• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2333-2345
• /
• 2024

Facial wrinkles are widely used to evaluate skin condition or aging for various fields such as skin diagnosis, plastic surgery consultations, and cosmetic recommendations. In order to effectively process facial wrinkles in facial image analysis, accurate wrinkle segmentation is required to identify wrinkled regions. Existing deep learning-based methods have difficulty segmenting fine wrinkles due to insufficient wrinkle data and the imbalance between wrinkle and non-wrinkle data. Therefore, in this paper, we propose a new facial wrinkle segmentation method based on a UNet++ model. Specifically, we construct a new facial wrinkle dataset by manually annotating fine wrinkles across the entire face. We then extract only the skin region from the facial image using a facial landmark point extractor. Lastly, we train the UNet++ model using both dice loss and focal loss to alleviate the class imbalance problem. To validate the effectiveness of the proposed method, we conduct comprehensive experiments using our facial wrinkle dataset. The experimental results showed that the proposed method was superior to the latest wrinkle segmentation method by 9.77%p and 10.04%p in IoU and F1 score, respectively.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2010.04a
• /
• pp.231-233
• /
• 2010

Many algorithms for processing LIDAR data are being developed for diverse applications not limited to patch segmentation, bare-earth filtering and building extraction. However, since we cannot exactly know the true locations of LIDAR points, it is difficult to assess the performance of a LIDAR data processing algorithm. In this paper, we thus attempted the performance assessment of the segmentation algorithm developed by Lee (2006) using the LIDAR data generated through simulation based on sensor modelling. Consequently, based on simulation, we can perform the performance assessment of a LIDAR processing algorithm more objectively and quantitatively with an automatic procedure.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1663-1676
• /
• 2022

Recently, a number of deep-learning based land cover segmentation studies have been introduced. Some studies denoted that the performance of land cover segmentation deteriorated due to insufficient training data. In this study, we verified the improvement of land cover segmentation performance through data augmentation. U-Net was implemented for the segmentation model. And 2020 satellite-derived landcover dataset was utilized for the study data. The pixel accuracies were 0.905 and 0.923 for U-Net trained by original and augmented data respectively. And the mean F1 scores of those models were 0.720 and 0.775 respectively, indicating the better performance of data augmentation. In addition, F1 scores for building, road, paddy field, upland field, forest, and unclassified area class were 0.770, 0.568, 0.433, 0.455, 0.964, and 0.830 for the U-Net trained by original data. It is verified that data augmentation is effective in that the F1 scores of every class were improved to 0.838, 0.660, 0.791, 0.530, 0.969, and 0.860 respectively. Although, we applied data augmentation without considering class balances, we find that data augmentation can mitigate biased segmentation performance caused by data imbalance problems from the comparisons between the performances of two models. It is expected that this study would help to prove the importance and effectiveness of data augmentation in various image processing fields.

• Journal of Digital Convergence
• /
• v.7 no.3
• /
• pp.93-102
• /
• 2009

Recently, concerns regarding ubiquitous health have been on the increase according to development of ubiquitous technology and growth of health industry. This study suggested a necessity for market segmentation for the creation of new markets of ubiquitous health business under this background. This paper also analyzed possibile health service industry with characteristics of customers by making an analysis of market segmentation. It was grouped into 4 parts by factor analysis and cluster analysis with raw data collected, the results showed that they would be main potential ubiquitous health service industry. However, some are not significant in statistics, which means that since ubiquitous health industry has not yet been experienced, it probably shows uncertainty about its favour. Finally, the study suggested that a future study should build up more detailed market segmentation data with continuous supplementation.

