• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.385-398
• /
• 2021

The complexity of deep learning models affects the real-time performance of gesture recognition, thereby limiting the application of gesture recognition algorithms in actual scenarios. Hence, a residual learning neural network based on a deep convolutional neural network is proposed. First, small convolution kernels are used to extract the local details of gesture images. Subsequently, a shallow residual structure is built to share weights, thereby avoiding gradient disappearance or gradient explosion as the network layer deepens; consequently, the difficulty of model optimisation is simplified. Additional convolutional neural networks are used to accelerate the refinement of deep abstract features based on the spatial importance of the gesture feature distribution. Finally, a fully connected cascade softmax classifier is used to complete the gesture recognition. Compared with the dense connection multiplexing feature information network, the proposed algorithm is optimised in feature multiplexing to avoid performance fluctuations caused by feature redundancy. Experimental results from the ISOGD gesture dataset and Gesture dataset prove that the proposed algorithm affords a fast convergence speed and high accuracy.

• 디지털산업정보학회논문지
• /
• 제18권2호
• /
• pp.17-26
• /
• 2022

In this paper, we propose a novel method of performing convolutional operations on a 2-D Processing Element(PE) array. The conventional method [1] of mapping the convolutional operation using the 2-D PE array lacks flexibility and provides low utilization of PEs. However, by mapping a convolutional operation from a 2-D PE array to a 1-D PE array, the proposed method can increase the number and utilization of active PEs. Consequently, the throughput of the proposed Deep Convolutional Neural Network(DCNN) accelerator can be increased significantly. Furthermore, the power consumption for the transmission of weights between PEs can be saved. Based on the simulation results, the performance of the proposed method provides approximately 4.55%, 13.7%, and 2.27% throughput gains for each of the convolutional layers of AlexNet, VGG16, and ResNet50 using the DCNN accelerator with a (weights size) x (output data size) 2-D PE array compared to the conventional method. Additionally the proposed method provides approximately 63.21%, 52.46%, and 39.23% power savings.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.311-326
• /
• 2024

The rapid development of neural network technology promotes the neural network model driven by big data to overcome the texture effect of complex objects. Due to the limitations in complex scenes, it is necessary to establish custom template matching and apply it to the research of many fields of computational vision technology. The dependence on high-quality small label sample database data is not very strong, and the machine learning system of deep feature connection to complete the task of texture effect inference and speculation is relatively poor. The style transfer algorithm based on neural network collects and preserves the data of patterns, extracts and modernizes their features. Through the algorithm model, it is easier to present the texture color of patterns and display them digitally. In this paper, according to the texture effect reasoning of custom template matching, the 3D visualization of the target is transformed into a 3D model. The high similarity between the scene to be inferred and the user-defined template is calculated by the user-defined template of the multi-dimensional external feature label. The convolutional neural network is adopted to optimize the external area of the object to improve the sampling quality and computational performance of the sample pyramid structure. The results indicate that the proposed algorithm can accurately capture the significant target, achieve more ablation noise, and improve the visualization results. The proposed deep convolutional neural network optimization algorithm has good rapidity, data accuracy and robustness. The proposed algorithm can adapt to the calculation of more task scenes, display the redundant vision-related information of image conversion, enhance the powerful computing power, and further improve the computational efficiency and accuracy of convolutional networks, which has a high research significance for the study of image information conversion.

• 한국전자통신학회논문지
• /
• 제15권6호
• /
• pp.1081-1088
• /
• 2020

본 논문에서는 합성곱 신경망을 기반으로 CCTV 이미지를 통한 해무 탐지 방법을 제안한다. 학습에 필요한 자료로 시정 1km 기준으로 총 11개의 항만 또는 해수욕장(부산항, 부산신항, 평택항, 인천항, 군산항, 대산항, 목포항, 여수광양항, 울산항, 포항항, 해운대해수욕장)에서 수집된 해무와 해무가 아닌 이미지 10004장을 랜덤 추출하였다. 전체 10004장의 데이터셋 중에 80%를 추출하여 합성곱 신경망 모델 학습에 사용하였다. 사용된 모델은 16개의 합성곱층과 3개의 완전 연결층을 가지고 있으며, 마지막 완전 연결층에서 Softmax 분류를 수행하는 합성곱 신경망을 활용하였다. 나머지 20%를 이용하여 모델 정확도 평가를 수행하였고 정확도 평가 결과 약 96%의 분류 정확도를 보였다.

