• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.4
• /
• pp.205-212
• /
• 2024

This study developed a deep learning model that distinguishes the front (with garnish) and the back (without garnish) surface of the dried semi-finished product (dried bukak) for screening operation before transfter the dried bukak to oil heater using robot's vacuum gripper. For deep learning model training and verification, RGB images for the front and back surfaces of 400 dry bukak that treated by data preproccessing were obtained. YOLO-v5 was used as a base structure of deep learning model. The area, surface information labeling, and data augmentation techniques were applied from the acquired image. Parameters including mAP, mIoU, accumulation, recall, decision, and F1-score were selected to evaluate the performance of the developed YOLO-v5 deep learning model-based surface detection model. The mAP and mIoU on the front surface were 0.98 and 0.96, respectively, and on the back surface, they were 1.00 and 0.95, respectively. The results of binary classification for the two front and back classes were average 98.5%, recall 98.3%, decision 98.6%, and F1-score 98.4%. As a result, the developed model can classify the surface information of the dried bukak using RGB images, and it can be used to develop a robot-automated system for the surface detection process of the dried bukak before deep frying.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.10
• /
• pp.21-34
• /
• 2024

In medical images such as MRI(Magnetic Resonance Imaging) and CT(Computed Tomography) images, noise removal has a significant impact on the performance of medical imaging systems. Recently, the introduction of deep learning in image processing technology has improved the performance of noise removal methods. However, there is a limit to removing only noise while preserving details in the image domain. In this paper, we propose a wavelet transform-based CNN(Convolutional Neural Network) model, namely the WT-DnCNN(Wavelet Transform-Denoising Convolutional Neural Network) model, to improve noise removal performance. This model first removes noise by dividing the noisy image into frequency bands using wavelet transform, and then applies the existing DnCNN model to the corresponding frequency bands to finally remove noise. In order to evaluate the performance of the WT-DnCNN model proposed in this paper, experiments were conducted on MRI and CT images damaged by various noises, namely Gaussian noise, Poisson noise, and speckle noise. The performance experiment results show that the WT-DnCNN model is superior to the traditional filter, i.e., the BM3D(Block-Matching and 3D Filtering) filter, as well as the existing deep learning models, DnCNN and CDAE(Convolution Denoising AutoEncoder) model in qualitative comparison, and in quantitative comparison, the PSNR(Peak Signal-to-Noise Ratio) and SSIM(Structural Similarity Index Measure) values were 36~43 and 0.93~0.98 for MRI images and 38~43 and 0.95~0.98 for CT images, respectively. In addition, in the comparison of the execution speed of the models, the DnCNN model was much less than the BM3D model, but it took a long time due to the addition of the wavelet transform in the comparison with the DnCNN model.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.3
• /
• pp.70-77
• /
• 2017

Recently, Internet of Things (IoT) and deep learning techniques have affected video surveillance systems in various ways. The surveillance features that perform detection, tracking, and classification of specific objects in Closed Circuit Television (CCTV) video are becoming more intelligent. This paper presents real-time algorithm that can run in a PC environment using only a low power CPU. Traditional tracking algorithms combine background modeling using the Gaussian Mixture Model (GMM), Hungarian algorithm, and a Kalman filter; they have relatively low complexity but high detection errors. To supplement this, deep learning technology was used, which can be trained from a large amounts of data. In particular, an SRGB(Sequential RGB)-3 Layer CNN was used on tracked objects to emphasize the features of moving people. Performance evaluation comparing the proposed algorithm with existing ones using HOG and SVM showed move-in and move-out error rate reductions by 7.6 % and 9.0 %, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.11-18
• /
• 2020

This study proposes a technique for the determination of outlet blockage using deep learning in a conveyor system. The proposed method aims to apply the best model to the actual process, where we train various CNN models for the determination of outlet blockage using images collected by CCTV in an industrial scene. We used the well-known CNN model such as VGGNet, ResNet, DenseNet and NASNet, and used 18,000 images collected by CCTV for model training and performance evaluation. As a experiment result with various models, VGGNet showed the best performance with 99.03% accuracy and 29.05ms processing time, and we confirmed that VGGNet is suitable for the determination of outlet blockage.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.439-451
• /
• 2021

