• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.12
• /
• pp.3274-3292
• /
• 2013

Unsupervised methods for image segmentation are recently drawing attention because most images do not have labels or tags. A topic model is such an unsupervised probabilistic method that captures latent aspects of data, where each latent aspect, or a topic, is associated with one homogeneous region. The results of topic models, however, usually have noises, which decreases the overall segmentation performance. In this paper, to improve the performance of image segmentation using topic models, we propose two topic masks applicable to topic assignments of homogeneous regions obtained from topic models. The topic masks capture the noises among the assigned topic assignments or topic labels, and remove the noises by replacements, just like image masks for pixels. However, as the nature of topic assignments is different from image pixels, the topic masks have properties that are different from the existing image masks for pixels. There are two contributions of this paper. First, the topic masks can be used to reduce the noises of topic assignments obtained from topic models for image segmentation tasks. Second, we test the effectiveness of the topic masks by applying them to segmented images obtained from the Latent Dirichlet Allocation model and the Spatial Latent Dirichlet Allocation model upon the MSRC image dataset. The empirical results show that one of the masks successfully reduces the topic noises.

• Journal of the Korea Convergence Society
• /
• v.3 no.4
• /
• pp.15-21
• /
• 2012

Image segmentation for object to extract data from ultrasound acquired is an essential preprocessing step for the effective diagnosis. Various image segmentation methods have been studied. In this study, interactive image segmentation method by graph cut algorithm is proposed to develop a variety of applications of vascular ultrasound imaging and diagnostics. General imaging and vascular ultrasound imaging segmentation by entering constrain condition such as foreground and background. In the future it will be able to develop new ultrasound diagnostics.

• The Journal of Fisheries Business Administration
• /
• v.49 no.4
• /
• pp.53-68
• /
• 2018

The industrial structure of Chuja Island is mainly occupied by fisheries. Since the fisheries resources have been depleted and the marine environment has been changed, the fishery industry has been hard to survive. It is the time when residents are looking for a breakthrough in the tourism industry. Market segmentation is a valuable tool in the establishment of marketing strategies. Segmentation of tourists by the same desire and motivation is an essential factor in identifying the characteristics of tourists. The research on market segmentation of tourism sector focuses mainly on demographic subdivision, psychological subdivision, and behavioral subdivision, so it is urgent to study geographical market segmentation. The purpose of this study is to present data that can be used to establish a marketing strategy for tourism promotion in Chuja Island by analyzing the tourism activities via subdivision market according to demographic characteristics, tourism behavior characteristics, and tourism motivation after grasping the geographical segment of tourists through empirical analysis. In this study, 285 valid samples were analyzed by frequency analysis, ${\chi}^2$ test, cluster analysis and ANOVA test.

• Journal of Korea Multimedia Society
• /
• v.25 no.5
• /
• pp.661-669
• /
• 2022

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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.2
• /
• pp.471-485
• /
• 2023

As data sharing increases explosively, such information encoded in QR code is completely public as private messages are not securely protected. This paper proposes a new 'PROMISE' framework for hiding information based on the QR code projection matrix by using image segmentation without modifying the essential QR code characteristics. Projection matrix mapping, matrix scrambling, fusion image segmentation and steganography with SEL(secret embedding logic) are part of the PROMISE framework. The QR code could be mapped to determine the segmentation site of the fusion image as a binary information matrix. To further protect the site information, matrix scrambling could be adopted after the mapping phase. Image segmentation is then performed on the fusion image and the SEL module is applied to embed the secret message into the fusion image. Matrix transformation and SEL parameters should be uploaded to the server as the secret key for authorized users to decode the private message. And it was possible to further obtain the private message hidden by the framework we proposed. Experimental findings show that when compared to some traditional information hiding methods, better anti-detection performance, greater secret key space and lower complexity could be obtained in our work.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.215-223
• /
• 2021

3D data can be categorized into two parts : Euclidean data and non-Euclidean data. In general, 3D data exists in the form of non-Euclidean data. Due to irregularities in non-Euclidean data such as mesh and point cloud, early 3D deep learning studies transformed these data into regular forms of Euclidean data to utilize them. This approach, however, cannot use memory efficiently and causes loses of essential information on objects. Thus, various approaches that can directly apply deep learning architecture to non-Euclidean 3D data have emerged. In this survey, we introduce various deep learning methods for mesh and point cloud data. After analyzing the operating principles of these methods designed for irregular data, we compare the performance of existing methods for shape classification and segmentation tasks.

