• Journal of Broadcast Engineering
• /
• v.22 no.2
• /
• pp.162-172
• /
• 2017

In this paper, we propose facial expression recognition using CNN (Convolutional Neural Network), one of the deep learning technologies. To overcome the disadvantages of existing facial expression databases, various databases are used. In the proposed technique, we construct six facial expression data sets such as 'expressionless', 'happiness', 'sadness', 'angry', 'surprise', and 'disgust'. Pre-processing and data augmentation techniques are also applied to improve efficient learning and classification performance. In the existing CNN structure, the optimal CNN structure that best expresses the features of six facial expressions is found by adjusting the number of feature maps of the convolutional layer and the number of fully-connected layer nodes. Experimental results show that the proposed scheme achieves the highest classification performance of 96.88% while it takes the least time to pass through the CNN structure compared to other models.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.341-350
• /
• 2022

In this paper, we propose a deep learning based on-device augmented reality (AR) system in which multiple input images are used to implement the correct occlusion in a real environment. The proposed system is composed of three technical steps; camera pose estimation, depth estimation, and object augmentation. Each step employs various mobile frameworks to optimize the processing on the on-device environment. Firstly, in the camera pose estimation stage, the massive computation involved in feature extraction is parallelized using OpenCL which is the GPU parallelization framework. Next, in depth estimation, monocular and multiple image-based depth image inference is accelerated using the mobile deep learning framework, i.e. TensorFlow Lite. Finally, object augmentation and occlusion handling are performed on the OpenGL ES mobile graphics framework. The proposed augmented reality system is implemented as an application in the Android environment. We evaluate the performance of the proposed system in terms of augmentation accuracy and the processing time in the mobile as well as PC environments.

• Journal of the Korea Institute of Building Construction
• /
• v.23 no.2
• /
• pp.197-207
• /
• 2023

Concrete is a widely used material due to its excellent compressive strength and durability. However, depending on the surrounding environment and the characteristics of the materials used in the construction, various defects may occur, such as cracks on the surface and subsidence of the structure. The detects on the surface of the concrete structure occur after completion or over time. Neglecting these cracks may lead to severe structural damage, necessitating regular safety inspections. Traditional visual inspections of concrete walls are labor-intensive and expensive. This research presents a deep learning-based semantic segmentation model designed to detect cracks in concrete walls. The model addresses surface defects that arise from aging, and an image augmentation technique is employed to enhance feature extraction and generalization performance. A dataset for semantic segmentation was created by combining publicly available and self-generated datasets, and notable semantic segmentation models were evaluated and tested. The model, specifically trained for concrete wall fracture detection, achieved an extraction performance of 81.4%. Moreover, a 3% performance improvement was observed when applying the developed augmentation technique.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.1
• /
• pp.147-165
• /
• 2021

In this work, we empirically evaluated the efficiency of the recent EfficientNetB0 model to identify and diagnose malaria parasite infections in blood smears. The dataset used was collected and classified by relevant experts from the Lister Hill National Centre for Biomedical Communications (LHNCBC). We prepared our samples with minimal image transformations as opposed to others, as we focused more on the feature extraction capability of the EfficientNetB0 baseline model. We applied transfer learning to increase the initial feature sets and reduced the training time to train our model. We then fine-tuned it to work with our proposed layers and re-trained the entire model to learn from our prepared dataset. The highest overall accuracy attained from our evaluated results was 94.70% from fifty epochs and followed by 94.68% within just ten. Additional visualization and analysis using the Gradient-weighted Class Activation Mapping (Grad-CAM) algorithm visualized how effectively our fine-tuned EfficientNetB0 detected infections better than other recent state-of-the-art DCNN models. This study, therefore, concludes that when fine-tuned, the recent EfficientNetB0 will generate highly accurate deep learning solutions for the identification of malaria parasites in blood smears without the need for stringent pre-processing, optimization, or data augmentation of images.

• Phonetics and Speech Sciences
• /
• v.15 no.2
• /
• pp.53-59
• /
• 2023

Detection of children with autism spectrum disorder (ASD) based on speech has relied on predefined feature sets due to their ease of use and the capabilities of speech analysis. However, clinical impressions may not be adequately captured due to the broad range and the large number of features included. This paper demonstrates that the knowledge-driven speech features (KDSFs) specifically tailored to the speech traits of ASD are more effective and efficient for detecting speech of ASD children from that of children with typical development (TD) than a predefined feature set, extended Geneva Minimalistic Acoustic Standard Parameter Set (eGeMAPS). The KDSFs encompass various speech characteristics related to frequency, voice quality, speech rate, and spectral features, that have been identified as corresponding to certain of their distinctive attributes of them. The speech dataset used for the experiments consists of 63 ASD children and 9 TD children. To alleviate the imbalance in the number of training utterances, a data augmentation technique was applied to TD children's utterances. The support vector machine (SVM) classifier trained with the KDSFs achieved an accuracy of 91.25%, surpassing the 88.08% obtained using the predefined set. This result underscores the importance of incorporating domain knowledge in the development of speech technologies for individuals with disorders.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.56-60
• /
• 2023

