Single image rain removal is a typical inverse problem which decomposes the image into a background scene and a rain streak. Recent works have witnessed a substantial progress on the task due to the development of convolutional neural network (CNN). However, existing CNN-based approaches train the network with synthetically generated training examples. These data tend to make the network bias to the synthetic scenes. In this paper, we present an unsupervised framework for removing rain streaks from real-world rainy images. We focus on the natural phenomena that static rainy scenes capture a common background but different rain streak. From this observation, we train siamese network with the real rain image pairs, which outputs identical backgrounds from the pairs. To train our network, a real rainy dataset is constructed via web-crawling. We show that our unsupervised framework outperforms the recent CNN-based approaches, which are trained by supervised manner. Experimental results demonstrate that the effectiveness of our framework on both synthetic and real-world datasets, showing improved performance over previous approaches.

In High Dynamic Range (HDR) image processing, tone mapping is the process to compress an input image into a Low Dynamic Range (LDR) image. In most cases, the reason that detail preservation is prior to take over tone mapping is that the dynamic range is significantly different between input and output images. In the case of iCAM06, details are separated by using a bilateral filter, however, it causes noise amplification at the dim surround region. Thus, we suggest that the detail signal, which is separated from the bilateral filter, is combined with the base signal after an adaptive Kalman filter is applied according to the local standard deviation. We confirmed that the proposed method enhances the HDR images quality by checking the noise reduction in a dim surround region.

In this paper we propose how to detect circular objects in the gray scale image and segment them using the discrete Morse theory, which makes it possible to analyze the topology of a digital image, when it is transformed into the data structure of some combinatorial complex. It is possible to get meaningful information about how many connected components and topologically circular shapes are in the image by computing the persistent homology of the filtration using the Morse complex. We obtain a Morse complex by modeling an image as a cubical cellular complex. Each cell in the Morse complex is the critical point at which the topological structure changes in the filtration consisting of the level sets of the image. In this paper, we implement the proposed algorithm of segmenting the circularly shaped objects with a long persistence of homology as well as computing persistent homology along the filtration of the input image and displaying in the form of a persistence diagram.

In this paper, a new type of lip feature is proposed as distance metric in CIELUV color system. The performance of the proposed feature was tested on face image database, Helen dataset from University of Illinois. The test processes consists of three steps. The first step is feature extraction and second step is principal component analysis for the optimal projection of a feature vector. The final step is Otsu's threshold for a two-class problem. The performance of the proposed feature was better than conventional features. Performance metrics for the evaluation are OverLap and Segmentation Error. Best performance for the proposed feature was OverLap of 65% and 59 % of segmentation error. Conventional methods shows 80~95% for OverLap and 5~15% of segmentation error usually. In conventional cases, the face database is well calibrated and adjusted with the same background and illumination for the scene. The Helen dataset used in this paper is not calibrated or adjusted at all. These images are gathered from internet and therefore, there are no calibration and adjustment.

Template tracking refers to the procedure of finding the most similar image patch corresponding to the given template through an image sequence. In order to obtain more accurate trajectory of the template, the template requires to be updated to reflect various appearance changes as it traverses through an image sequence. To do that, appearance images are used to model appearance variations and these are obtained by the computation of the principal components of the augmented image matrix at every iteration. Unfortunately, it is prohibitively expensive to compute the principal components at every iteration. Thus in this paper, we suggest a new Sliding Window based truncated URV Decomposition (TURVD) algorithm which enables updating their structure by recycling their previous decomposition instead of decomposing the image matrix from the beginning. Specifically, we show an efficient algorithm for updating and downdating the TURVD simultaneously, followed by the rank-one update to the TURVD while tracking the decomposition error accurately and adjusting the truncation level adaptively. Experiments show that the proposed algorithm produces no-meaningful differences but much faster execution speed compared to the typical algorithms in template tracking applications, thereby maintaining a good approximation for the principal components.

Recently, image-based object detection has made great progress with the introduction of Convolutional Neural Network (CNN). Many trials such as Region-based CNN, Fast R-CNN, and Faster R-CNN, have been proposed for achieving better performance in object detection. YOLO has showed the best performance under consideration of both accuracy and computational complexity. However, these data-driven detection methods including YOLO have the fundamental problem is that they can not guarantee the good performance without a large number of training database. In this paper, we propose a data sampling method using CycleGAN to solve this problem, which can convert styles while retaining the characteristics of a given input image. We will generate the insufficient data samples for training more robust object detection without efforts of collecting more database. We make extensive experimental results using the day-time and night-time road images and we validate the proposed method can improve the object detection accuracy of the night-time without training night-time object databases, because we converts the day-time training images into the synthesized night-time images and we train the detection model with the real day-time images and the synthesized night-time images.

