaller data sets of interest. In this work we propose a transfer learning approach that trains a convolutional neural network to infer the metastatic origin of tumor tissue from whole slide images of hematoxylin and eosin (H&E) stained tissue sections and illustrate the advantages of pre-training network on whole slide images of primary tumor morphology. We further characterize statistical dissimilarity between primary and metastatic tumors of various indications on patch-level images to highlight limitations of our indication-specific transfer learning approach. Using a primary-to-metastatic transfer learning approach, we achieved mean class-specific areas under receiver operator characteristics curve (AUROC) of 0.779, which outperformed comparable models trained on only images of primary tumor (mean AUROC of 0.691) or trained on only images of metastatic tumor (mean AUROC of 0.675), supporting the use of large scale primary tumor imaging data in developing computer vision models to characterize metastatic origin of tumor lesions.

scholarly journals Plastic Gasket Defect Detection Based on Transfer Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Xieyi Chen ◽  
Dongyun Wang ◽  
Jinjun Shao ◽  
Jun Fan
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Defect Detection ◽  
Data Augmentation ◽  
Surface Defects ◽  
Visual Detection ◽  
Training Data

To automatically detect plastic gasket defects, a set of plastic gasket defect visual detection devices based on GoogLeNet Inception-V2 transfer learning was designed and established in this study. The GoogLeNet Inception-V2 deep convolutional neural network (DCNN) was adopted to extract and classify the defect features of plastic gaskets to solve the problem of their numerous surface defects and difficulty in extracting and classifying the features. Deep learning applications require a large amount of training data to avoid model overfitting, but there are few datasets of plastic gasket defects. To address this issue, data augmentation was applied to our dataset. Finally, the performance of the three convolutional neural networks was comprehensively compared. The results showed that the GoogLeNet Inception-V2 transfer learning model had a better performance in less time. It means it had higher accuracy, reliability, and efficiency on the dataset used in this paper.

scholarly journals Deep Learning-Based Differentiation between Mucinous Cystic Neoplasm and Serous Cystic Neoplasm in the Pancreas Using Endoscopic Ultrasonography

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1052
Author(s):  
Leang Sim Nguon ◽  
Kangwon Seo ◽  
Jung-Hyun Lim ◽  
Tae-Jun Song ◽  
Sung-Hyun Cho ◽  
...  
Keyword(s):  
Decision Making ◽  
Deep Learning ◽  
Network Model ◽  
Endoscopic Ultrasonography ◽  
Data Augmentation ◽  
Clinical Information ◽  
Training Data ◽  
Fine Tuning ◽  
Cystic Neoplasm ◽  
Cystic Neoplasms

Mucinous cystic neoplasms (MCN) and serous cystic neoplasms (SCN) account for a large portion of solitary pancreatic cystic neoplasms (PCN). In this study we implemented a convolutional neural network (CNN) model using ResNet50 to differentiate between MCN and SCN. The training data were collected retrospectively from 59 MCN and 49 SCN patients from two different hospitals. Data augmentation was used to enhance the size and quality of training datasets. Fine-tuning training approaches were utilized by adopting the pre-trained model from transfer learning while training selected layers. Testing of the network was conducted by varying the endoscopic ultrasonography (EUS) image sizes and positions to evaluate the network performance for differentiation. The proposed network model achieved up to 82.75% accuracy and a 0.88 (95% CI: 0.817–0.930) area under curve (AUC) score. The performance of the implemented deep learning networks in decision-making using only EUS images is comparable to that of traditional manual decision-making using EUS images along with supporting clinical information. Gradient-weighted class activation mapping (Grad-CAM) confirmed that the network model learned the features from the cyst region accurately. This study proves the feasibility of diagnosing MCN and SCN using a deep learning network model. Further improvement using more datasets is needed.

scholarly journals Self-Supervised Pre-Training of Transformers for Satellite Image Time Series Classification

2020 ◽  
Author(s):  
Yuan Yuan ◽  
Lei Lin
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Large Scale ◽  
Temporal Structure ◽  
Satellite Image ◽  
Fine Tuning ◽  
Small Scale ◽  
Model Parameters ◽  
Learning Approaches ◽  
Wide Range