• Korean Journal of Remote Sensing
• /
• v.26 no.6
• /
• pp.731-740
• /
• 2010

A region merging technique is suggested in this paper for the segmentation of high-spatial resolution imagery. It employs a region growing scheme based on the region adjacency graph (RAG). The proposed algorithm uses directional neighbor-line average feature vectors to improve the quality of segmentation. The feature vector consists of 9 components which includes an observation and 8 directional averages. Each directional average is the average of the pixel values along the neighbor line for a given neighbor line length at each direction. The merging coefficients of the segmentation process use a part of the feature components according to a given merging coefficient order. This study performed the extensive experiments using simulation data and a real high-spatial resolution data of IKONOS. The experimental results show that the new approach proposed in this study is quite effective to provide segments of high quality for the object-based analysis of high-spatial resolution images.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.5
• /
• pp.799-806
• /
• 2021

In the IoT environment, event data from sensors is continuously reported over time. Event data obtained in this trend is accumulated indefinitely, so a method for efficient analysis and management of data is required. In this study, a data stream segmentation method was proposed to support the effective selection and utilization of event data from sensors that are continuously reported and received. An identifier for identifying the point at which to start the analysis process was selected. By introducing the role of these identifiers, it is possible to clarify what is being analyzed and to reduce data throughput. The identifier for stream segmentation proposed in this study is a semantic-oriented data stream segmentation method based on the event occurrence of each stream. The existence of identifiers in stream processing can be said to be useful in terms of providing efficiency and reducing its costs in a large-volume continuous data inflow environment.

• MALSORI
• /
• no.47
• /
• pp.131-140
• /
• 2003

We propose a new method of generating client models for HMM based text-dependent speaker verification system with only a small amount of training data. To make a client model, statistical methods such as segmental K-means algorithm are widely used, but they do not guarantee the quality or reliability of a model when only limited data are avaliable. In this paper, we propose a blind speech segmentation based on level building DTW algorithm as an alternative method to make a client model with limited data. In addition, considering the fact that voiced sounds have much more speaker-specific information than unvoiced sounds and energy of the former is higher than that of the latter, we also propose a new score evaluation method using the observation probability raised to the power of weighting factor estimated from the normalized log energy. Our experiment shows that the proposed methods are superior to conventional HMM based speaker verification system.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.808-813
• /
• 2022

This study presents the problems of data imbalance, varying difficulties across target objects, and small objects in construction object segmentation for far-field monitoring and utilize compound loss functions to address it. Construction site scenes of assembling scaffolds were analyzed to test the effectiveness of compound loss functions for five construction object classes---workers, hardhats, harnesses, straps, hooks. The challenging problem was mitigated by employing a focal and Jaccard loss terms in the original loss function of LinkNet segmentation model. The findings indicates the importance of the loss function design for model performance on construction site scenes for far-field monitoring.

• Journal of Korean Library and Information Science Society
• /
• v.38 no.3
• /
• pp.277-296
• /
• 2007

This study aims to propose that archives introduce marketing strategies for their archival reference services. Target marketing which is based on market segmentation for customer satisfaction is popular among enterprises in these days. Market segmentation strategy of target marketing need to be used for user centered archival reference services in archives. This study proposed that demographic, geographic, psychographics, and use variables can be used for archival user segmentation. And for the user segmentation, archives should collect data of use and users systematically.

• Journal of Information Technology Applications and Management
• /
• v.23 no.2
• /
• pp.11-28
• /
• 2016

In this paper, we proposed a dictionary extension and a ternary decomposition technique to improve the effectiveness of Khmer word segmentation. Most word segmentation approaches depend on a dictionary. However, the dictionary being used is not fully reliable and cannot cover all the words of the Khmer language. This causes an issue of unknown words or out-of-vocabulary words. Our approach is to extend the original dictionary to be more reliable with new words. In addition, we use ternary decomposition for the segmentation process. In this research, we also introduced the invisible space of the Khmer Unicode (char\u200B) in order to segment our training corpus. With our segmentation algorithm, based on ternary decomposition and invisible space, we can extract new words from our training text and then input the new words into the dictionary. We used an extended wordlist and a segmentation algorithm regardless of the invisible space to test an unannotated text. Our results remarkably outperformed other approaches. We have achieved 88.8%, 91.8% and 90.6% rates of precision, recall and F-measurement.