Almost all 3D displays have a brightness reduction in the 3D mode comparing to the 2D mode. When the brightness is reduced, one of the color attributes, the colorfulness, is decreased. In this case, the viewer feels that the image quality is deteriorated. In this paper, we proposed a method to compensate for the degradation of colorfulness due to brightness reduction in 3D mode for high quality 3D image viewing using the CIECAM02 model and the color correction matrix. As a result of applying the proposed method, we can confirm that the colorfulness is improved in 3D mode.

In this paper, we propose iZone system for safe walking of children. The proposed system recognizes the state that a child is down a roadway as a dangerous situation. And then it informs the surrounding adults and guardians of the child in the event of a dangerous situation. The iZone system consists of the iZone device that attaches to a child's bag or clothing, the iZone app for children, the iZone server, and external beacons. The proposed system uses the ultrasonic sensor of the iZone device and the GPS coordinates and external beacons information by the children's smartphone to determine the dangerous situation. The proposed system uses external beacons to calibrate the GPS coordinates. Moreover, it determines whether the child is down the roadway in sidewalk by measuring the height difference between the roadway and the sidewalk using ultrasonic sensor.

The smart festival costume developed in this study maximizes the design elements by attaching electronic device to clothing, and uses voice, movement, and light sensor to utilize as expression elements. In addition, as a way to maximize cultural exchanges between Korea and China, smart festival costume was developed by applying smart clothing technology to the traditional costumes of both countries. and it was exhibited for 10 days at the 'Andong International Mask Dance Festival 2018'. The smart festival costume has the effect of multiplying the dynamism and excitement of the festival by the use of colorful lighting and it has been evaluated that the experience of wearing traditional costume of both countries contributes greatly to promote international cultural exchange. However, since smart clothing is inconvenient to wear due to the use of electronic products, meticulous research for consumer safety is required for practical use. Smart devices is expected to utilize for the development of traditional culture resources and the fashion industry in the future.

Appropriate strategies are needed to ensure long-term preservation of various types of electronic records. For proper preservation of electronic records, it is necessary of decision-making processes for risk assessment, notification and implementation of conservation measures. To do this, the task of assessing various risk factors that impede the long-term preservation and utilization of electronic records should be done first. In this study, since electronic records are mostly stored in file form, risk assessment for electronic records of file type is performed. The risk factors required for the risk assessment of the file format are derived, and the algorithms are developed to devise a calculation method of the weighting factor and the risk factor index for evaluating the risk based on the proposed risk factors. In addition, the proposed methods are applied to the file formats used in Korea and risk assessment is performed and the results are analyzed.

This study was conducted to explore ways to create a cultural city using local cultural resources. To that end, the qualitative case study was applied. As the original city center had been declining due to the expansion and changes of city space caused by the changes of city function and social change, the old downtown of Andong city was selected as an example. For the result, research shows that the region's historical resources and culture have to blend and develop together with abundant cultural resources, such as contents development, city's symbolic space settings, differentiated cultural and artistic establishment, comfort in living, utilization of cultural infrastructure, and supporting facilities which are suitable for cultural diversity. In particular, we found that the importance of establishing a new city image that leads local residents willing to participate and of forming a consensus among tourists. Therefore, for the implementation of a cultural city, policies, undertaking, and administrative support that meet to the city's conditions and environment are required, and a further study on that issue is needed.

Realistic rendering of natural phenomena is a difficult problem. Many environmental factors must be considered to simulate this phenomenon. At the same time, we need to think about their computational complexity to be simulated with computer algorithm One of the most difficult problems in creating weather conditions is the rain. To simulate realistic rainy scene, you have to consider the physical properties of rain and the environmental where the rain is falling down as well. In this paper, we survey the modeling and rendering techniques for realistic rainfall scenes from three different aspects. First, we list up techniques for modeling raindrop dynamics. Second, we survey the rendering techniques that render the raindrop in the environment. Third, we take a look at the hybrid methods that combines the rendering the modeling at the same time. For each aspect, we compare the algorithms in terms of implementation and their speciality.

Virtual reality (VR) sickness can have an influential effect on the viewing quality of VR 3D contents. Particularly, watching the 3D contents on a head-mounted display (HMD) could cause some severe level of visual discomfort. Despite the importance of assessing the VR sickness, most of the recent studies have focused on unveiling the reason of inducing VR sickness. In this paper, we subjectively measure the level of VR sickness induced in the viewing of omnidirectional 3D graphics contents in HMD environment. Apart from that, we propose an objective assessment model that estimates the level of induced VR sickness by calculating the difference between head movement velocity and global camera motion velocity.