We propose a deep learning-based beamformer combined with spectral subtraction for continuous speech recognition operating in noisy environments. Conventional beamforming systems were mostly evaluated by using pre-segmented audio signals which were typically generated by mixing speech and noise continuously on a computer. However, since speech utterances are sparsely uttered along the time axis in real environments, conventional beamforming systems degrade in case when noise-only signals without speech are input. To alleviate this drawback, we combine online beamforming algorithm and spectral subtraction. We construct a Continuous Speech Enhancement (CSE) evaluation set to evaluate the online beamforming algorithm in noisy environments. The evaluation set is built by mixing sparsely-occurring speech utterances of the CHiME3 evaluation set and continuously-played CHiME3 background noise and background music of MUSDB. Using a Kaldi-based toolkit and Google web speech recognizer as a speech recognition back-end, we confirm that the proposed online beamforming algorithm with spectral subtraction shows better performance than the baseline online algorithm.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1141-1147
• /
• 2020

The hornet species are so similar in shape that they are difficult for non-experts to classify, and because the size of the objects is small and move fast, it is more difficult to detect and classify the species in real time. In this paper, we developed a system that classifies hornets species in real time based on a deep learning algorithm using a boundary box. In order to minimize the background area included in the bounding box when labeling the training image, we propose a method of selecting only the head and body of the hornet. It also experimentally compares existing boundary box-based object recognition algorithms to find the best algorithms that can detect wasps in real time and classify their species. As a result of the experiment, when the mish function was applied as the activation function of the convolution layer and the hornet images were tested using the YOLOv4 model with the Spatial Attention Module (SAM) applied before the object detection block, the average precision was 97.89% and the average recall was 98.69%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.44-49
• /
• 2021

Recently, due to COVID-19, studies have been popularly worked to apply neural network to mask wearing automatic detection system. For applying neural networks, the 1-stage detection or 2-stage detection methods are used, and if data are not sufficiently collected, the pretrained neural network models are studied by applying fine-tuning techniques. In this paper, the system is consisted of 2-stage detection method that contain MTCNN model for face recognition and ResNet model for mask detection. The mask detector was experimented by applying five ResNet models to improve accuracy and fps in various environments. Training data used 17,217 images that collected using web crawler, and for inference, we used 1,913 images and two one-minute videos respectively. The experiment showed a high accuracy of 96.39% for images and 92.98% for video, and the speed of inference for video was 10.78fps.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.9-16
• /
• 2024

It is difficult to know the efficacy of pills if the pill bag or wrapper is lost after purchasing the pill. Many people do not classify the use of commercial pills when storing them after purchasing and taking them, so the inaccessibility of information on the side effects of pills leads to misuse of pills. Even with existing applications that search and provide information about pills, users have to select the details of the pills themselves. In this paper, we develope a pill recognition application by building a model that learns the formulation and colour of 22,000 photos of pills provided by a Pharmaceutical Information Institution to solve the above situation. We also develope a pill medication management function.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.4
• /
• pp.35-42
• /
• 2024

In this study, we propose a method for real-time recognition and analysis of dog behavior using a motion sensor and deep learning techonology. The existing home CCTV (Closed-Circuit Television) that recognizes dog behavior has privacy and security issues, so there is a need for new technologies to overcome them. In this paper, we propose a system that can analyze and care for a dog's behavior based on the data measured by the motion sensor. The study compares the MLP (Multi-Layer Perceptron) and CNN (Convolutional Neural Network) models to find the optimal model for dog behavior analysis, and the final model, which has an accuracy of about 82.19%, is selected. The model is lightened to confirm its potential for use in embedded environments.

• Journal of Digital Convergence
• /
• v.19 no.10
• /
• pp.295-301
• /
• 2021

Individual mental fatigue not only reduces cognitive ability and work performance, but also becomes a major factor in large and small accidents occurring in daily life. In this paper, a CNN model for EEG-based mental fatigue discrimination was proposed. To this end, EEG in the resting state and task state were collected and applied to the proposed CNN model, and then the model performance was analyzed. All subjects who participated in the experiment were right-handed male students attending university, with and average age of 25.5 years. Spectral analysis was performed on the measured EEG in each state, and the performance of the CNN model was compared and analyzed using the raw EEG, absolute power, and relative power as input data of the CNN model. As a result, the relative power of the occipital lobe position in the alpha band showed the best performance. The model accuracy is 85.6% for training data, 78.5% for validation, and 95.7% for test data. The proposed model can be applied to the development of an automated system for mental fatigue detection.