• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.731-734
• /
• 1998

A scalable parallel algorithm is proposed for efficient image component labeling with local operatos on a mesh connected SIMD computer. In contrast to the conventional parallel labeling algorithms, where a single pixel is assigned to each PE, the algorithm presented here is scalable and can assign m$\times$m pixel set to each PE according to the input image size. The assigned pixel set is converted to a single pixel that has representative value, and the amount of the required memory and processing time can be highly reduced. For N$\times$N image, if m$\times$m pixel set is assigned to each PE of P$\times$P mesh, where P=N/m, the time complexity due to the communication of each PE and the computation complexity are reduced to O(PlogP) bit operations and O(P) bit operations, respectively, which is 1/m of each of the conventional method. This method also diminishes the amount of memory in each PE to O(P), and can decrease the number of PE to O(P2) =Θ(N2/m2) as compared to O(N2) of conventional method. Because the proposed parallel labeling algorithm is scalable, we can adapt to the increase of image size without the hardware change of the given mesh connected SIMD computer.

• Journal of the Institute of Convergence Signal Processing
• /
• v.16 no.1
• /
• pp.1-8
• /
• 2015

In many image processing tasks, connected component labeling (CCL) is performed to extract regions of interest. CCL was usually done in a sequential fashion when image resolution was relatively low and there are small number of input channels. As image resolution gets higher up to HD or Full HD and as the number of input channels increases, sequential CCL is too time-consuming to be used in real time applications. To cope with this situation, parallel CCL framework was introduced where multiple cores are utilized simultaneously. Several parallel CCL methods have been proposed in the literature. Among them are NSZ label equivalence (NSZ-LE) method[1], modified 8 directional label selection (M8DLS) method[2], and HYBRID1 method[3]. Soh [3] showed that HYBRID1 outperforms NSZ-LE and M8DLS, and argued that HYBRID1 is by far the best. In this paper we propose an improved hybrid parallel CCL algorithm termed as HYBRID2 that hybridizes M8DLS with label backtracking (LB) and show that it runs around 20% faster than HYBRID1 for various kinds of images.

• Journal of Drive and Control
• /
• v.20 no.4
• /
• pp.92-99
• /
• 2023

Autonomous vehicles should recognize and respond to the specified speed to drive in compliance with regulations. To recognize the specified speed, the most representative method is to read the numbers of the signs by recognizing the speed signs in the front camera image. This study proposes a method that utilizes YOLO-Labeling-Labeling-EfficientNet. The sign box is first recognized with YOLO, and the numeric digit is extracted according to the pixel value from the recognized box through two labeling stages. After that, the number of each digit is recognized using EfficientNet (CNN) learned with the virtual environment dataset produced directly. In addition, we estimated the depth of information from the height value of the recognized sign through regression analysis. We verified the proposed algorithm using the virtual racing environment and GTSRB, and proved its real-time performance and efficient recognition performance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.9C
• /
• pp.860-867
• /
• 2003

In this paper, an efficient core point detection method using orientation pattern labeling is proposed in fingerprint image. The core point, which is one of the singular points in fingerprint image, is used as the reference point in the most fingerprint recognizing system. Therefore, the detection of the core point is the most essential step of the fingerprint recognizing system, it can affect in the whole system performance. The proposed method could detect the position of the core point by applying the labeling method for the directional pattern which is come from the distribution of the ridges in fingerprint image and applying detailed algorithms for the decision of the core point's position. The simulation result of proposed method is better than the result of Poincare index method and the sine map method in executing time and detecting rate. Especially, the Poincare index method can't detect the core point in the detection of the arch type and the sine map method takes too much times for executing. But the proposed method can overcome these problems.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.1117-1118
• /
• 2008

The LightScribe Technology is for printing images on the label side of recordable media using CD laser diode. By implementing Optimum Labeling Power Calibration for LightScribe, Labeling Quality can be improved. This paper proposes a new laser power calibration method using RFSUM signal. This function is implemented based on GH22LP20 of LG Electronics.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.241-241
• /
• 2000

In this Paper, we present a new efficient algorithm that can segment an object in the image. There are many algorithms for segmentation and many studies for criteria or threshold value. But, if the environment or brightness is changed, their would not be suitable. Accordingly, we apply a clustering algorithm for adopting and compensating environmental factors. And applying labeling method, we try arranging segment by the similarity that calculated with the fuzzy algorithm. we also present simulations for searching an object and show that the algorithm is somewhat more efficient than the other algorithm.

