• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.686-689
• /
• 2018

3D 손 포즈 추정(Hand Pose Estimation, HPE)은 스마트 인간 컴퓨터 인터페이스를 위해서 중요한 기술이다. 이 연구에서는 딥러닝 방법을 기반으로 하여 단일 RGB-Depth 카메라로 촬영한 양손의 3D 손 자세를 실시간으로 인식하는 손 포즈 추정 시스템을 제시한다. 손 포즈 추정 시스템은 4단계로 구성된다. 첫째, Skin Detection 및 Depth cutting 알고리즘을 사용하여 양손을 RGB와 깊이 영상에서 감지하고 추출한다. 둘째, Convolutional Neural Network(CNN) Classifier는 오른손과 왼손을 구별하는데 사용된다. CNN Classifier 는 3개의 convolution layer와 2개의 Fully-Connected Layer로 구성되어 있으며, 추출된 깊이 영상을 입력으로 사용한다. 셋째, 학습된 CNN regressor는 추출된 왼쪽 및 오른쪽 손의 깊이 영상에서 손 관절을 추정하기 위해 다수의 Convolutional Layers, Pooling Layers, Fully Connected Layers로 구성된다. CNN classifier와 regressor는 22,000개 깊이 영상 데이터셋으로 학습된다. 마지막으로, 각 손의 3D 손 자세는 추정된 손 관절 정보로부터 재구성된다. 테스트 결과, CNN classifier는 오른쪽 손과 왼쪽 손을 96.9%의 정확도로 구별할 수 있으며, CNN regressor는 형균 8.48mm의 오차 범위로 3D 손 관절 정보를 추정할 수 있다. 본 연구에서 제안하는 손 포즈 추정 시스템은 가상 현실(virtual reality, VR), 증강 현실(Augmented Reality, AR) 및 융합 현실 (Mixed Reality, MR) 응용 프로그램을 포함한 다양한 응용 분야에서 사용할 수 있다.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.151-160
• /
• 2023

Breast cancer is the most dangerous and deadly form of cancer. Initial detection of breast cancer can significantly improve treatment effectiveness. The second most common cancer among Indian women in rural areas. Early detection of symptoms and signs is the most important technique to effectively treat breast cancer, as it enhances the odds of receiving an earlier, more specialist care. As a result, it has the possible to significantly improve survival odds by delaying or entirely eliminating cancer. Mammography is a high-resolution radiography technique that is an important factor in avoiding and diagnosing cancer at an early stage. Automatic segmentation of the breast part using Mammography pictures can help reduce the area available for cancer search while also saving time and effort compared to manual segmentation. Autoencoder-like convolutional and deconvolutional neural networks (CN-DCNN) were utilised in previous studies to automatically segment the breast area in Mammography pictures. We present Automatic SegmenAN, a unique end-to-end adversarial neural network for the job of medical image segmentation, in this paper. Because image segmentation necessitates extensive, pixel-level labelling, a standard GAN's discriminator's single scalar real/fake output may be inefficient in providing steady and appropriate gradient feedback to the networks. Instead of utilising a fully convolutional neural network as the segmentor, we suggested a new adversarial critic network with a multi-scale L1 loss function to force the critic and segmentor to learn both global and local attributes that collect long- and short-range spatial relations among pixels. We demonstrate that an Automatic SegmenAN perspective is more up to date and reliable for segmentation tasks than the state-of-the-art U-net segmentation technique.

• Smart Media Journal
• /
• v.11 no.1
• /
• pp.31-37
• /
• 2022

This paper proposes a study on applying signal processing and deep learning for sound recognition that detects sounds commonly heard in daily life (Screaming, Clapping, Crowd_clapping, Car_passing_by and Back_ground, etc.). In the proposed sound recognition, several techniques related to the spectrum of sound waves, augmentation of sound data, ensemble learning for various predictions, convolutional neural networks (CNN) deep learning, and two-dimensional (2-D) data are used for improving the recognition accuracy. The proposed sound recognition technology shows that it can accurately recognize various sounds through experiments.

• Journal of Multimedia Information System
• /
• v.9 no.1
• /
• pp.1-10
• /
• 2022

China is a big country in animal fur industry. The total production and consumption of fur are increasing year by year. However, the recognition of fur in the fur production process still mainly relies on the visual identification of skilled workers, and the stability and consistency of products cannot be guaranteed. In response to this problem, this paper proposes a feature fusion-based animal fur recognition network on the basis of typical convolutional neural network structure, relying on rapidly developing deep learning techniques. This network superimposes texture feature - the most prominent feature of fur image - into the channel dimension of input image. The output feature map of the first layer convolution is inverted to obtain the inverted feature map and concat it into the original output feature map, then Leaky ReLU is used for activation, which makes full use of the texture information of fur image and the inverted feature information. Experimental results show that the algorithm improves the recognition accuracy by 9.08% on Fur_Recognition dataset and 6.41% on CIFAR-10 dataset. The algorithm in this paper can change the current situation that fur recognition relies on manual visual method to classify, and can lay foundation for improving the efficiency of fur production technology.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.15-17
• /
• 2021