기존의 음성인식은 청장년 층에 초점이 맞추어져 있었으나, 최근 고령화가 가속되면서 노인 음성에 대한 연구 필요성이 증대되고 있다. 그러나 노인 음성 데이터셋은 청장년 음성 데이터셋에 비해서는 아직까지 충분히 확보되지 못하고 있다. 본 연구에서는 부족한 노인 음성 데이터셋 확보에 기여하고자 희소한 노인 데이터셋을 증강할 수 있는 방법론에 대해 연구하였다. 이를 위해 노인 음성 특징(feature)을 분석하였으며, '주파수'와 '발화 속도' 특징을 일반 성인 음성에 합성하여 데이터를 증강하였다. 이후 Whisper small 모델을 파인 튜닝한 뒤 노인 음성에 대한 CER(Character Error Rate)를 구하였고, 기존 노인 데이터셋에 증강한 데이터셋을 함께 사용하는 것이 가장 효과적임을 밝혀내었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.605-607
• /
• 2023

Recent research has highlighted the effectiveness of Deep Learning (DL) techniques in automating the detection of lung sound anomalies. However, the available lung sound datasets often suffer from limitations in both size and balance, prompting DL methods to employ data preprocessing such as augmentation and transfer learning techniques. These strategies, while valuable, contribute to the increased complexity of DL models and necessitate substantial training memory. In this study, we proposed a streamlined and lightweight DL method but effectively detects lung sound anomalies from small and imbalanced dataset. The utilization of 1D dilated convolutional neural networks enhances sensitivity to lung sound anomalies by efficiently capturing deep temporal features and small variations. We conducted a comprehensive evaluation of the ICBHI dataset and achieved a notable improvement over state-of-the-art results, increasing the average score of sensitivity and specificity metrics by 2.7%.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.2
• /
• pp.84-91
• /
• 2009

This paper presents an online partial 3D modeling methodology that uses a mobile augmented reality system and aerial photographs, and a tracking methodology that compares the 3D model with a video image. Instead of relying on models which are created in advance, the system generates a 3D model for a real building on the fly by combining frontal and aerial views. A user's initial pose is estimated using an aerial photograph, which is retrieved from a database according to the user's GPS coordinates, and an inertial sensor which measures pitch. We detect edges of the rooftop based on Graph cut, and find edges and a corner of the bottom by minimizing the proposed cost function. To track the user's position and orientation in real-time, feature-based tracking is carried out based on salient points on the edges and the sides of a building the user is keeping in view. We implemented camera pose estimators using both a least squares estimator and an unscented Kalman filter (UKF). We evaluated the speed and accuracy of both approaches, and we demonstrated the usefulness of our computations as important building blocks for an Anywhere Augmentation scenario.

• Journal of Platform Technology
• /
• v.10 no.4
• /
• pp.47-55
• /
• 2022

Recently, diverse devices using different wireless technologies are gradually increasing in the IoT environment. In particular, it is essential to design an efficient feature extraction approach and detect the exact types of radio signals in order to accurately identify various radio signal modulation techniques. However, it is difficult to gather labeled wireless signal in a real environment due to the complexity of the process. In addition, various learning techniques based on deep learning have been proposed for wireless signal classification. In the case of deep learning, if the training dataset is not enough, it frequently meets the overfitting problem, which causes performance degradation of wireless signal classification techniques using deep learning models. In this paper, we propose a generative adversarial network(GAN) based on data augmentation techniques to improve classification performance when various wireless signals exist. When there are various types of wireless signals to be classified, if the amount of data representing a specific radio signal is small or unbalanced, the proposed solution is used to increase the amount of data related to the required wireless signal. In order to verify the validity of the proposed data augmentation algorithm, we generated the additional data for the specific wireless signal and implemented a CNN and LSTM-based wireless signal classifier based on the result of balancing. The experimental results show that the classification accuracy of the proposed solution is higher than when the data is unbalanced.

• The KIPS Transactions:PartB
• /
• v.13B no.5 s.108
• /
• pp.499-506
• /
• 2006

This Paper describes a fast and stable camera pose estimation method for real-time augmented reality systems. From the feature tracking results of a marker on a single frame, we estimate the camera rotation matrix and the translation vector. For the camera pose estimation, we use the shape factorization method based on the scaled orthographic Projection model. In the scaled orthographic factorization method, all feature points of an object are assumed roughly at the same distance from the camera, which means the selected reference point and the object shape affect the accuracy of the estimation. This paper proposes a flexible and stable selection method for the reference point. Based on the proposed method, we implemented a video augmentation system that inserts virtual 3D objects into the input video frames. Experimental results showed that the proposed camera pose estimation method is fast and robust relative to the previous methods and it is applicable to various augmented reality applications.