• Journal of KIISE
• /
• v.41 no.9
• /
• pp.699-706
• /
• 2014

As XML documents are getting bigger and more complex, a keyword-based search method that does not require structural information is needed to search these large XML documents. In order to use this method, not only all keywords expressed as nodes in the XML document must be labeled for indexing but also structural information should be well represented. However, the existing labeling methods either have very simple information of XML documents for index or represent the structural information which is difficult to deal with the increase of XML documents' size. As the size of XML documents is getting larger, it causes either the poor performance of keyword search or the exponential increase of space usage. In this paper, we present the Repetitive Prime Labeling Scheme (RPLS) in order to improve the problem of the existing labeling methods for keyword-based search of large XML documents. This method is based on the existing prime number labeling method and allows a parent's prime number to be used at a lower level repeatedly so that the number of prime numbers being generated can be reduced. Then, we show an experimental result of the comparison between our methods and the existing methods.

• Archives of Pharmacal Research
• /
• v.27 no.9
• /
• pp.961-967
• /
• 2004

The development of an antibody labeling method with $^{99m}$Tc is important for cancer imaging. Most bifunctional chelate methods for $^{99m}$Tc labeling of antibody incorporate a $^{99m}$Tc chelator through a linkage to lysine residue. In the present study, a novel site-specific $^{99m}$Tc labeling method at carbohydrate side chain in the Fc region of 2 antibodies (T101 and rabbit anti-human serum albumin antibody (RPAb)) using dihydrazinophthalazine (DHZ) which has 2 hydrazino groups was developed. The antibodies were oxidized with sodium periodate to pro-duce aldehyde on the Fc region. Then, one hydrazine group of DHZ was conjugated with an aldehyde group of antibody through the formation of a hydrazone. The other hydrazine group was used for labeling with $^{99m}$Tc. The number of conjugated DHZ was 1.7 per antibody. $^{99m}$Tc labeling efficiency was 46-85％ for T101 and 67∼87％ for RPAb. Indirect labeling with DHZ conjugated antibodies showed higher stability than direct labeling with reduced antibodies. High immunoreactivities were conserved for both indirectly and directly labeled antibodies. A biodistribution study found high blood activity related to directly labeled T1 01 at early time point as well as low liver activity due to indirectly labeled T101 at later time point. However, these findings do not affect practical use. No significantly different biodistribution was observed in the other organs. The research concluded that DHZ can be used as a site-specific bifunctional chelating agent for labeling antibody with $^{99m}$Tc. Moreover, $^{99m}$Tc labeled antibody via DHZ was found to have excellent chemical and biological properties for nuclear medicine imaging.edicine imaging.

• Korean Journal of Human Ecology
• /
• v.6 no.2
• /
• pp.115-120
• /
• 1997

To investigate the cognition of labeling system and its problems, problems in laundry, and consumer's dissatisfaction and to decrease problems in management of clothing products, total 476 subjects were surveyed in Taejon. The major results were as follows ; 1. The cognition of labeling system was understood by 93.1% of respondents, and 72.9% of them prefer to recognized labeling by figures and letters than by either of them. Most of respondents got the knowledge of labeling system from school. The most frequently experienced mislabeling was the label for management. 2. In cleaning, 60.4% of respondents made their decisions of the laundry method after seeing labeling system. When the label recommanded either of hand washing or dry cleaning, they usually laundered with hand washing after a few times of dry cleaning. The first consideration factor for laundry was fiber composition of textiles. 3. About 70% of respondents understood ironing, laundry, and drying mark on labeling system, and 53.8% understood fiber composition and bleaching. 4. More than 90% of respondents experienced dissatisfaction in handling clothing products. The reason of dissatisfaction was deformation and decoloring after laundry. Most of respondents experienced change of tactile sensation, too.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.686-691
• /
• 2017

Telemarketing has become the center of marketing action of the industry in the information society. Recently, machine learning has emerged in many areas, especially, financial prediction. Financial data consists of lots of unlabeled data in most parts, and therefore, it is difficult for humans to perform their labeling. In this paper, we propose a fusion method of semi-supervised learning for automatic labeling of unlabeled data to predict telemarketing. Specifically, we integrate labeling results of label propagation and co-training with a decision tree. The data with lower reliabilities are removed, and the data are extracted that have consistent label from two labeling methods. After adding them to the training set, a decision tree is learned with all of them. To confirm the usefulness of the proposed method, we conduct the experiments with a real telemarketing dataset in a Portugal bank. Accuracy of the proposed method is 83.39%, which is 1.82% higher than that of the conventional method, and precision of the proposed method is 19.37%, which is 2.67% higher than that of the conventional method. As a result, we have shown that the proposed method has a better performance as assessed by the t-test.