• Journal of the Korea Society of Computer and Information
• /
• v.27 no.4
• /
• pp.19-26
• /
• 2022

With the recent development of intelligent transportation systems, car license plate recognition systems are being used in various fields. Such systems need to guarantee real-time performance to recognize the license plate of a driving car. Also, they should keep a high recognition rate even in problematic situations such as small license plates in low-resolution and unclear image due to distortion. In this paper, we propose a real-time car license plate recognition system that improved processing speed using object detection algorithm based on anchor-free method and text recognition algorithm based on Convolutional Neural Network(CNN). In addition, we used Spatial Transformer Network to increase the recognition rate on the low resolution or distorted images. We confirm that the proposed system is faster than previously existing car license plate recognition systems and maintains a high recognition rate in a variety of environment and quality images because the proposed system's recognition rate is 93.769% and the processing speed per image is about 0.006 seconds.

• Imaging Science in Dentistry
• /
• v.52 no.3
• /
• pp.239-244
• /
• 2022

Purpose: Despite the proliferation of numerous morphometric and anthropometric methods for sex identification based on linear, angular, and regional measurements of various parts of the body, these methods are subject to error due to the observer's knowledge and expertise. This study aimed to explore the possibility of automated sex determination using convolutional neural networks(CNNs) based on lateral cephalometric radiographs. Materials and Methods: Lateral cephalometric radiographs of 1,476 Iranian subjects (794 women and 682 men) from 18 to 49 years of age were included. Lateral cephalometric radiographs were considered as a network input and output layer including 2 classes(male and female). Eighty percent of the data was used as a training set and the rest as a test set. Hyperparameter tuning of each network was done after preprocessing and data augmentation steps. The predictive performance of different architectures (DenseNet, ResNet, and VGG) was evaluated based on their accuracy in test sets. Results: The CNN based on the DenseNet121 architecture, with an overall accuracy of 90%, had the best predictive power in sex determination. The prediction accuracy of this model was almost equal for men and women. Furthermore, with all architectures, the use of transfer learning improved predictive performance. Conclusion: The results confirmed that a CNN could predict a person's sex with high accuracy. This prediction was independent of human bias because feature extraction was done automatically. However, for more accurate sex determination on a wider scale, further studies with larger sample sizes are desirable.

• Journal of Digital Policy
• /
• v.2 no.3
• /
• pp.1-7
• /
• 2023

In this paper, I proposes a method for performing single image super resolution by separating texture-spatial domains and then classifying features based on detailed information. In CNN (Convolutional Neural Network) based super resolution, the complex procedures and generation of redundant feature information in feature estimation process for enhancing details can lead to quality degradation in super resolution. The proposed method reduced procedural complexity and minimizes generation of redundant feature information by splitting input image into two channels: texture and spatial. In texture channel, a feature refinement process with step-wise skip connections is applied for detail restoration, while in spatial channel, a method is introduced to preserve the structural features of the image. Experimental results using proposed method demonstrate improved performance in terms of PSNR and SSIM evaluations compared to existing super resolution methods, confirmed the enhancement in quality.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.1188-1203
• /
• 2020

The human expression contains a lot of information that can be used to detect complex conditions such as pain and fatigue. After deep learning became the mainstream method, the traditional feature extraction method no longer has advantages. However, in order to achieve higher accuracy, researchers continue to stack the number of layers of the neural network, which makes the real-time performance of the model weak. Therefore, this paper proposed an expression recognition framework based on densely concatenated convolutional neural networks to balance accuracy and latency and apply it to humanoid robots. The techniques of feature reuse and parameter compression in the framework improved the learning ability of the model and greatly reduced the parameters. Experiments showed that the proposed model can reduce tens of times the parameters at the expense of little accuracy.

• Journal of Information Processing Systems
• /
• v.20 no.3
• /
• pp.375-390
• /
• 2024

Edge computing architecture has effectively alleviated the computing pressure on cloud platforms, reduced network bandwidth consumption, and improved the quality of service for user experience; however, it has also introduced new security issues. Existing anomaly detection methods in big data scenarios with cloud-edge computing collaboration face several challenges, such as sample imbalance, difficulty in dealing with complex network traffic attacks, and difficulty in effectively training large-scale data or overly complex deep-learning network models. A lightweight deep-learning model was proposed to address these challenges. First, normalization on the user side was used to preprocess the traffic data. On the edge side, a trained Wasserstein generative adversarial network (WGAN) was used to supplement the data samples, which effectively alleviates the imbalance issue of a few types of samples while occupying a small amount of edge-computing resources. Finally, a trained lightweight deep learning network model is deployed on the edge side, and the preprocessed and expanded local data are used to fine-tune the trained model. This ensures that the data of each edge node are more consistent with the local characteristics, effectively improving the system's detection ability. In the designed lightweight deep learning network model, two sets of convolutional pooling layers of convolutional neural networks (CNN) were used to extract spatial features. The bidirectional long short-term memory network (BiLSTM) was used to collect time sequence features, and the weight of traffic features was adjusted through the attention mechanism, improving the model's ability to identify abnormal traffic features. The proposed model was experimentally demonstrated using the NSL-KDD, UNSW-NB15, and CIC-ISD2018 datasets. The accuracies of the proposed model on the three datasets were as high as 0.974, 0.925, and 0.953, respectively, showing superior accuracy to other comparative models. The proposed lightweight deep learning network model has good application prospects for anomaly traffic detection in cloud-edge collaborative computing architectures.

