The purpose of this study is to compare and analyze Deep Learning (DL) and Digital Image Processing (DIP) techniques using the results of the glottis segmentation of the two methods followed by the quantification of the asymmetric degree of the vocal cord mucosa. The data consists of 40 normal and abnormal images. The DL model is based on Deeplab V3 architecture, and the Canny edge detector algorithm and morphological operations are used for the DIP technique. According to the segmentation results, the average accuracy of the DL model and the DIP was 97.5% and 94.7% respectively. The quantification results showed high correlation coefficients for both the DL experiment (r=0.8512, p<0.0001) and the DIP experiment (r=0.7784, p<0.0001). In the conclusion, the DL model showed relatively higher segmentation accuracy than the DIP. In this paper, we propose the clinical applicability of this technique applying the segmentation and asymmetric quantification algorithm to the glottal area in the laryngoscopic images.

This study proposes an improved binarization method to improve image recognition rate. The research goal is to minimize the information loss that occurs during the binarization process, and to transform the object of the original image that cannot be determined through the transformation process into an image that can be judged. The proposed method uses a stepwise segmentation method of an image and divides blocks using prime numbers. Also, within one block, a trapezoidal type of fuzzy is applied. The fuzzy trapezoid is binarized by dividing the brightness histogram area into three parts according to the degree of membership. As a result of the experiment, information loss was minimized in general images. In addition, it was found that the converted binarized image expressed the object better than the original image in the special image in which the brightness region was tilted to one side.

As realistic media are widespread in various image processing areas, image or video compression is one of the key technologies to enable real-time applications with limited network bandwidth. Generally, image or video compression cause the unnecessary compression artifacts, such as blocking artifacts and ringing effects. In this study, we propose a Deep Residual Channel-attention Network, so called DRCAN, which consists of an input layer, a feature extractor and an output layer. Experimental results showed that the proposed DRCAN can reduced the total memory size and the inference time by as low as 47% and 59%, respectively. In addition, DRCAN can achieve a better peak signal-to-noise ratio and structural similarity index measure for compressed images compared to the previous methods.

The goal of few-shot semantic segmentation is to build a network that quickly adapts to novel classes with extreme data shortage regimes. Most existing few-shot segmentation methods leverage single or multiple prototypes from extracted support features. Although there have been promising results for natural images, these methods are not directly applicable to the aerial image domain. A key factor in few-shot segmentation on aerial images is to effectively exploit information that is robust against extreme changes in background and object scales. In this paper, we propose a Mask-Guided Attention module to extract more comprehensive support features for few-shot segmentation in aerial images. Taking advantage of the support ground-truth masks, the area correlated to the foreground object is highlighted and enables the support encoder to extract comprehensive support features with contextual information. To facilitate reproducible studies of the task of few-shot semantic segmentation in aerial images, we further present the few-shot segmentation benchmark iSAID-, which is constructed from a large-scale iSAID dataset. Extensive experimental results including comparisons with the state-of-the-art methods and ablation studies demonstrate the effectiveness of the proposed method.

In this paper, we propose the method of a table structure recognition in various table types for document processing automation. A table with items surrounded by ruled lines are analyzed by detecting horizontal and vertical lines for recognizing the table structure. In case of a table with items separated by spaces, the table structure are recognized by analyzing the arrangement of row items. After recognizing the table structure, the areas of the table items are input into OCR engine and the character recognition result output to a text file in a structured format such as CSV or JSON. In simulation results, the average accuracy of table item recognition is about 94%.

Based on the love styles theory used in psychology, this paper classifies users(Passionate Love, Game-playing Love, Friendship Love, Practical Love, Possessive Love, Altruistic Love) and investigates satisfaction with the motivation for using TikTok love videos(Entertainment, Social Relationship, Love skills-learning, Self-verification, Problem-solving) according to the theory of use and satisfaction. First, 414 users were selected to conduct TikTok surveys to collect data. Then, through the analysis of the research results, among the six love types, game-playing type and possessive type have a positive (+) impact on entertainment motivation and love skill-learning motivation. Game-playing type also have a positive (+) impact on social relationship motivation and self-verification motivation. In addition, altruistic type and possessive type are also factors to strengthen the motivation of self-verification. The altruistic type, possessive type and practical type will improve the problem-solving motivation. Finally, through hierarchial multiple regression analysis, it is confirmed that game-playing love type, entertainment motivation, love skill-learning motivation and self-verification motivation can improve user satisfaction. The above results enrich the research of user classification as well as providing inspiration for improving the quality and communication efficiency of TikTok's video and enhancing user experience.

