This paper presents a light exposure correction algorithm for less pleasant images, acquired with a light metering failure. Since conventional tone mapping and gamma correction methods adopt a function mapping with the same range of input and output, the results are pleasurable for almost symmetric distributions to their intensity average. However, their corrections gave insufficient outputs for asymmetric cases at either bright or dark regions. Also, histogram modification approaches show good results on varied pattern images, but these generate unintentional noises at flat regions because of the compulsive shift of the intensity distribution. Therefore, in order to sufficient corrections for both bright and dark areas, the proposed algorithm calculates the gamma coefficients using primary parameters extracted from the global distribution. And the fusion weights are adaptively determined with complementary parameters, considering the classification information of a binary segmentation. As the result, the proposed algorithm can obtain a good output about both the symmetric and the asymmetric distribution images even with severe exposure values.

Image stacking technique is one of the key techniques for complex surface reconstruction. The process includes sample collection, image processing, algorithm editing, surface reconstruction, and finally reaching reliable conclusions. Since this experiment is based on laser scanning confocal microscope to collect the original contour information of the sample, it is necessary to briefly introduce the relevant principle and operation method of laser scanning confocal microscope. After that, the original image is collected and processed, and the data is expanded by interpolation method. Meanwhile, several methods of surface reconstruction are listed. After comparing the advantages and disadvantages of each method, one-dimensional interpolation and volume rendering are finally used to reconstruct the 3D model. The experimental results show that the final 3d surface modeling is more consistent with the appearance information of the original samples. At the same time, the algorithm is simple and easy to understand, strong operability, and can meet the requirements of surface reconstruction of different types of samples.

Since most biosignals rely on contact-based measurement, there is still a problem in that it is hard to provide convenience to users by applying them to daily life. In this paper, we present a mobile application for estimating heart rate based on a deep learning model. The proposed application measures heart rate by capturing real-time face images in a non-contact manner. We trained a three-dimensional convolutional neural network to predict photoplethysmography (PPG) from face images. The face images used for training were taken in various movements and situations. To evaluate the performance of the proposed system, we used a pulse oximeter to measure a ground truth PPG. As a result, the deviation of the calculated root means square error between the heart rate from remote PPG measured by the proposed system and the heart rate from the ground truth was about 1.14, showing no significant difference. Our findings suggest that heart rate measurement by mobile applications is accurate enough to help manage health during daily life.

Skin prick test is widely used in diagnosing allergic sensitization to common inhalant or food allergens, in which positivities are manually determined by calculating the areas or mean diameters of wheals and erythemas provoked by allergens pricked into patients' skin. In this work, we propose a segmentation algorithm over U-Net, one of the FCN models of deep learning, to help us more objectively grasp the erythema boundaries. The performance of the model is analyzed by comparing the results of automatic segmentation of the test data to U-Net with the results of manual segmentation. As a result, the average Dice coefficient value was 94.93%, the average precision and sensitivity value was 95.19% and 95.24% respectively. We find that the proposed algorithm effectively discriminates the skin's erythema boundaries. We expect this algorithm to play an auxiliary role in skin prick test in real clinical trials in the future.

Identification and analysis of the first and second heart sounds(S1, S2) is the easiest way for cardiovascular disease prevention and early diagnosis. However, accurate identification is difficult because the heart sound includes organ movement, blood vortex, user experience, and noise influenced by subjective judgment. Therefore, an algorithm to automatically identify the S1 and S2 heart sounds based on blood vessel transit time(VTT) is presented in this paper. According to the experimental results of comparing the algorithm developed for S1 and S2 heart sound analysis with the conventional Shannon energy algorithm in 10 volunteers, it has been proven that the proposed algorithm can automatically identify S1 and S2 heart sounds with higher accuracy than existing algorithms.

In CCTV environments, a lot of learning image data is required to monitor illegal dumping of garbage with a typical image-based object detection using deep learning method. In this paper, we propose a system to monitor unauthorized dumping of garbage by learning the articular points of the person using only a small number of images without immediate use of the image for deep learning. In experiment, the proposed system showed 74.97% of garbage dumping detection performance with only a relatively small amount of image data in CCTV environments.

Due to the growth of VR industry and rise of digital twin industry, the importance of implementing 3D data same as real space is increasing. However, the fact that it requires expertise personnel and huge amount of time is a problem. In this paper, we propose a system that generates point cloud data with same shape and color as a real space, just by scanning the space. The proposed system integrates 3D geometric information from lidar and color information from stereo camera into one point cloud. Since the number of 3D points generated by lidar is not enough to express a real space with good quality, some of the pixels of 2D image generated by camera are mapped to the correct 3D coordinate to increase the number of points. Additionally, to minimize the capacity, overlapping points are filtered out so that only one point exists in the same 3D coordinates. Finally, 6DoF pose information generated from lidar point cloud is replaced with the one generated from camera image to position the points to a more accurate place. Experimental results show that the proposed system easily and quickly generates point clouds very similar to the scanned space.