Satellite image time series (SITS) classification is a major research topic in remote sensing and is relevant for a wide range of applications. Deep learning approaches have been commonly employed for SITS classification and have provided state-of-the-art performance. However, deep learning methods suffer from overfitting when labeled data is scarce. To address this problem, we propose a novel self-supervised pre-training scheme to initialize a Transformer-based network by utilizing large-scale unlabeled data. In detail, the model is asked to predict randomly contaminated observations given an entire time series of a pixel. The main idea of our proposal is to leverage the inherent temporal structure of satellite time series to learn general-purpose spectral-temporal representations related to land cover semantics. Once pre-training is completed, the pre-trained network can be further adapted to various SITS classification tasks by fine-tuning all the model parameters on small-scale task-related labeled data. In this way, the general knowledge and representations about SITS can be transferred to a label-scarce task, thereby improving the generalization performance of the model as well as reducing the risk of overfitting. Comprehensive experiments have been carried out on three benchmark datasets over large study areas. Experimental results demonstrate the effectiveness of the proposed method, leading to a classification accuracy increment up to 1.91% to 6.69%. <div><b>This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.</b></div>

scholarly journals Comparative Analysis on Deep Learning Approaches for Heavy-Vehicle Detection based on Data Augmentation and Transfer-Learning techniques

2021 ◽  
Vol 13 (3) ◽  
pp. 809-820
Author(s):  
V. Sowmya ◽  
R. Radha
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Real Time ◽  
Transfer Learning ◽  
Convolutional Neural Networks ◽  
Traffic Management ◽  
Data Augmentation ◽  
Vehicle Detection ◽  
Heavy Vehicles ◽  
Detection And Recognition

Vehicle detection and recognition require demanding advanced computational intelligence and resources in a real-time traffic surveillance system for effective traffic management of all possible contingencies. One of the focus areas of deep intelligent systems is to facilitate vehicle detection and recognition techniques for robust traffic management of heavy vehicles. The following are such sophisticated mechanisms: Support Vector Machine (SVM), Convolutional Neural Networks (CNN), Regional Convolutional Neural Networks (R-CNN), You Only Look Once (YOLO) model, etcetera. Accordingly, it is pivotal to choose the precise algorithm for vehicle detection and recognition, which also addresses the real-time environment. In this study, a comparison of deep learning algorithms, such as the Faster R-CNN, YOLOv2, YOLOv3, and YOLOv4, are focused on diverse aspects of the features. Two entities for transport heavy vehicles, the buses and trucks, constitute detection and recognition elements in this proposed work. The mechanics of data augmentation and transfer-learning is implemented in the model; to build, execute, train, and test for detection and recognition to avoid over-fitting and improve speed and accuracy. Extensive empirical evaluation is conducted on two standard datasets such as COCO and PASCAL VOC 2007. Finally, comparative results and analyses are presented based on real-time.

Combining Self-supervised Learning and Active Learning for Disfluency Detection

2022 ◽  
Vol 21 (3) ◽  
pp. 1-25
Author(s):  
Shaolei Wang ◽  
Zhongyuan Wang ◽  
Wanxiang Che ◽  
Sendong Zhao ◽  
Ting Liu
Keyword(s):  
Neural Network ◽  
Active Learning ◽  
Supervised Learning ◽  
Large Scale ◽  
Training Data ◽  
Fine Tuning ◽  
Training Dataset ◽  
Performance Gap ◽  
Annotation Costs ◽  
Trained Neural Network

