• Journal of Korea Multimedia Society
• /
• v.3 no.5
• /
• pp.454-460
• /
• 2000

To retrieve complex data such as images, the content-based retrieval method rather than keyword based method is required. In this paper, we implemented a content-based image retrieval system which retrieves object of user query effectively using invariant moments which have invariant properties about linear transformation like position transition, rotation and scaling. To extract the shape feature of objects in an image, we propose a labeling algorithm that extracts objects from an image and apply invariant moments to each object. Hashing method is also applied to reduce a retrieval time and index images effectively. The experimental results demonstrate the high retrieval efficiency i.e precision 85%, recall 23%. Consequently, our retrieval system shows better performance than the conventional system that cannot express the shale of objects exactly.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.9
• /
• pp.950-956
• /
• 2014

In this paper, the real-time detection method of a DDP (Driving Direction Point) is proposed for an unmanned vehicle to safely follow the center of the road. Since the DDP is defined as a center point between two lanes, the lane is first detected using a web camera. For robust detection of the lane, the binary thresholding and the labeling methods are applied to the color camera image as image preprocessing. From the preprocessed image, the lane is detected, taking the intrinsic characteristics of the lane such as width into consideration. If both lanes are detected, the DDP can be directly obtained from the preprocessed image. However, if one lane is detected, the DDP is obtained from the inverse perspective image to guarantee reliability. To verify the proposed method, several experiments to detect the DDPs are carried out using a 4 wheeled vehicle ERP-42 with a web camera.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.25 no.3
• /
• pp.17-29
• /
• 2023

This study collected and analyzed reference information on the size labeling method and size of clothing products in 13 online shopping malls for plus size women in their 20s and 30s, and compared the size specification information focusing on jeans. First, in the results of examining the method of clothing size designation, clothing sizes indicated by 1, 2, 3 or physique designation (M, L, XL) differed between shopping malls, and even in the same shopping mall, even if the same size notation was used. Most the clothing sizes were different depending on the type of clothing. For bottoms, it was found that one company used seven size designation methods at the same time, two shopping malls used four size designation methods, and five shopping malls used three size designation methods. In the meantime, in the results of comparing the size specifications of jeans XL (size 88, 32 inches) by product part, for waist and hip circumferences, each of the eight companies showed that the size was smaller than the body size suggested by KS adult women's wear.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.1
• /
• pp.9-16
• /
• 2010

Moving object detection is to detect foreground object different from background scene in a new incoming image frame and is an essential ingredient process in some image processing applications such as intelligent visual surveillance, HCI, object-based video compression and etc. Most of previous object detection algorithms are still computationally heavy so that it is difficult to develop real-time multi-channel moving object detection in a workstation or even one-channel real-time moving object detection in an embedded system using them. Foreground mask correction necessary for a more precise object detection is usually accomplished using morphological operations like opening and closing. Morphological operations are not computationally cheap and moreover, they are difficult to be rendered to run simultaneously with the subsequent connected component labeling routine since they need quite different type of processing from what the connected component labeling does. In this paper, we first devise a fast and precise foreground mask correction algorithm, "Neighbor Foreground Pixel Propagation (NFPP)" which utilizes neighbor pixel checking employed in the connected component labeling. Next, we propose a novel moving object detection method based on the devised foreground mask correction algorithm, NFPP where the connected component labeling routine can be executed simultaneously with the foreground mask correction. Through experiments, it is verified that the proposed moving object detection method shows more precise object detection and more than 4 times faster processing speed for a image frame and videos in the given the experiments than the previous moving object detection method using morphological operations.

• The Korean Journal of Nuclear Medicine
• /
• v.26 no.2
• /
• pp.380-391
• /
• 1992

