Evaluation of Several Artificial Intelligence and Machine Learning Algorithms for Image Classification on Small Datasets
0
Citation
14
Reference
10
Related Paper
Keywords:
Overfitting
Transfer of learning
Benchmark (surveying)
Upload
Transfer of learning
Feature (linguistics)
Cite
Citations (11)
In this paper, an attempt is addressed towards accurate vegetable image classification. A dataset consisting of 21,000 images of 15 classes is used for this classification. Convolutional neural network, a deep learning algorithm is the most efficient tool in the machine learning field for classification problems. But CNN requires large datasets so that it performs well in natural image classification problems. Here, we conduct an experiment on the performance of CNN for vegetable image classification by developing a CNN model from the ground. Additionally, several pre-trained CNN architectures using transfer learning are employed to compare the accuracy with the typical CNN. This work proposes the study between such typical CNN and its architectures(VGG16, MobileNet, InceptionV3, ResNet etc.) to build up which technique would work best regarding accuracy and effectiveness with new image datasets. Experimental results are presented for all the proposed architectures of CNN. Besides, a comparative study is done between developed CNN models and pre-trained CNN architectures. And the study shows that by utilizing previous information gained from related large-scale work, the transfer learning technique can achieve better classification results over traditional CNN with a small dataset. And one more enrichment in this paper is that we build up a vegetable images dataset of 15 categories consisting of a total of 21,000 images.
Transfer of learning
Contextual image classification
Cite
Citations (35)
CNN-based transfer learning method plays a significant role in the detection of various objects such as cars, dogs, motorcycles, face and human detection in nighttime images by using visible light camera sensors. This method mainly depends on the images captured by cameras in order to detect the mentioned objects in a variety of environments based on convolutional neural networks (CNNs). In this study, we utilized the same method to detect coronavirus phenomena by using chest X-ray images that have been collected from three different open-source datasets with the aim of rapid detection of the infected patients and speed up the diagnostic process. We used one of the deep learning architectures in a Transfer Learning mode and modified its final layers to adapt to the number of classes in our investigation. The deep learning architecture that we used for the purpose of COVID-19 detection from X-ray images is a CNN designed to detect human in nighttime. We also modified the CNN architecture in three different scenarios named (Model 1, Model 2 and Model 3) in order to improve the classification results. Compared to model one and two, the result improved in model three and the number of misclassified cases reduced particularly in detecting Abnormal and COVID-19 cases. Although our CNN-based method shows high performance in COVID-19 detection, CNN decisions should not to be taken into consideration until clinical tests confirms symptoms of the infected patients.
Transfer of learning
Cite
Citations (3)
Purpose The paper aims to address the tracking algorithm based on deep learning and four deep learning tracking models developed. They compared with each other to prevent collision and to obtain target tracking in autonomous aircraft. Design/methodology/approach First, to follow the visual target, the detection methods were used and then the tracking methods were examined. Here, four models (deep convolutional neural networks (DCNN), deep convolutional neural networks with fine-tuning (DCNNFN), transfer learning with deep convolutional neural network (TLDCNN) and fine-tuning deep convolutional neural network with transfer learning (FNDCNNTL)) were developed. Findings The training time of DCNN took 9 min 33 s, while the accuracy percentage was calculated as 84%. In DCNNFN, the training time of the network was calculated as 4 min 26 s and the accuracy percentage was 91%. The training of TLDCNN) took 34 min and 49 s and the accuracy percentage was calculated as 95%. With FNDCNNTL, the training time of the network was calculated as 34 min 33 s and the accuracy percentage was nearly 100%. Originality/value Compared to the results in the literature ranging from 89.4% to 95.6%, using FNDCNNTL, better results were found in the paper.
Transfer of learning
Tracking (education)
Cite
Citations (16)
Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs). CNNs enable learning data-driven, highly representative, hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models pre-trained from natural image dataset to medical image tasks. In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computer-aided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks.
Transfer of learning
Contextual image classification
Cite
Citations (5,109)
Pneumonia ranks as a leading cause of mortality, particularly in children aged five and under. Detecting this disease typically requires radiologists to examine chest X-rays and report their findings to physicians, a task susceptible to human error. The application of Deep Transfer Learning (DTL) for the identification of pneumonia through chest X-rays is hindered by a shortage of available images, which has led to less than optimal DTL performance and issues with overfitting. Overfitting is characterized by a model’s learning that is too closely fitted to the training data, reducing its effectiveness on unseen data. The problem of overfitting is especially prevalent in medical image processing due to the high costs and extensive time required for image annotation, as well as the challenge of collecting substantial datasets that also respect patient privacy concerning infectious diseases such as pneumonia. To mitigate these challenges, this paper introduces the use of conditional generative adversarial networks (CGAN) to enrich the pneumonia dataset with 2690 synthesized X-ray images of the minority class, aiming to even out the dataset distribution for improved diagnostic performance. Subsequently, we applied four modified lightweight deep transfer learning models such as Xception, MobileNetV2, MobileNet, and EfficientNetB0. These models have been fine-tuned and evaluated, demonstrating remarkable detection accuracies of 99.26%, 98.23%, 97.06%, and 94.55%, respectively, across fifty epochs. The experimental results validate that the models we have proposed achieve high detection accuracy rates, with the best model reaching up to 99.26% effectiveness, outperforming other models in the diagnosis of pneumonia from X-ray images.