The pandemic of COVID-19 has led "E-commerce+ Live streaming", the new form of retail business, development rapidly. And more and more consumers choose to buy commodities in E-commerce live streaming. According to the related investigation at home and abroad, the purchase intention and WOM intention are two important measuring factors of the effect of the direct transmission of e-commerce. In previous research, the author proved that IWOM has become an important reference for consumers to make online purchases. In this study, the author mainly focus on the impact of online WOM on consumer intention. Based on the Involvement Theory, this paper proposes a model of the influence of IWOM on WOM intention in e-commerce live broadcast which is adjusted by the product involvement degree. The results show that the characteristics of anchor, the quantity and quality of IWOM, the prescription of IWOM, the difference of IWOM and the intention of WOM are positively regulated by the product involvement. However, product involvement did not play a moderating role between relationship strength and WOM intention.

Based on visual Thinking theory, VR(virtual reality) game changes the traditional form of memory and maps the content into game elements to realize the immersive spatial memory mode. This paper analyzes the influencing factors of game design and system function construction. This paper proposes a hypothesis: with the help of visual thinking theory, VR game is helpful to improve learners' visual memory, and carries out research. The experiment sets different levels of game through empirical research and case analysis of memory flip game. For example, when judging two random cards. If the pictures are the same, it will be judged as the correct combination; if they are different, the two cards will be restored to the original state. The results are analyzed by descriptive statistical analysis and AMOS data analysis. The results show that game content using the concept of "Memory Palace", which can improve the accuracy of memory. We conclude that the use of spatial localization characteristics in flip games combining visual thinking can improve users' memory by helping users memorize and organize information in a Virtual environment, which means VR games have strong feasibility and effectiveness in improving memory.

In this study, the effect of augmented reality subtitle content on users was investigated by using a subjective evaluation method and a statistical approach. The human factor was defined as subtitle position and font size. Then, we analyzed the effects of the defined factors on human eye comfort and visibility. Ten participants conducted related survey evaluation tasks with a 1-minute break after viewing the content for 3 minutes.

Thanks to the competition of AlphaGo and Sedol Lee, machine learning has received world-wide attention and huge investments. The performance improvement of computing devices greatly contributed to big data processing and the development of neural networks. Artificial intelligence not only imitates human beings in many fields, but also seems to be better than human capabilities. Although humans' creation is still considered to be better and higher, several artificial intelligences continue to challenge human creativity. The quality of some creative outcomes by AI is as good as the real ones produced by human beings. Sometimes they are not distinguishable, because the neural network has the competence to learn the common features contained in big data and copy them. In order to confirm whether artificial intelligence can express the inherent characteristics of different arts, this paper proposes a new neural network model called Humming. It is an experimental model that combines vgg16, which extracts image features, and DeepJ's architecture, which excels in creating various genres of music. A dataset produced by our experiment shows meaningful and valid results. Different results, however, are produced when the amount of data is increased. The neural network produced a similar pattern of music even though it was a different classification of images, which was not what we were aiming for. However, these new attempts may have explicit significance as a starting point for feature transfer that will be further studied.

In this paper, we proposed a system that visualizes a hologram device in 3D by utilizing the CT image segmentation function based on artificial intelligence deep learning. The input axial CT medical image is converted into Sagittal and Coronal, and the input image and the converted image are divided into 3D volumes using ResUNet, a deep learning model. In addition, the volume is created by segmenting the tumor region in the segmented liver image. Each result is integrated into one 3D volume, displayed in a medical image viewer, and converted into a video. When the converted video is transmitted to the hologram device and output from the device, a 3D image with a sense of space can be checked. As for the performance of the deep learning model, in Axial, the basic input image, DSC showed 95.0% performance in liver region segmentation and 67.5% in liver tumor region segmentation. If the system is applied to a real-world care environment, additional physical contact is not required, making it safer for patients to explain changes before and after surgery more easily. In addition, it will provide medical staff with information on liver and liver tumors necessary for treatment or surgery in a three-dimensional manner, and help patients manage them after surgery by comparing and observing the liver before and after liver resection.