scholarly journals Unify Language and Vision: An Efficient COVID-19 Tomography Image Classification Approach

2020 ◽  
Author(s):  
Dezhou Shen
Keyword(s):  
Image Classification ◽  
High Accuracy ◽  
Specific Region ◽  
Language Models ◽  
Classification Model ◽  
Tomography Image ◽  
Image Test ◽  
Language And Vision ◽  
Image Pixels ◽  
Fully Connected

Abstract An accurate and efficient image classification algorithm used in the COVID-19 detection for lung tomography can be of great help for doctors working in places without advance equipments. The machine with high accuracy COVID-19 classification model can relief the burden by making testing and checking thousands of people’s tomography images easy for a specific region which suffers from the COVID-19 outbreak incidents. By encoding image pixels and meta-data using the pre-trained language models of Bidirectional Encoder Representations from Transformers, then connect to a fully connected layer, the classification model outperforms the ResNet model and the DenseNet image classification model, and achieved accuracy of 99.51% ∼ 100.00% on the COVID-19 tomography image test set.

scholarly journals Enhance Image Classification Performance Via Unsupervised Pre-trained Transformers Language Models

2020 ◽  
Author(s):  
Dezhou Shen
Keyword(s):  
Image Classification ◽  
Language Processing ◽  
Classification Performance ◽  
Language Models ◽  
Classification Model ◽  
Linear Probe ◽  
Image Set ◽  
Image Pixels ◽  
The Difference ◽  
Fully Connected

Abstract Image classification and categorization are essential to the capability of telling the difference between images for a machine. As Bidirectional Encoder Representations from Transformers became popular in many tasks of natural language processing recent years, it is intuitive to use these pre-trained language models for enhancing the computer vision tasks, \eg image classification. In this paper, by encoding image pixels using pre-trained transformers, then connect to a fully connected layer, the classification model outperforms the Wide ResNet model and the linear-probe iGPT-L model, and achieved accuracy of 99.60%～99.74% on the CIFAR-10 image set and accuracy of 99.10%～99.76% on the CIFAR-100 image set.

scholarly journals Deep Neural Learning Adaptive Sequential Monte Carlo for Automatic Image and Speech Recognition

2020 ◽  
Vol 2020 ◽  
pp. 1-9
Author(s):  
Patcharin Kamsing ◽  
Peerapong Torteeka ◽  
Wuttichai Boonpook ◽  
Chunxiang Cao
Keyword(s):  
Speech Recognition ◽  
Image Classification ◽  
Conventional Method ◽  
High Accuracy ◽  
Classification Model ◽  
Computational Time ◽  
Accuracy Score ◽  
Model Learning ◽  
Test Dataset ◽  
Applied Method

To enhance the performance of image classification and speech recognition, the optimizer is considered an important factor for achieving high accuracy. The state-of-the-art optimizer can perform to serve in applications that may not require very high accuracy, yet the demand for high-precision image classification and speech recognition is increasing. This study implements an adaptive method for applying the particle filter technique with a gradient descent optimizer to improve model learning performance. Using a pretrained model helps reduce the computational time to deploy an image classification model and uses a simple deep convolutional neural network for speech recognition. The applied method results in a higher speech recognition accuracy score—89.693% for the test dataset—than the conventional method, which reaches 89.325%. The applied method also performs well on the image classification task, reaching an accuracy of 89.860% on the test dataset, better than the conventional method, which has an accuracy of 89.644%. Despite a slight difference in accuracy, the applied optimizer performs well in this dataset overall.

AI-Provided Instant Differential Diagnosis of Pemphigus Vulgaris and Bullous Pemphigoid: Qualitative Study (Preprint)

2020 ◽  
Author(s):  
Xiaoyu He ◽  
Juan Su ◽  
Guangyu Wang ◽  
Kang Zhang ◽  
Navarini Alexander ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Early Diagnosis ◽  
Image Classification ◽  
Bullous Pemphigoid ◽  
Skin Diseases ◽  
Pemphigus Vulgaris ◽  
Classification Model ◽  
Clinical Image ◽  
Clinical Images ◽  
Multimodal Classification