This study was designed to evaluate a direct method of $^{99m}Tc$ labeling using $\beta-mercaptoethanol$ as a reducing agent, and to investigate whether $^{99m}Tc$ labeled specific monoclonal antibody against carcinoembryonic antigen (CEA-92) can be used for the scintigraphic localization of human colon cancer xenograft. Purified CEA-92 IgG was fragmented into F $(ab')_2$ and then labeled with $^{99m}Tc$ by transchelation method using glucarate as a chelator. Labeling efficiency, immunological reactivity and in vitro stability of $^{99m}Tc$ CEA-92 F $(ab')_2$ were measured and then injected intravenously into nude mice bearing human colon cancer (SNU-C4). Scintigrams were obtained at 24 hour after injection. Then nude mice were sacrificed and the radioactivity was measured Labeling efficiency of injected $^{99m}Tc$ CEA-92 F $(ab')_2$, immunoreative fraction and in vitro stability at 24 hour of injected $^{99m}Tc$ CEA-92 F $(ab')_2$ was 45.2%, 32.8% and 57.4%, respectively. At 24 hour after injection, % ID/g in kidney (46.77) showed high uptake, but %ID/g in tumor (1.65) was significantly higher than spleen (0.69), muscle (0.16), intestine (0.45), stomach (0.75), heart (0.48) and blood (0.45). There was no significant difference between tumor and liver (1.81). Tumor contrast as quantitated by tumor to blood ratio of $^{99m}Tc$ CEA-92 F $(ab')_2$ was increased significantly (p<0.005) until 24 hours (3.70), and there was no statistical differece from tumor to blood ratio of I-131 CEA-92 F $(ab')_2$. The scintigram demonstrated localization of radioactivity over transplanted tumor, but significant background radioactivity was also noted over kidney and abdomen. It is concluded that CEA-92 F $(ab')_2$ can be labeled with $^{99m}Tc$ by a direct transchelation method using $\beta-mercaptoethanol$ as a reducing agent and $^{99m}Tc$ labeled CEA-92 F $(ab')_2$ can be used for the scintigraphic localization of human colon cancer xenograft in nude mice model.

• Biomedical Science Letters
• /
• v.5 no.2
• /
• pp.155-165
• /
• 1999

This study involved applying rat sera (control, infected and immunized) to adult worm tissue in order to measure the antigenic response. A serum was obtained from rats infected with E. hortense metacercaria for 4 weeks. Another immunized serum was taken from rats given a muscle injection with crude adult worm antigen. The detection of antigenic response in E. hortense tissue was made by immunogold labeling method and measured through gold particles impregnated in the tissue. The antigenic sites, those with the highest density of gold particles, were the tegmental syncytium, vitelline cells, seminal receptacle and cecum.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.3
• /
• pp.375-382
• /
• 2010

In this study, we developed a method to predict the residual stress distribution and thermal deformation caused by in-mold labeling (IML) processes. IML is one of the injection molding processes for injecting a material into a cavity and subsequently inserting a decorated film. The IML process can yield products with decorations of outstanding excellent quality in only one working step. Although the IML process has various advantages, it causes defects such as film delamination, wash-out, and flow marks. In particular, deformation is considered to be a major concern in terms of delamination. To validate the model, the deformation predicted by using a numerical model was compared with experimental results, and both results showed good agreement. We verified that the developed method can be used to obtain the design guidelines for preventing delamination in the initial design stage of the IML process.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.24-29
• /
• 2022

Semantic role labeling task used in various natural language processing fields, such as information extraction and question answering systems, is the task of identifying the arugments for a given sentence and predicate. Predicate used as semantic role labeling input are extracted using lexical analysis results such as POS-tagging, but the problem is that predicate can't extract all linguistic patterns because predicate in korean language has various patterns, depending on the meaning of sentence. In this paper, we propose a korean predicate recognition method using neural network model with pre-trained embedding models and lexical features. The experiments compare the performance on the hyper parameters of models and with or without the use of embedding models and lexical features. As a result, we confirm that the performance of the proposed neural network model was 92.63%.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.801-804
• /
• 2008

During face recognition process, face detection process is most preceding process. However, face has very high floating property, so the result could be very different according to which method we used. This paper studies about eye detection and eye blinking verification using edge and color information from YCbCr distribution map, segmentation, and labeling methods.

• Bulletin of the Korean Chemical Society
• /
• v.33 no.2
• /
• pp.571-574
• /
• 2012

In present study, CdSe quantum dots (QDs) were prepared with a novel but simple, effective and exercisable method. Nine different types of carbohydrate molecules were used to modify CdSe QDs. D-mannose (Man)-coated quantum dots were prepared for labeling human hepatoma (HepG2) cells, because of the high expression of mannose receptor (MR) on HepG2 cells. The uptake characteristics of CdSe QDs-Man were investigated in HepG2 cells. The absorption rate result of MTT assay in 48 h suggested the extremely low cytotoxicity of CdSe QDs-Man. The presence of quantum dots was confirmed with fluorescence microscopy. These results were encouraging regarding the application of QDs molecules for early detection of HepG2 cells.