Handwriting recognition research is mainly focused on deep learning techniques and has achieved a great performance in the last few years. Especially, handwritten Thai digit recognition has been an important research area including generic digital numerical information, such as Thai official government documents and receipts. However, it becomes also a challenging task for a long time. For resolving the unavailability of a large Thai digit dataset, this paper constructs our dataset and learns them with some variants of the CNN model; Decision tree, K-nearest neighbors, Alexnet, LaNet-5, and VGG (11,13,16,19). The experimental results using the accuracy metric show the maximum accuracy of 98.29% when using VGG 13 with batch normalization.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.9
• /
• pp.2505-2528
• /
• 2023

The field of facial expression recognition (FER) has been actively researched to improve human-computer interaction. In recent years, deep learning techniques have gained popularity for addressing FER, with numerous studies proposing end-to-end frameworks that stack or widen significant convolutional neural network layers. While this has led to improved performance, it has also resulted in larger model sizes and longer inference times. To overcome this challenge, our work introduces a novel lightweight model architecture. The architecture incorporates three key factors: Depth-wise Separable Convolution, Residual Block, and Attention Modules. By doing so, we aim to strike a balance between model size, inference speed, and accuracy in FER tasks. Through extensive experimentation on popular benchmark FER datasets, our proposed method has demonstrated promising results. Notably, it stands out due to its substantial reduction in parameter count and faster inference time, while maintaining accuracy levels comparable to other lightweight models discussed in the existing literature.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.4065-4083
• /
• 2021

Super-resolution can improve the clarity of low-resolution (LR) images, which can increase the accuracy of high-level compute vision tasks. Portable devices have low computing power and storage performance. Large-scale neural network super-resolution methods are not suitable for portable devices. In order to save the computational cost and the number of parameters, Lightweight image processing method can improve the processing speed of portable devices. Therefore, we propose the Enhanced Information Multiple Distillation Network (EIMDN) to adapt lower delay and cost. The EIMDN takes feedback mechanism as the framework and obtains low level features through high level features. Further, we replace the feature extraction convolution operation in Information Multiple Distillation Block (IMDB), with Ghost module, and propose the Enhanced Information Multiple Distillation Block (EIMDB) to reduce the amount of calculation and the number of parameters. Finally, coordinate attention (CA) is used at the end of IMDB and EIMDB to enhance the important information extraction from Spaces and channels. Experimental results show that our proposed can achieve convergence faster with fewer parameters and computation, compared with other lightweight super-resolution methods. Under the condition of higher peak signal-to-noise ratio (PSNR) and higher structural similarity (SSIM), the performance of network reconstruction image texture and target contour is significantly improved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3729-3749
• /
• 2021

At present, deep convolution network-based salient object detection (SOD) has achieved impressive performance. However, it is still a challenging problem to make full use of the multi-scale information of the extracted features and which appropriate feature fusion method is adopted to process feature mapping. In this paper, we propose a new adjacency auxiliary network (AANet) based on multi-scale feature fusion for SOD. Firstly, we design the parallel connection feature enhancement module (PFEM) for each layer of feature extraction, which improves the feature density by connecting different dilated convolution branches in parallel, and add channel attention flow to fully extract the context information of features. Then the adjacent layer features with close degree of abstraction but different characteristic properties are fused through the adjacent auxiliary module (AAM) to eliminate the ambiguity and noise of the features. Besides, in order to refine the features effectively to get more accurate object boundaries, we design adjacency decoder (AAM_D) based on adjacency auxiliary module (AAM), which concatenates the features of adjacent layers, extracts their spatial attention, and then combines them with the output of AAM. The outputs of AAM_D features with semantic information and spatial detail obtained from each feature are used as salient prediction maps for multi-level feature joint supervising. Experiment results on six benchmark SOD datasets demonstrate that the proposed method outperforms similar previous methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5580-5593
• /
• 2019

A malicious Uniform Resource Locator (URL) recognition and detection method based on the combination of Attention mechanism with Convolutional Neural Network and Long Short-Term Memory Network (Attention-Based CNN-LSTM), is proposed. Firstly, the WHOIS check method is used to extract and filter features, including the URL texture information, the URL string statistical information of attributes and the WHOIS information, and the features are subsequently encoded and pre-processed followed by inputting them to the constructed Convolutional Neural Network (CNN) convolution layer to extract local features. Secondly, in accordance with the weights from the Attention mechanism, the generated local features are input into the Long-Short Term Memory (LSTM) model, and subsequently pooled to calculate the global features of the URLs. Finally, the URLs are detected and classified by the SoftMax function using global features. The results demonstrate that compared with the existing methods, the Attention-based CNN-LSTM mechanism has higher accuracy for malicious URL detection.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.2
• /
• pp.235-241
• /
• 2022

Several studies using Convolutional Neural Network (CNN) have been conducted to detect and classify the sounds of marine mammals in underwater acoustic data collected through passive acoustic monitoring. In this study, the possibility of automatic classification of bearded seal sounds was confirmed using a CNN model based on the underwater acoustic spectrogram images collected from August 2017 to August 2018 in East Siberian Sea. When only the clear seal sound was used as training dataset, overfitting due to memorization was occurred. By evaluating the entire training data by replacing some training data with data containing noise, it was confirmed that overfitting was prevented as the model was generalized more than before with accuracy (0.9743), precision (0.9783), recall (0.9520). As a result, the performance of the classification model for bearded seals signal has improved when the noise was included in the training data.