Due to the difference between the underwater communication environment and the terrestrial communication environment, the radio communication mainly used on the ground cannot be used in underwater. For this reason, in the underwater communication environment, various communication media such as acoustic waves, infrared rays, light and so on has been studied, but there exist several difficulties in operating them individually due to their physical limitations. The concept for overcoming these difficulties is the very underwater multi-media communication, a method to select a communication medium best suitable for the current underwater environment among underwater communication multimedia whenever there occurs underwater communication failure. In this paper, we present an underwater multi-media communication network based on star topology and a fragmentation and reassembly technique to solve the problems caused by the different MTU (Maximum Transmission Unit) sizes among different underwater communication media. We also present the estimations and analysis on processing times in each of fragmentation and reassembly and the total data amount for transmitting fragments in our proposed underwater multi-media communication network.

The current drone flight plan creation creates a flight path point of two-dimensional coordinates on the map and sets an arbitrary altitude value considering the altitude of the terrain and the possible flight altitude. If the created flight path is a simple terrain such as a mountain or field, or if the user is familiar with the terrain, setting the flight altitude will not be difficult. However, for drone flight in a city where buildings are dense, a safer and more precise flight path generation method is needed. In this study, using high-precision spatial information, we construct a drone safety flight map with a 3D grid map structure and propose a flight path search algorithm based on it. The safety of the flight path is checked through the virtual drone flight simulation extracted by searching for the flight path based on the 3D grid map created by setting weights on the properties of obstacles and terrain such as buildings.

Convolution neural networks (CNNs) show notable performance in image processing and are used as representative core models. CNNs extract and learn features from large amounts of train dataset. In general, it has a structure in which a convolution layer and a fully connected layer are stacked. The core of CNN is the convolution layer. The size of the kernel used for feature extraction and the number that affect the depth of the feature map determine the amount of weight parameters of the CNN that can be learned. These parameters are the main causes of increasing the computational complexity and memory usage of the entire neural network. The most computationally expensive components in CNNs are fully connected and spatial convolution computations. In this paper, we propose a Fourier Convolution Neural Network that performs the operation of the convolution layer in the Fourier domain. We work on modifying and improving the amount of computation by applying the fast fourier transform method. Using the MNIST dataset, the performance was similar to that of the general CNN in terms of accuracy. In terms of operation speed, 7.2% faster operation speed was achieved. An average of 19% faster speed was achieved in experiments using 1024x1024 images and various sizes of kernels.

Cyber Sickness, which occurs when using Virtual Reality contents, is the most serious problem in immersive Virtual Reality contents. The purpose of this study is to identify the effects and causes of graphic environmental factors on Cyber Sickness in Virtual Reality contents. To this end, cyber sickness experiments were conducted according to the light source and material settings, which are most commonly used in graphical environmental elements. Cyber Sickness measurements were based on the Simulator Sickness Question(SSQ) tool to derive an index that causes Cyber Sickness As a result of the analysis, the smaller the surface roughness, the higher the degree of Cyber Sickness, and the smaller the surface roughness, the smoother the surface of the 3D object, and many specular reflections from the light source occurred, which was confirmed to be the cause of great Cyber Sickness.

This study describes a multicultural literacy program that can nurture multicultural people who can live in a multicultural society. A total of 10 20-hour programs were conducted for 22 youths in Busan. Through this, the current perception and acceptance of multiculturalism among young people in Busan was investigated, and a curriculum suitable for multicultural awareness, multicultural acceptance, and multicultural competency enhancement was constructed. In accordance with the goal of strengthening the multicultural competency required for multicultural activists through education, learners can exchange opinions through the activity sheet, so that learners can know the difference between themselves and others. Students could learn about each other's culture and values through cultural exchange with others, and through teachers with diverse cultures, they could learn various perspectives and cultures about culture and values. Through the results of the multicultural literacy program, I would like to suggest three methods of multicultural literacy education to strengthen multicultural competence in a multicultural society. Therefore, efforts should be made to develop various multicultural education courses to strengthen the multicultural capabilities of Koreans.

Currently, the development and sale of various emoticons has given users a wider range of choices, but a systematic and specific approach to the recognition and use of emoticons by actual users is lacking. Therefore, this study tried to investigate the subjective perception and visual attention concentration of actual users on negative emotional expression emoticons through a survey and eye tracking experiment. First, as a result of subjective recognition analysis, it was found that emoticons are frequently used because their appearance is important, and they can express various emotions in a fun and interesting way. In particular, it was found that emoticons that express negative emotions are often used because they can indirectly express negative emotions through various and concretely expressed visual elements. Next, as a result of the eye tracking experiment, it was found that the negative emotional expression emoticons focused on the large elements that visually emphasized or emphasized the emotional expression elements, and it was found that the focus was not only on the facial expression but also on the physical behavioral responses and language of expression of emotions. These results will be used as basic data to understand users' perceptions and utilization of the diversified emoticons. In addition, for the long-term growth and activation of the emoticon industry market in the future, continuous research should be conducted to understand the various emotions of real users and to develop differentiated emoticons that can maximize the empathy effect appropriate to the situation.