Overfitting
Transfer of learning
Economic shortage
Cite
Citations (0)
: Dental panoramic radiographs (DPRs) provide information required to potentially evaluate bone density changes through a textural and morphological feature analysis on a mandible. This study aims to evaluate the discriminating performance of deep convolutional neural networks (CNNs), employed with various transfer learning strategies, on the classification of specific features of osteoporosis in DPRs. For objective labeling, we collected a dataset containing 680 images from different patients who underwent both skeletal bone mineral density and digital panoramic radiographic examinations at the Korea University Ansan Hospital between 2009 and 2018. Four study groups were used to evaluate the impact of various transfer learning strategies on deep CNN models as follows: a basic CNN model with three convolutional layers (CNN3), visual geometry group deep CNN model (VGG-16), transfer learning model from VGG-16 (VGG-16_TF), and fine-tuning with the transfer learning model (VGG-16_TF_FT). The best performing model achieved an overall area under the receiver operating characteristic of 0.858. In this study, transfer learning and fine-tuning improved the performance of a deep CNN for screening osteoporosis in DPR images. In addition, using the gradient-weighted class activation mapping technique, a visual interpretation of the best performing deep CNN model indicated that the model relied on image features in the lower left and right border of the mandibular. This result suggests that deep learning-based assessment of DPR images could be useful and reliable in the automated screening of osteoporosis patients.
Transfer of learning
Cite
Citations (146)
This study aims to evaluate the performance of different deep learning methods based on CNN (Convolutional Neural Networks) for hand-gun detection from images. Within the context of object detection, which is an application of CNN, this study further focusses on hand-gun detection from images. The application of a CNN trained from scratch, transfer learning method using VGG-16 (Visual Geometry Group) model and fine-tuning based on the same model are applied on the same image dataset and the results are evaluated using various evaluation metrics. The results on 8300 images with and without a hand-gun showed that the highest accuracies are obtained with fine tuning method. Besides, it has been observed that the CNN model obtained with fine-tuning method gave balanced accuracies on the images containing and not containing hand-gun.
Transfer of learning
Scratch
Contextual image classification
Cite
Citations (5)
COVID-19 originated in Wuhan, China, in December 2019 and quickly became a global outbreak in January 2020. COVID-19 is a disease caused by SARS-CoV-2, which is a human transmission disease. Since it is a human transmission disease, thus mass gathering in public is not allowed to prevent the possible spread of COVID-19. However, the current monitoring technology, such as closed-circuit television (CCTV), only cover a limited area of the public and lack of mobility. Image classification is one of the approaches that can detect crowds in an image and can be done through either machine learning or deep learning approach. Recently, deep learning, especially convolutional neural networks (CNNs) outperform classical machine learning in image classification and the common approach for modelling CNN is through transfer learning. Thus, this study aims to develop a convolutional neural network that can detect illegal crowd gathering from offline drone view images through image classification using the transfer learning technique. Several models are used to train on the same dataset obtained, and the all-model performance is evaluated through a confusion matrix. Based on performance analysis, it shows that the ResNet50 model outperforms the VGG16 model and InceptionV3 model by achieving 95% test accuracy, 95% precision, 95% recall and 95% F1-score. In conclusion, it can be concluded that the deep learning approach uses a pre-trained convolutional neural network that can be used to classify object images in this study.
Transfer of learning
Confusion matrix
Cite
Citations (0)
Deep learning has made spectacular achievements in analysing natural images, but it faces challenges for medical applications partly due to inadequate images.Aiming to classify malignant and benign pulmonary nodules using CT images, we explore different strategies to utilize the state-of-the-art deep convolutional neural networks (CNN).Experiments are conducted using the Lung Image Database Consortium image collection (LIDC-IDRI), which is a public database containing 1018 cases. Three strategies are implemented including to 1) modify some state-of-the-art CNN architectures, 2) integrate different CNNs and 3) adopt transfer learning. Totally, 11 deep CNN models are compared using the same dataset.Study demonstrates that, for the model modification scheme, a concise CifarNet performs better than the other modified CNNs with more complex architectures, achieving an area under ROC curve of AUC = 0.90. Integrated CNN models do not significantly improve the classification performance, but the model complexity is reduced. Transfer learning outperforms the other two schemes and ResNet with fine-tuning leads to the best performance with an AUC = 0.94, as well as the sensitivity of 91% and an overall accuracy of 88%.Model modification, model integration, and transfer learning can play important roles to identify and generate optimal deep CNN models in classifying pulmonary nodules based on CT images efficiently. Transfer learning is preferred when applying deep learning to medical imaging applications.
Transfer of learning
Cite
Citations (54)