BACKGROUND Pemphigus vulgaris (PV) and bullous pemphigoid (BP) are two rare but severe inflammatory dermatoses. Due to the regional lack of trained dermatologists, many patients with these two diseases are misdiagnosed and therefore incorrectly treated. An artificial intelligence diagnosis framework would be highly adaptable for the early diagnosis of these two diseases. OBJECTIVE Design and evaluate an artificial intelligence diagnosis framework for PV and BP. METHODS The work was conducted on a dermatological dataset consisting of 17,735 clinical images and 346 patient metadata of bullous dermatoses. A two-stage diagnosis framework was designed, where the first stage trained a clinical image classification model to classify bullous dermatoses from five common skin diseases and normal skin and the second stage developed a multimodal classification model of clinical images and patient metadata to further differentiate PV and BP. RESULTS The clinical image classification model and the multimodal classification model achieved an area under the receiver operating characteristic curve (AUROC) of 0.998 and 0.942, respectively. On the independent test set of 20 PV and 20 BP cases, our multimodal classification model (sensitivity: 0.85, specificity: 0.95) performed better than the average of 27 junior dermatologists (sensitivity: 0.68, specificity: 0.78) and comparable to the average of 69 senior dermatologists (sensitivity: 0.80, specificity: 0.87). CONCLUSIONS Our diagnosis framework based on clinical images and patient metadata achieved expert-level identification of PV and BP, and is potential to be an effective tool for dermatologists in remote areas in the early diagnosis of these two diseases.

scholarly journals Image Classification for the Automatic Feature Extraction in Human Worn Fashion Data

Mathematics ◽  
2021 ◽  
Vol 9 (6) ◽  
pp. 624
Author(s):  
Stefan Rohrmanstorfer ◽  
Mikhail Komarov ◽  
Felix Mödritscher
Keyword(s):  
Neural Networks ◽  
Feature Extraction ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Image Data ◽  
Classification Model ◽  
Upper Body ◽  
Automatic Feature Extraction

With the always increasing amount of image data, it has become a necessity to automatically look for and process information in these images. As fashion is captured in images, the fashion sector provides the perfect foundation to be supported by the integration of a service or application that is built on an image classification model. In this article, the state of the art for image classification is analyzed and discussed. Based on the elaborated knowledge, four different approaches will be implemented to successfully extract features out of fashion data. For this purpose, a human-worn fashion dataset with 2567 images was created, but it was significantly enlarged by the performed image operations. The results show that convolutional neural networks are the undisputed standard for classifying images, and that TensorFlow is the best library to build them. Moreover, through the introduction of dropout layers, data augmentation and transfer learning, model overfitting was successfully prevented, and it was possible to incrementally improve the validation accuracy of the created dataset from an initial 69% to a final validation accuracy of 84%. More distinct apparel like trousers, shoes and hats were better classified than other upper body clothes.

scholarly journals A Novel Lightweight Deep Learning-Based Histopathological Image Classification Model for IoMT

2021 ◽  
Author(s):  
Koyel Datta Gupta ◽  
Deepak Kumar Sharma ◽  
Shakib Ahmed ◽  
Harsh Gupta ◽  
Deepak Gupta ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Classification ◽  
Classification Model ◽  
Histopathological Image ◽  
Histopathological Image Classification

scholarly journals POLSAR Image Classification via Clustering-WAE Classification Model

IEEE Access ◽  
2018 ◽  
Vol 6 ◽  
pp. 40041-40049 ◽  
Author(s):  
Wen Xie ◽  
Ziwei Xie ◽  
Feng Zhao ◽  
Bo Ren
Keyword(s):  
Image Classification ◽  
Classification Model

scholarly journals Extracting image features for classification by two-tier genetic programming

2020 ◽  
Author(s):  
Harith Al-Sahaf ◽  
A Song ◽  
K Neshatian ◽  
Mengjie Zhang
Keyword(s):  
Genetic Programming ◽  
Image Classification ◽  
Domain Knowledge ◽  
Extraction Process ◽  
High Accuracy ◽  
Classification Performance ◽  
Image Features ◽  
Classification Methods ◽  
Feature Based ◽  
Second Tier

Image classification is a complex but important task especially in the areas of machine vision and image analysis such as remote sensing and face recognition. One of the challenges in image classification is finding an optimal set of features for a particular task because the choice of features has direct impact on the classification performance. However the goodness of a feature is highly problem dependent and often domain knowledge is required. To address these issues we introduce a Genetic Programming (GP) based image classification method, Two-Tier GP, which directly operates on raw pixels rather than features. The first tier in a classifier is for automatically defining features based on raw image input, while the second tier makes decision. Compared to conventional feature based image classification methods, Two-Tier GP achieved better accuracies on a range of different tasks. Furthermore by using the features defined by the first tier of these Two-Tier GP classifiers, conventional classification methods obtained higher accuracies than classifying on manually designed features. Analysis on evolved Two-Tier image classifiers shows that there are genuine features captured in the programs and the mechanism of achieving high accuracy can be revealed. The Two-Tier GP method has clear advantages in image classification, such as high accuracy, good interpretability and the removal of explicit feature extraction process. © 2012 IEEE.

Sign in / Sign up

Export Citation Format

Share Document