• Journal of Internet Computing and Services
• /
• v.19 no.5
• /
• pp.43-54
• /
• 2018

Images taken in haze weather are characteristic of low contrast and poor visibility. The process of reconstructing clear-weather image from a hazy image is called dehazing. The main challenge of image dehazing is to estimate the transmission map or depth map for an input hazy image. In this paper, we propose a single image dehazing method by utilizing the Generative Adversarial Network(GAN) for accurate depth map estimation. The proposed GAN model is trained to learn a nonlinear mapping between the input hazy image and corresponding depth map. With the trained model, first the depth map of the input hazy image is estimated and used to compute the transmission map. Then a guided filter is utilized to preserve the important edge information of the hazy image, thus obtaining a refined transmission map. Finally, the haze-free image is recovered via atmospheric scattering model. Although the proposed GAN model is trained on synthetic indoor images, it can be applied to real hazy images. The experimental results demonstrate that the proposed method achieves superior dehazing results against the state-of-the-art algorithms on both the real hazy images and the synthetic hazy images, in terms of quantitative performance and visual performance.

• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.35-43
• /
• 2022

Makeup is the most common way to improve a person's appearance. However, since makeup styles are very diverse, there are many time and cost problems for an individual to apply makeup directly to himself/herself.. Accordingly, the need for makeup automation is increasing. Makeup transfer is being studied for makeup automation. Makeup transfer is a field of applying makeup style to a face image without makeup. Makeup transfer can be divided into a traditional image processing-based method and a deep learning-based method. In particular, in deep learning-based methods, many studies based on Generative Adversarial Networks have been performed. However, both methods have disadvantages in that the resulting image is unnatural, the result of makeup conversion is not clear, and it is smeared or heavily influenced by the makeup style face image. In order to express the clear boundary of makeup and to alleviate the influence of makeup style facial images, this study divides the makeup area and calculates the loss function using HoG (Histogram of Gradient). HoG is a method of extracting image features through the size and directionality of edges present in the image. Through this, we propose a makeup transfer network that performs robust learning on edges.By comparing the image generated through the proposed model with the image generated through BeautyGAN used as the base model, it was confirmed that the performance of the model proposed in this study was superior, and the method of using facial information that can be additionally presented as a future study.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.5
• /
• pp.205-211
• /
• 2009

The Weightless Neural Network(WNN) has the advantage of the processing speed, less computability than weighted neural network which readjusts the weight. Especially, The behavior information such as sequential gesture has many serial correlation. So, It is required the high computability and processing time to recognize. To solve these problem, Many algorithms used that added preprocessing and hardware interface device to reduce the computability and speed. In this paper, we proposed the Ram based Sequential Cumulative Neural Network(SCNN) model which is sign language recognition system without preprocessing and hardware interface. We experimented with using compound words in continuous korean sign language which was input binary image with edge detection from camera. The recognition system of sign language without preprocessing got 93% recognition rate.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.4
• /
• pp.1457-1470
• /
• 2015

In wireless multimedia sensor networks (WMSN), the latency of transmission is an increasingly problem. With the improvement of resolution, the time cost in image and video compression is more and more, which seriously affects the real-time of WMSN. In JPEG system, the core of the system is DCT, but DCT-JPEG is not the best choice. Block-based DCT transform coding has serious blocking artifacts when the image is highly compressed at low bit rates. APBT is used in this paper to solve that problem, but APBT does not have a fast algorithm. In this paper, we analyze the structure in JPEG and propose a parallel framework to speed up the algorithm of JPEG on GPU. And we use all phase biorthogonal transform (APBT) to replace the discrete cosine transform (DCT) for the better performance of reconstructed image. Therefore, parallel APBT-JPEG is proposed to solve the real-time of WMSN and the blocking artifacts in DCT-JPEG in this paper. We use the CUDA toolkit based on GPU which is released by NVIDIA to design the parallel algorithm of APBT-JPEG. Experimental results show that the maximum speedup ratio of parallel algorithm of APBT-JPEG can reach more than 100 times with a very low version GPU, compared with conventional serial APBT-JPEG. And the reconstructed image using the proposed algorithm has better performance than the DCT-JPEG in terms of objective quality and subjective effect. The proposed parallel algorithm based on GPU of APBT also can be used in image compression, video compression, the edge detection and some other fields of image processing.

• Journal of KIISE:Information Networking
• /
• v.27 no.2
• /
• pp.187-196
• /
• 2000

Failures in ATM networks can occur at virtual path (VP) links, virtual path switches, and virtual channel (VC) switches. Restoration schemes have been proposed for VP link and VP switch failures, however, none for VC switch failures. In general, VC switches are used for edge nodes in protection domains. Since even only one VC switch failure can cause a critical problem, new restoration schemes for VC switch failures are highly required. Restoration schemes at the VP level proposed so far can be categorized into those using the flooding algorithm and those using the backup virtual path (BVP) concept. Even though the latter cannot handle unpredictable failures, it has some advantages such as fast restoration and low spare capacity requirement. In this paper, we propose new restoration schemes using a new type of BVPs to handle VC switch failures. The simulation results show that the proposed schemes can restore virtual connection failures due to VC switch failures without degrading restorability for VP failures.