• Journal of Information Technology Applications and Management
• /
• v.22 no.1
• /
• pp.77-93
• /
• 2015

As the range of the customer choice becomes more diverse, the average life span of companies' products and services is becoming shorter. Most companies are striving to maximize the revenue by understanding the customer's needs and providing customized products and services. However, companies had to bear a significant burden, in terms of the time and cost involved in the process of determining each individual customer's needs. Therefore, an alternative method is employed that involves grouping the customers into different categories based on certain criteria and establishing a marketing strategy tailored for each group. In this way, customer segmentation and customer clustering are performed using demographic information and behavioral information. Demographic information included sex, age, income level, and etc., while behavioral information was usually identified indirectly through customers' purchase history and search history. However, there is a limitation regarding companies' customer behavioral information, because the information is usually obtained through the limited data provided by a customer on a company's website. This is because the pattern indicated when a customer accesses a particular site might not be representative of the general tendency of that customer. Therefore, in this study, rather than the pattern indicated through a particular site, a customer's interest is identified using that customer's access record pertaining to external news. Hence, by utilizing this method, we proposed a methodology to perform customer segmentation. In addition, by extracting the main issues through a topic analysis covering approximately 3,000 Internet news articles, the actual experiment applying customer segmentation is performed and the applicability of the proposed methodology is analyzed.

• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.5
• /
• pp.187-195
• /
• 2005

A new segmentation-based image coding method which no needs transmission of contour data is proposed. The shape information acts as bottleneck in the segmentation-based video coding because it has much portion of transmission data. The proposed method segments a previous decoded frame, instead of a current frame. As a result, there is no need for transmission of contour information to a decoder. Therefore, the saved bits can be assigned to encode other information such as error signals. As shown in experiment results, if data rate is very highly increased due to abrupt motion under very low bit rate coding having limited transmission bits, PSNR of conventional block-based method go down about 20dB, while the proposed method shows a good reconstruction quality without rapid PSNR drop.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.9
• /
• pp.1049-1059
• /
• 2019

We propose a learning-based image segmentation algorithm. Starting from super-pixels, our method learns the probability of merging two regions based on the ground truth made by humans. The learned information is used in determining whether the two regions should be merged or not in a segmentation stage. Unlike exiting learning-based algorithms, we use both local and object information. The local information represents features computed from super-pixels and the object information represent high level information available only in the learning process. The object information is considered as privileged information, and we can use a framework that utilize the privileged information such as SVM+. In experiments on the Berkeley Segmentation Dataset and Benchmark (BSDS 500) and PASCAL Visual Object Classes Challenge (VOC 2012) data set, out model exhibited the best performance with a relatively small training data set and also showed competitive results with a sufficiently large training data set.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.365-381
• /
• 2023

The existing vision-based techniques for inspection and condition assessment of civil infrastructure are mostly manual and consequently time-consuming, expensive, subjective, and risky. As a viable alternative, researchers in the past resorted to deep learning-based autonomous damage detection algorithms for expedited post-disaster reconnaissance of structures. Although a number of automatic damage detection algorithms have been proposed, the scarcity of labeled training data remains a major concern. To address this issue, this study proposed a semi-supervised learning (SSL) framework based on consistency regularization and cross-supervision. Image data from post-earthquake reconnaissance, that contains cracks, spalling, and exposed rebars are used to evaluate the proposed solution. Experiments are carried out under different data partition protocols, and it is shown that the proposed SSL method can make use of unlabeled images to enhance the segmentation performance when limited amount of ground truth labels are provided. This study also proposes DeepLab-AASPP and modified versions of U-Net++ based on channel-wise attention mechanism to better segment the components and damage areas from images of reinforced concrete buildings. The channel-wise attention mechanism can effectively improve the performance of the network by dynamically scaling the feature maps so that the networks can focus on more informative feature maps in the concatenation layer. The proposed DeepLab-AASPP achieves the best performance on component segmentation and damage state segmentation tasks with mIoU scores of 0.9850 and 0.7032, respectively. For crack, spalling, and rebar segmentation tasks, modified U-Net++ obtains the best performance with Igou scores (excluding the background pixels) of 0.5449, 0.9375, and 0.5018, respectively. The proposed architectures win the second place in IC-SHM2021 competition in all five tasks of Project 2.