• Journal of Technologic Dentistry
• /
• v.46 no.2
• /
• pp.36-41
• /
• 2024

Purpose: This study aimed to generate virtual mandibular left first molar teeth using deep convolutional generative adversarial networks (DCGANs) and analyze their matching accuracy with actual tooth morphology to propose a new paradigm for using medical data. Methods: Occlusal surface images of the mandibular left first molar scanned using a dental model scanner were analyzed using DCGANs. Overall, 100 training sets comprising 50 original and 50 background-removed images were created, thus generating 1,000 virtual teeth. These virtual teeth were classified based on the number of cusps and occlusal surface ratio, and subsequently, were analyzed for consistency by expert dental technicians over three rounds of examination. Statistical analysis was conducted using IBM SPSS Statistics ver. 23.0 (IBM), including intraclass correlation coefficient for intrarater reliability, one-way ANOVA, and Tukey's post-hoc analysis. Results: Virtual mandibular left first molars exhibited high consistency in the occlusal surface ratio but varied in other criteria. Moreover, consistency was the highest in the occlusal buccal lingual criteria at 91.9%, whereas discrepancies were observed most in the occusal buccal cusp criteria at 85.5%. Significant differences were observed among all groups (p<0.05). Conclusion: Based on the classification of the virtually generated left mandibular first molar according to several criteria, DCGANs can generate virtual data highly similar to real data. Thus, subsequent research in the dental field, including the development of improved neural network structures, is necessary.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.3
• /
• pp.148-153
• /
• 2020

In order to obtain high accuracy with an convolutional neural network(CNN), it is necessary to set the optimal hyperparameters. However, the exact value of the hyperparameter that can make high performance is not known, and the optimal hyperparameter value is different based on the type of the dataset, therefore, it is necessary to find it through various experiments. In addition, since the range of hyperparameter values is wide and the number of combinations is large, it is necessary to find the optimal values of the hyperparameters after the experimental design in order to save time and computational costs. In this paper, we suggest an algorithm that use the design of experiments and grid search algorithm to determine the optimal hyperparameters for a classification problem. This algorithm determines the optima values of the hyperparameters that yields high performance using the factorial design of experiments. It is shown that the amount of computational time can be efficiently reduced and the accuracy can be improved by performing a grid search after reducing the search range of each hyperparameter through the experimental design. Moreover, Based on the experimental results, it was shown that the learning rate is the only hyperparameter that has the greatest effect on the performance of the model.

• Journal of Korea Multimedia Society
• /
• v.21 no.8
• /
• pp.888-896
• /
• 2018

In this paper, we report detection and recognition of vehicle logo from images captured from street CCTV. Image data includes both the front and rear view of the vehicles. The proposed method is a two-step process which combines image preprocessing and faster region-based convolutional neural network (R-CNN) for logo recognition. Without preprocessing, faster R-CNN accuracy is high only if the image quality is good. The proposed system is focusing on street CCTV camera where image quality is different from a front facing camera. Using perspective transformation the top view images are transformed into front view images. In this system, the detection and accuracy are much higher as compared to the existing algorithm. As a result of the experiment, on day data the detection and recognition rate is improved by 2% and night data, detection rate improved by 14%.

• Smart Structures and Systems
• /
• v.29 no.3
• /
• pp.421-431
• /
• 2022

Concrete slab cracks monitoring of modern high-speed railway is important for safety and reliability of train operation, to prevent catastrophic failure, and to reduce maintenance costs. This paper proposes a curvature filtering improved crack detection method in concrete slabs of high-speed railway via graph-based anomalies calculation. Firstly, large curvature information contained in the images is extracted for the crack identification based on an improved curvature filtering method. Secondly, a graph-based model is developed for the image sub-blocks anomalies calculation where the baseline of the sub-blocks is acquired by crack-free samples. Once the anomaly is large than the acquired baseline, the sub-block is considered as crack-contained block. The experimental results indicate that the proposed method performs better than convolutional neural network method even under different curvature structures and illumination conditions. This work therefore provides a useful tool for concrete slabs crack detection and is broadly applicable to variety of infrastructure systems.

• Journal of the Korean Society of Radiology
• /
• v.18 no.5
• /
• pp.541-549
• /
• 2024

The various structures of artificial neural networks, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), have been extensively studied and served as the backbone of numerous models. Among these, a transformer architecture has demonstrated its potential for natural language processing and become a subject of in-depth research. Currently, the techniques can be adapted for image processing through the modifications of its internal structure, leading to the development of Vision transformer (ViT) models. The ViTs have shown high accuracy and performance with large data-sets. This study aims to develop a ViT-based model for detecting pneumonia using chest X-ray images and quantitatively evaluate its performance. The various architectures of the ViT-based model were constructed by varying the number of encoder blocks, and different patch sizes were applied for network training. Also, the performance of the ViT-based model was compared to the CNN-based models, such as VGGNet, GoogLeNet, and ResNet. The results showed that the traninig efficiency and accuracy of the ViT-based model depended on the number of encoder blocks and the patch size, and the F1 scores of the ViT-based model ranged from 0.875 to 0.919. The training effeciency of the ViT-based model with a large patch size was superior to the CNN-based models, and the pneumonia detection accuracy of the ViT-based model was higher than that of the VGGNet. In conclusion, the ViT-based model can be potentially used for pneumonia detection using chest X-ray images, and the clinical availability of the ViT-based model would be improved by this study.