• 대한임베디드공학회논문지
• /
• 제11권3호
• /
• pp.163-171
• /
• 2016

Lane detection is a widely researched topic. Although simple road detection is easily achieved by previous methods, lane detection becomes very difficult in several complex cases involving noisy edges. To address this, we use a Convolution neural network (CNN) for image enhancement. CNN is a deep learning method that has been very successfully applied in object detection and recognition. In this paper, we introduce a robust lane detection method based on a CNN combined with random sample consensus (RANSAC) algorithm. Initially, we calculate edges in an image using a hat shaped kernel, then we detect lanes using the CNN combined with the RANSAC. In the training process of the CNN, input data consists of edge images and target data is images that have real white color lanes on an otherwise black background. The CNN structure consists of 8 layers with 3 convolutional layers, 2 subsampling layers and multi-layer perceptron (MLP) of 3 fully-connected layers. Convolutional and subsampling layers are hierarchically arranged to form a deep structure. Our proposed lane detection algorithm successfully eliminates noise lines and was found to perform better than other formal line detection algorithms such as RANSAC

• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1310-1319
• /
• 2016

Face detection is the first step in a wide range of face applications. However, detecting faces in the wild is still a challenging task due to the wide range of variations in pose, scale, and occlusions. Recently, many deep learning methods have been proposed for face detection. However, further improvements are required in the wild. Another important issue to be considered in the face detection is the computational complexity. Current state-of-the-art deep learning methods require a large number of patches to deal with varying scales and the arbitrary image sizes, which result in an increased computational complexity. To reduce the complexity while achieving better detection accuracy, we propose a fully convolutional network-based face detection that can take arbitrarily-sized input and produce feature maps (heat maps) corresponding to the input image size. To deal with the various face scales, a multi-scale network architecture that utilizes the facial components when learning the feature maps is proposed. On top of it, we design multi-task learning technique to improve detection performance. Extensive experiments have been conducted on the FDDB dataset. The experimental results show that the proposed method outperforms state-of-the-art methods with the accuracy of 82.33% at 517 false alarms, while improving computational efficiency significantly.

• 한국컴퓨터정보학회논문지
• /
• 제25권12호
• /
• pp.25-34
• /
• 2020

본 논문에서는 딥러닝 지도학습 알고리즘을 사용한 학습 모델을 대상으로 미용 관련 피부질환 인식의 효과성을 실험적으로 비교한다. 최근 딥러닝 기술을 산업, 교육, 의료 등 다양한 분야에 적용하고 있으며, 의료 분야에서는 중요 피부질환 중 하나인 피부암 식별의 수준을 전문가 수준으로 높인 성과를 보이고 있다. 그러나 아직 피부미용과 관련된 질환에 적용한 사례가 다양하지 못하다. 따라서 딥러닝 기반 이미지 분류에 활용도가 높은 CNN 알고리즘을 비롯하여 ResNet, SE-ResNet을 적용하여 실험적으로 정확도를 비교함으로써 미용 관련 피부질환을 판단하는 효과성을 평가한다. 각 알고리즘을 적용한 학습 모델을 실험한 결과에서 CNN의 경우 평균 71.5%, ResNet은 평균 90.6%, SE-ResNet은 평균 95.3%의 정확도를 보였다. 특히 학습 깊이를 다르게하여 비교한 결과 50개의 계층 구조를 갖는 SE-ResNet-50 모델이 평균 96.2%의 정확도로 미용 관련 피부질환 식별을 위해 가장 효과적인 결과를 보였다. 본 논문의 목적은 피부 미용과 관련된 질환의 판별을 고려하여 효과적인 딥러닝 알고리즘의 학습과 방법을 연구하기 위한 것으로 이를 통해 미용 관련 피부질환 개선을 위한 서비스 개발로 확장할 수 있을 것이다.

• 인터넷정보학회논문지
• /
• 제21권5호
• /
• pp.21-29
• /
• 2020

Accurate estimation of human pose relies on backbone method in which its role is to extract feature map. Up to dated, the method of backbone feature extraction is conducted by the plain convolutional neural networks named by CNN and the residual neural networks named by Resnet, both of which have various architectures and performances. The CNN family network such as VGG which is well-known as a multiple stacked hidden layers architecture of deep learning methods, is base and simple while Resnet which is a bottleneck layers architecture yields fewer parameters and outperform. They have achieved inspired results as a backbone network in human pose estimation. However, they were used then followed by different pose estimation networks named by pose parsing module. Therefore, in this paper, we present a comparison between the plain CNN family network (VGG) and bottleneck network (Resnet) as a backbone method in the same pose parsing module. We investigate their performances such as number of parameters, loss score, precision and recall. We experiment them in the bottom-up method of human pose estimation system by adapted the pose parsing module of openpose. Our experimental results show that the backbone method using VGG network outperforms the Resent network with fewer parameter, lower loss score and higher accuracy of precision and recall.

• 사물인터넷융복합논문지
• /
• 제8권2호
• /
• pp.79-84
• /
• 2022

본 논문은 문서의 보안과 손실 및 오염에 대하여 복원능력을 향상시키는 방안을 제안한다. 이를 위해서 암호화로 DnCNN(DeNoise Convolution Neural Network)을 제시한다. 암호화 방법을 구현하기 위하여 2D이미지정보를 광학에 사용되는 공간주파수 전달함수(Spatial Frequency Transfer Function)의 수학적 모델을 적용한다. 공간 주파수 전달함수를 사용하여 광학적 간섭 패턴을 암호화로 사용하고 공간 주파수 전달함수의 수학적 변수를 복호화하는 암호로 사용하는 방법을 제안하였다. 또한, 딥러닝을 적용한 DnCNN 방법을 적용하여 노이즈 제거하여 복원 성능을 개선한다. 실험결과, 65%의 정보 손실이 있는 경우에도 Pre-Training DnCNN Deep Learning을 적용한 결과 공간 주파수 전달함수만을 활용한 복원 결과 와 비교하여 PSNR(Peak Signal-to-noise ratio)을 11% 이상 우수한 성능을 확인할 수 있다. 또한, CC(Correlation Coefficient)의 특성도 16% 이상 우수한 결과를 보이고 있다.