• Journal of the Korean Society for information Management
• /
• v.17 no.3
• /
• pp.7-20
• /
• 2000

Many organizations have developed their own information systems not only for internal efficiency but also for effectiveness of external customer services. The infusion of powerful information networks into business environments is beginning to have a profound impact on the nature of governance between buyers and sellers in the market place. One of the most effective service tools for their customers is the use of information technology. The web technology is rapidly becoming one of the most effective online customer service tools toward strategic competitive advantage. In order to gain competitive edge, organizations must have effective web sites for customer services. A study on web service development phase has been conducted and present states of web usages by Korean, US., Japanese companies are surveyed. Cases of business web sites are empirically analyzed in order to compare the different levels of web site application in three countries. Conclusively, countries with longer experience with internet has more advanced level of web application such as business transaction and internet process innovation. In order to support effective web site planning, organizations have to understand their current position in Internet application and form strategies for e-business.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.9A
• /
• pp.728-735
• /
• 2003

It is a mainly issue that provide mobility smoothly in Mobile IP networks. The IP mobility support being standardized in the IETF utilized tunneling of IP packets from a home agent to foreign agent and utilized reverse tunneling of IP packets from foreign agent to home agent. In this paper, We propose that solve the triangular routing problem in IP mobility and that lessen the messages about IETF routing optimization. Through the Mobile Routing Table on the edge router, agent process the message instead of a end node when handoff occur and that lessen the routing path length by sending directly from FA to to Correspond Node's router. This action lessen the message occurrence frequency and the packet drop. We compare the standard IP, Routing Optimization of Mobile IP, Wu's method and the proposed algorithm. Finally, the simulation results are presented.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.7
• /
• pp.794-798
• /
• 2010

Assuming that a wireless link is mostly used at the network edge and the wireless NIC driver keeps monitoring the error rate of its link, this paper proposes an enhanced TCP congestion control, TCP-L (TCP Link-Aware). TCP-L predicts true congestion losses occurred inside the wired link area by utilizing the wireless link error rate. As a result, it mitigates performance degradation caused from TCP congestion control actions when segments losses occur in a wireless link. Experimental results show that TCP-L provides better performance and fairness in lossy wireless links than existing TCP congestion control schemes. Our approach utilizing the characteristic of the link at TCP could be well adapted to new wireless environments such as Cognitive Radio and ACK-less IEEE 802.11, where a frame may be delivered with a very long delay or lost in the link.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1405-1408
• /
• 2005

An embedded system has been applied to many fields including households and industrial sites. In the past, user interface products with simple functions were commercialized .but now user demands are increasing and the system has more various applicable fields due to a high penetration rate of the Internet. Therefore, the demand for embedded system is tend to rise In this paper, we Implementation of an embedded system for image tracking. This system is used a fixed IP for the reliable server operation on TCP/IP networks. A real time broadcasting of video image on the internet was developed by using an USB camera on the embedded Linux system. The digital camera is connected at the USB host port of the embedded board. all input images from the video camera is continuously stored as a compressed JPEG file in a directory at the Linux web-server. And each frame image data from web camera is compared for measurement of displacement Vector. That used Block matching algorithm and edge detection algorithm for past speed. And the displacement vector is used at pan/tilt motor control through RS232 serial cable. The embedded board utilized the S3C2410 MPU Which used the ARM 920T core form Samsung. The operating system was ported to embedded Linux kernel and mounted of root file system. And the stored images are sent to the client PC through the web browser. It used the network function of Linux and it developed a program with protocol of the TCP/IP.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.40 no.12
• /
• pp.9-17
• /
• 2003

In this paper we proposea method for estimating the bandwidth in next-generation If network. Especially, we concentrate on the edge routers accommodating the VoIP connections as well as a group of data connections. Bandwidth dimensioning is carried out at call level and packet level for voice traffic in the next-generation IP network. The model incorporates the statistical estimation approach at a call level for obtaining the number of voice connections simultaneously in the active mode. The call level model incorporates a statistical technique to compute the statistics of the number of active connections such as the mean and variance of the simultaneously connected calls in the network. The packet level model represents a load map for voice and data traffic by using non-preemptive M/G/1 queuing model with strict priority for voice over data buffer, From the proposed traffic model, we can derive a graph for upper bounds on the traffic load in terms of bandwidth for voice and data connections. Via numerical experiments we illustrate the implication of the work.