Spoken language is fundamentally different from the written language in that it contains frequent disfluencies or parts of an utterance that are corrected by the speaker. Disfluency detection (removing these disfluencies) is desirable to clean the input for use in downstream NLP tasks. Most existing approaches to disfluency detection heavily rely on human-annotated data, which is scarce and expensive to obtain in practice. To tackle the training data bottleneck, in this work, we investigate methods for combining self-supervised learning and active learning for disfluency detection. First, we construct large-scale pseudo training data by randomly adding or deleting words from unlabeled data and propose two self-supervised pre-training tasks: (i) a tagging task to detect the added noisy words and (ii) sentence classification to distinguish original sentences from grammatically incorrect sentences. We then combine these two tasks to jointly pre-train a neural network. The pre-trained neural network is then fine-tuned using human-annotated disfluency detection training data. The self-supervised learning method can capture task-special knowledge for disfluency detection and achieve better performance when fine-tuning on a small annotated dataset compared to other supervised methods. However, limited in that the pseudo training data are generated based on simple heuristics and cannot fully cover all the disfluency patterns, there is still a performance gap compared to the supervised models trained on the full training dataset. We further explore how to bridge the performance gap by integrating active learning during the fine-tuning process. Active learning strives to reduce annotation costs by choosing the most critical examples to label and can address the weakness of self-supervised learning with a small annotated dataset. We show that by combining self-supervised learning with active learning, our model is able to match state-of-the-art performance with just about 10% of the original training data on both the commonly used English Switchboard test set and a set of in-house annotated Chinese data.

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 A general approach for improving deep learning-based medical relation extraction using a pre-trained model and fine-tuning

Database ◽  
2019 ◽  
Vol 2019 ◽  
Author(s):  
Tao Chen ◽  
Mingfen Wu ◽  
Hexi Li
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Relation Extraction ◽  
Training Model ◽  
Biomedical Literature ◽  
Training Data ◽  
Fine Tuning ◽  
Learning Approaches ◽  
Additional Time ◽  
Clinical Records

Abstract The automatic extraction of meaningful relations from biomedical literature or clinical records is crucial in various biomedical applications. Most of the current deep learning approaches for medical relation extraction require large-scale training data to prevent overfitting of the training model. We propose using a pre-trained model and a fine-tuning technique to improve these approaches without additional time-consuming human labeling. Firstly, we show the architecture of Bidirectional Encoder Representations from Transformers (BERT), an approach for pre-training a model on large-scale unstructured text. We then combine BERT with a one-dimensional convolutional neural network (1d-CNN) to fine-tune the pre-trained model for relation extraction. Extensive experiments on three datasets, namely the BioCreative V chemical disease relation corpus, traditional Chinese medicine literature corpus and i2b2 2012 temporal relation challenge corpus, show that the proposed approach achieves state-of-the-art results (giving a relative improvement of 22.2, 7.77, and 38.5% in F1 score, respectively, compared with a traditional 1d-CNN classifier). The source code is available at https://github.com/chentao1999/MedicalRelationExtraction.

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 DEEP LEARNING BASED ROOF TYPE CLASSIFICATION USING VERY HIGH RESOLUTION AERIAL IMAGERY

2021 ◽  
Vol XLIII-B3-2021 ◽  
pp. 55-60
Author(s):  
M. Buyukdemircioglu ◽  
R. Can ◽  
S. Kocaman
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Urban Areas ◽  
Image Features ◽  
Training Data ◽  
Fine Tuning ◽  
Computer Hardware ◽  
Geographical Information ◽  
Training Dataset ◽  
Very High

Abstract. Automatic detection, segmentation and reconstruction of buildings in urban areas from Earth Observation (EO) data are still challenging for many researchers. Roof is one of the most important element in a building model. The three-dimensional geographical information system (3D GIS) applications generally require the roof type and roof geometry for performing various analyses on the models, such as energy efficiency. The conventional segmentation and classification methods are often based on features like corners, edges and line segments. In parallel to the developments in computer hardware and artificial intelligence (AI) methods including deep learning (DL), image features can be extracted automatically. As a DL technique, convolutional neural networks (CNNs) can also be used for image classification tasks, but require large amount of high quality training data for obtaining accurate results. The main aim of this study was to generate a roof type dataset from very high-resolution (10 cm) orthophotos of Cesme, Turkey, and to classify the roof types using a shallow CNN architecture. The training dataset consists 10,000 roof images and their labels. Six roof type classes such as flat, hip, half-hip, gable, pyramid and complex roofs were used for the classification in the study area. The prediction performance of the shallow CNN model used here was compared with the results obtained from the fine-tuning of three well-known pre-trained networks, i.e. VGG-16, EfficientNetB4, ResNet-50. The results show that although our CNN has slightly lower performance expressed with the overall accuracy, it is still acceptable for many applications using sparse data.

Sign in / Sign up

Export Citation Format

Share Document