• The Journal of the Korea Contents Association
• /
• v.9 no.7
• /
• pp.102-109
• /
• 2009

In this paper, we present an algorithm which generates the impossible drawings after the manner of M.C. Escher. A class of the impossible drawings, focused on this paper, depicts the non-realistic configuration such that an ascent (or a descent) looks like keeping on permanently with a height-deceptive loop. We analyze the fact that the ascending direction in the non-realistic illustrations comes not from the physical heights of the objects but from the artist's intended forwarding direction about the loop, which does not have any physical sense of depths. The basic idea to support such impossible drawings is to use a loop of layered depth images (LDIs), where several LDIs are arranged along with the forwarding direction of the loop while having the physically constant heights. The height-deception between two adjacent objects comes from the layer values in the LDIs. In this paper, we propose a NPR system which can manipulate a shape of the loop and layer values of the LDIs and demonstrate several impossible drawings results generated by using our system.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.70-75
• /
• 2007

본 논문은 연결정보(connectivity) 및 미리 계산된 계층적 데이터 구조(hierarchical data structure)를 이용하지 않는 그래픽 및 햅틱 렌더링 알고리즘을 제안한다. 제안된 알고리즘은 점 기반 그래픽 표현(point-based graphic representation) 기법을 이용하여 3차원 자유 곡면을 생성한다. 생성된 점 기반 곡면 물체와의 햅틱 상호작용을 위해 그래픽 하드웨어(GPU)에 접근하여 점 기반 곡면에서 생성된 깊이 이미지(depth image)를 이용하여 햅틱 상호작용에 필수 요소인 충돌검출(collision detection) 및 반력 연산(contact force computation)을 수행한다.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.1
• /
• pp.13-20
• /
• 2016

In this paper, we propose an object recognition system that can effectively find out its category, its instance name, and several attributes from the color and depth images of an object with hierarchical feature learning. In the preprocessing stage, our system transforms the depth images of the object into the surface normal vectors, which can represent the shape information of the object more precisely. In the feature learning stage, it extracts a set of patch features and image features from a pair of the color image and the surface normal vector through two-layered learning. And then the system trains a set of independent classification models with a set of labeled feature vectors and the SVM learning algorithm. Through experiments with UW RGB-D Object Dataset, we verify the performance of the proposed object recognition system.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.429-440
• /
• 2021

With the recent development of deep convolutional neural network learning, deep learning techniques applied to single image super-resolution are showing good results. One of the existing deep learning-based super-resolution techniques is RDN(Residual Dense Network), in which the initial feature information is transmitted to the last layer using residual dense blocks, and subsequent layers are restored using input information of previous layers. However, if all hierarchical features are connected and learned and a large number of residual dense blocks are stacked, despite good performance, a large number of parameters and huge computational load are needed, so it takes a lot of time to learn a network and a slow processing speed, and it is not applicable to a mobile system. In this paper, we use the residual dense structure, which is a continuous memory structure that reuses previous information, and the residual dense channel attention block using the channel attention method that determines the importance according to the feature map of the image. We propose a method that can increase the depth to obtain a large receptive field and maintain a concise model at the same time. As a result of the experiment, the proposed network obtained PSNR as low as 0.205dB on average at 4× magnification compared to RDN, but about 1.8 times faster processing speed, about 10 times less number of parameters and about 1.74 times less computation.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.25-34
• /
• 2020

In this paper, we empirically compare the effectiveness of training models to recognize beauty-related skin disease using supervised deep learning algorithms. Recently, deep learning algorithms are being actively applied for various fields such as industry, education, and medical. For instance, in the medical field, the ability to diagnose cutaneous cancer using deep learning based artificial intelligence has improved to the experts level. However, there are still insufficient cases applied to disease related to skin beauty. This study experimentally compares the effectiveness of identifying beauty-related skin disease by applying deep learning algorithms, considering CNN, ResNet, and SE-ResNet. The experimental results using these training models show that the accuracy of CNN is 71.5% on average, ResNet is 90.6% on average, and SE-ResNet is 95.3% on average. In particular, the SE-ResNet-50 model, which is a SE-ResNet algorithm with 50 hierarchical structures, showed the most effective result for identifying beauty-related skin diseases with an average accuracy of 96.2%. The purpose of this paper is to study effective training and methods of deep learning algorithms in consideration of the identification for beauty-related skin disease. Thus, it will be able to contribute to the development of services used to treat and easy the skin disease.