• 품질경영학회지
• /
• 제48권4호
• /
• pp.581-596
• /
• 2020

Purpose: purpose of this study was to propose the web application platform which can be to detect and discriminate various diseases and pest of tomato plant based on the large amount of disease image data observed in the facility or the open field. Methods: The deep learning algorithms uesed at the web applivation platform are consisted as the combining form of Faster R-CNN with the pre-trained convolution neural network (CNN) models such as SSD_mobilenet v1, Inception v2, Resnet50 and Resnet101 models. To evaluate the superiority of the newly proposed web application platform, we collected 850 images of four diseases such as Bacterial cankers, Late blight, Leaf miners, and Powdery mildew that occur the most frequent in tomato plants. Of these, 750 were used to learn the algorithm, and the remaining 100 images were used to evaluate the algorithm. Results: From the experiments, the deep learning algorithm combining Faster R-CNN with SSD_mobilnet v1, Inception v2, Resnet50, and Restnet101 showed detection accuracy of 31.0%, 87.7%, 84.4%, and 90.8% respectively. Finally, we constructed a web application platform that can detect and discriminate various tomato deseases using best deep learning algorithm. If farmers uploaded image captured by their digital cameras such as smart phone camera or DSLR (Digital Single Lens Reflex) camera, then they can receive an information for detection, identification and disease control about captured tomato disease through the proposed web application platform. Conclusion: Incheon Port needs to act actively paying.

• Journal of information and communication convergence engineering
• /
• 제16권2호
• /
• pp.106-113
• /
• 2018

Although deep learning methods of convolutional neural networks (CNNs) and long-/short-term memory (LSTM) are widely used for text categorization, they still have certain shortcomings. CNNs require that the text retain some order, that the pooling lengths be identical, and that collateral analysis is impossible; In case of LSTM, it requires the unidirectional operation and the inputs/outputs are very complex. Against these problems, we thus improved these traditional deep learning methods in the following ways: We created collateral CNNs accepting disorder and variable-length pooling, and we removed the input/output gates when creating bidirectional LSTMs. We have used four benchmark datasets for topic and sentiment classification using the new methods that we propose. The best results were obtained by combining LTSM regional embeddings with data convolution. Our method is better than all previous methods (including deep learning methods) in terms of topic and sentiment classification.

• Journal of Platform Technology
• /
• 제12권1호
• /
• pp.3-11
• /
• 2024

Deaf people who use sign language as their first language sometimes have difficulty communicating because they do not know spoken Korean. Deaf people are also members of society, so we must support to create a society where everyone can live together. In this paper, we present a method to increase the recognition rate of Korean sign language using a CNN model. When the original image was used as input to the CNN model, the accuracy was 0.96, and when the image corresponding to the skin area in the YCbCr color space was used as input, the accuracy was 0.72. It was confirmed that inserting the original image itself would lead to better results. In other studies, the accuracy of the combined Conv1d and LSTM model was 0.92, and the accuracy of the AlexNet model was 0.92. The CNN model proposed in this paper is 0.96 and is proven to be helpful in recognizing Korean sign language.

• International Journal of Computer Science & Network Security
• /
• 제24권5호
• /
• pp.129-134
• /
• 2024

Object Detection is an emerging technology in the field of Computer Vision and Image Processing that deals with detecting objects of a particular class in digital images. It has considered being one of the complicated and challenging tasks in computer vision. Earlier several machine learning-based approaches like SIFT (Scale-invariant feature transform) and HOG (Histogram of oriented gradients) are widely used to classify objects in an image. These approaches use the Support vector machine for classification. The biggest challenges with these approaches are that they are computationally intensive for use in real-time applications, and these methods do not work well with massive datasets. To overcome these challenges, we implemented a Deep Learning based approach Convolutional Neural Network (CNN) in this paper. The Proposed approach provides accurate results in detecting objects in an image by the area of object highlighted in a Bounding Box along with its accuracy.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2016년도 춘계학술대회
• /
• pp.727-730
• /
• 2016

TSC(Time Series Classification)은 시계열데이터를 패턴에 따라 분류하는 것으로, 시계열이 매우 흔한 데이터형태이고, 또한 활용도가 높기 때문에 오랜 시간동안 Data Mining 과 Machine Learning 분야의 주요한 이슈였다. 전통적인 방법에서는 Distance와 Dictionary 기반의 방법들을 많이 활용하였으나, Time Scale과 Random Noise의 문제로 인해 분류의 정확도가 제한되었다. 본 논문에서는 Deep Learning의 CNN(Convolutional Neural Network)과 변종데이터(Data Mutation)을 이용해 정확도를 향상시킨 방법을 제시한다. CNN은 이미지분야에서 이미 검증된 신경망 모델로써 시계열데이터의 특성을 나타내는 Feature를 인식하는데 효과적으로 활용할 수 있고, 변종데이터는 하나의 데이터를 다양한 방식으로 변종을 만들어 CNN이 특정 패턴의 가능한 변형에 대해서도 학습할 수 있도록 데이터를 제공한다. 제시한 방식은 기존의 방식보다 우수한 정확도를 보여준다.