• Journal of information and communication convergence engineering
• /
• 제16권3호
• /
• pp.160-165
• /
• 2018

This paper designed and developed the image processing system of integrating feature extraction and matching by using convolutional neural network (CNN), rather than relying on the simple method of processing feature extraction and matching separately in the image processing of conventional image recognition system. To implement it, the proposed system enables CNN to operate and analyze the performance of conventional image processing system. This system extracts the features of an image using CNN and then learns them by the neural network. The proposed system showed 84% accuracy of recognition. The proposed system is a model of recognizing learned images by deep learning. Therefore, it can run in batch and work easily under any platform (including embedded platform) that can read all kinds of files anytime. Also, it does not require the implementing of feature extraction algorithm and matching algorithm therefore it can save time and it is efficient. As a result, it can be widely used as an image recognition program.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권10호
• /
• pp.5159-5178
• /
• 2018

Network Intrusion detection is a rapidly growing field of information security due to its importance for modern IT infrastructure. Many supervised and unsupervised learning techniques have been devised by researchers from discipline of machine learning and data mining to achieve reliable detection of anomalies. In this paper, a deep convolutional neural network (DCNN) based intrusion detection system (IDS) is proposed, implemented and analyzed. Deep CNN core of proposed IDS is fine-tuned using Randomized search over configuration space. Proposed system is trained and tested on NSLKDD training and testing datasets using GPU. Performance comparisons of proposed DCNN model are provided with other classifiers using well-known metrics including Receiver operating characteristics (RoC) curve, Area under RoC curve (AuC), accuracy, precision-recall curve and mean average precision (mAP). The experimental results of proposed DCNN based IDS shows promising results for real world application in anomaly detection systems.

• 한국멀티미디어학회논문지
• /
• 제22권4호
• /
• pp.455-462
• /
• 2019

This paper proposes a method of utilizing convolutional neural network to classify the images of Bender Gestalt Test (BGT), which is a tool to understand and analyze a person's characteristic. The proposed network is composed of 29 layers including 18 convolutional layers and 2 fully connected layers, where the network is to be trained with augmented images. To verify the proposed method, 10 fold validation was adopted. In results, the proposed method classified the images into 9 classes with the mean f1 score of 97.05%, which is 13.71%p higher than a previous method. The analysis of the results shows the classification accuracy of the proposed method is stable over all the patterns as the worst f1 score among all the patterns was 92.11%.

• ETRI Journal
• /
• 제46권2호
• /
• pp.307-322
• /
• 2024

Most object detection methods use a horizontal bounding box that causes problems between adjacent objects with arbitrary directions, resulting in misaligned detection. Hence, the horizontal anchor should be replaced by a rotating anchor to determine oriented bounding boxes. A two-stage process of delineating a horizontal bounding box and then converting it into an oriented bounding box is inefficient. To improve detection, a box-boundary-aware vector can be estimated based on a convolutional neural network. Specifically, we propose a ResNeXt101 encoder to overcome the weaknesses of the conventional ResNet, which is less effective as the network depth and complexity increase. Owing to the cardinality of using a homogeneous design and multi-branch architecture with few hyperparameters, ResNeXt captures better information than ResNet. Experimental results demonstrate more accurate and faster oriented object detection of our proposal compared with a baseline, achieving a mean average precision of 89.41% and inference rate of 23.67 fps.

• 문화기술의 융합
• /
• 제3권4호
• /
• pp.171-175
• /
• 2017

최근 CNN(Convolutional Neural Network)의 구조가 복잡해지고 신견망의 깊이가 깊어지고 있다. 이에 따라 신경망의 학습에 요구되는 연산량 및 학습 시간이 증가하게 되었다. 최근 GPGPU 및 FPGA를 이용하여 신경망의 학습 속도를 가속화 하는 방법에 대한 연구가 활발히 진행되고 있다. 본 논문에서는 NVIDIA GPGPU를 제어하는 CUDA를 이용하여 CNN의 특징추출부와 분류부에 대한 연산을 가속화하는 방법을 제시한다. 특징추출부와 분류부에 대한 연산을 GPGPU의 블록 및 스레드로 할당하여 병렬로 처리하였다. 본 논문에서 제안하는 방법과 기존 CPU를 이용하여 CNN을 학습하여 학습 속도를 비교하였다. MNIST 데이터세트에 대하여 총 5 epoch을 학습한 결과 제안하는 방법이 CPU를 이용하여 학습한 방법에 비하여 약 314% 정도 학습 속도가 향상된 것을 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제22권12호
• /
• pp.1457-1465
• /
• 2019

3D convolution is to stack multiple consecutive frames to form a cube, and then apply the 3D convolution kernel in the cube. In this structure, each feature map of the convolutional layer is connected to multiple adjacent sequential frames in the previous layer, thus capturing the motion information. However, due to the changes of pedestrian posture, motion and position, the convolution at the same place is inappropriate, and when the 3D convolution kernel is convoluted in the time domain, only time domain features of three consecutive frames can be extracted, which is not a good enough to get action information. This paper proposes an action recognition method based on feature fusion of 3D convolutional neural network. Based on the VGG16 network model, sending a pre-acquired optical flow image for learning, then get the time domain features, and then the feature of the time domain is extracted from the features extracted by the 3D convolutional neural network. Finally, the behavior classification is done by the SVM classifier.