• Title/Summary/Keyword: N-transform

Search Result 716, Processing Time 0.021 seconds

Multi-modal Image Processing for Improving Recognition Accuracy of Text Data in Images (이미지 내의 텍스트 데이터 인식 정확도 향상을 위한 멀티 모달 이미지 처리 프로세스)

  • Park, Jungeun;Joo, Gyeongdon;Kim, Chulyun
    • Database Research
    • /
    • v.34 no.3
    • /
    • pp.148-158
    • /
    • 2018
  • The optical character recognition (OCR) is a technique to extract and recognize texts from images. It is an important preprocessing step in data analysis since most actual text information is embedded in images. Many OCR engines have high recognition accuracy for images where texts are clearly separable from background, such as white background and black lettering. However, they have low recognition accuracy for images where texts are not easily separable from complex background. To improve this low accuracy problem with complex images, it is necessary to transform the input image to make texts more noticeable. In this paper, we propose a method to segment an input image into text lines to enable OCR engines to recognize each line more efficiently, and to determine the final output by comparing the recognition rates of CLAHE module and Two-step module which distinguish texts from background regions based on image processing techniques. Through thorough experiments comparing with well-known OCR engines, Tesseract and Abbyy, we show that our proposed method have the best recognition accuracy with complex background images.

Receptor binding motif surrounding sites in the Spike 1 protein of infectious bronchitis virus have high susceptibility to mutation related to selective pressure

  • Seung-Min Hong;Seung-Ji Kim;Se-Hee An;Jiye Kim;Eun-Jin Ha;Howon Kim;Hyuk-Joon Kwon;Kang-Seuk Choi
    • Journal of Veterinary Science
    • /
    • v.24 no.4
    • /
    • pp.51.1-51.17
    • /
    • 2023
  • Background: To date, various genotypes of infectious bronchitis virus (IBV) have co-circulated and in Korea, GI-15 and GI-19 lineages were prevailing. The spike protein, particularly S1 subunit, is responsible for receptor binding, contains hypervariable regions and is also responsible for the emerging of novel variants. Objective: This study aims to investigate the putative major amino acid substitutions for the variants in GI-19. Methods: The S1 sequence data of IBV isolated from 1986 to 2021 in Korea (n = 188) were analyzed. Sequence alignments were carried out using Multiple alignment using Fast Fourier Transform of Geneious prime. The phylogenetic tree was generated using MEGA-11 (ver. 11.0.10) and Bayesian analysis was performed by BEAST v1.10.4. Selective pressure was analyzed via online server Datamonkey. Highlights and visualization of putative critical amino acid were conducted by using PyMol software (version 2.3). Results: Most (93.5%) belonged to the GI-19 lineage in Korea, and the GI-19 lineage was further divided into seven subgroups: KM91-like (Clade A and B), K40/09-like, QX-like (I-IV). Positive selection was identified at nine and six residues in S1 for KM91-like and QX-like IBVs, respectively. In addition, several positive selection sites of S1-NTD were indicated to have mutations at common locations even when new clades were generated. They were all located on the lateral surface of the quaternary structure of the S1 subunits in close proximity to the receptor-binding motif (RBM), putative RBM motif and neutralizing antigenic sites in S1. Conclusions: Our results suggest RBM surrounding sites in the S1 subunit of IBV are highly susceptible to mutation by selective pressure during evolution.

Mapping and estimating forest carbon absorption using time-series MODIS imagery in South Korea (시계열 MODIS 영상자료를 이용한 산림의 연간 탄소 흡수량 지도 작성)

  • Cha, Su-Young;Pi, Ung-Hwan;Park, Chong-Hwa
    • Korean Journal of Remote Sensing
    • /
    • v.29 no.5
    • /
    • pp.517-525
    • /
    • 2013
  • Time-series data of Normal Difference Vegetation Index (NDVI) obtained by the Moderate-resolution Imaging Spectroradiometer(MODIS) satellite imagery gives a waveform that reveals the characteristics of the phenology. The waveform can be decomposed into harmonics of various periods by the Fourier transformation. The resulting $n^{th}$ harmonics represent the amount of NDVI change in a period of a year divided by n. The values of each harmonics or their relative relation have been used to classify the vegetation species and to build a vegetation map. Here, we propose a method to estimate the annual amount of carbon absorbed on the forest from the $1^{st}$ harmonic NDVI value. The $1^{st}$ harmonic value represents the amount of growth of the leaves. By the allometric equation of trees, the growth of leaves can be considered to be proportional to the total amount of carbon absorption. We compared the $1^{st}$ harmonic NDVI values of the 6220 sample points with the reference data of the carbon absorption obtained by the field survey in the forest of South Korea. The $1^{st}$ harmonic values were roughly proportional to the amount of carbon absorption irrespective of the species and ages of the vegetation. The resulting proportionality constant between the carbon absorption and the $1^{st}$ harmonic value was 236 tCO2/5.29ha/year. The total amount of carbon dioxide absorption in the forest of South Korea over the last ten years has been estimated to be about 56 million ton, and this coincides with the previous reports obtained by other methods. Considering that the amount of the carbon absorption becomes a kind of currency like carbon credit, our method is very useful due to its generality.

Speech Recognition Using Linear Discriminant Analysis and Common Vector Extraction (선형 판별분석과 공통벡터 추출방법을 이용한 음성인식)

  • 남명우;노승용
    • The Journal of the Acoustical Society of Korea
    • /
    • v.20 no.4
    • /
    • pp.35-41
    • /
    • 2001
  • This paper describes Linear Discriminant Analysis and common vector extraction for speech recognition. Voice signal contains psychological and physiological properties of the speaker as well as dialect differences, acoustical environment effects, and phase differences. For these reasons, the same word spelled out by different speakers can be very different heard. This property of speech signal make it very difficult to extract common properties in the same speech class (word or phoneme). Linear algebra method like BT (Karhunen-Loeve Transformation) is generally used for common properties extraction In the speech signals, but common vector extraction which is suggested by M. Bilginer et at. is used in this paper. The method of M. Bilginer et al. extracts the optimized common vector from the speech signals used for training. And it has 100% recognition accuracy in the trained data which is used for common vector extraction. In spite of these characteristics, the method has some drawback-we cannot use numbers of speech signal for training and the discriminant information among common vectors is not defined. This paper suggests advanced method which can reduce error rate by maximizing the discriminant information among common vectors. And novel method to normalize the size of common vector also added. The result shows improved performance of algorithm and better recognition accuracy of 2% than conventional method.

  • PDF

Effect of Yeongyupaedog-san on Cytokine Levels of Mouse Th1/Th2 Cells and Anti-allergic Activity in Ovalbumin-sensitized Allergic Inflammation Model (연교적패독산(連翹敗毒散) 물 추출물(抽出物)의 마우스 Th1/Th2 사이토카인 조절(調節)에 의한 항알레르기 효과)

  • Khwag, Nyo-Gyu;Kang, Hee;Myung, Eu-Gene;Park, Sung-Min;Shim, Bum-Sang;Kim, Sung-Hoon;Choi, Seung-Hoon;Ahn, Kyoo-Seok
    • Journal of Physiology & Pathology in Korean Medicine
    • /
    • v.20 no.4
    • /
    • pp.844-852
    • /
    • 2006
  • This study was to evaluate the effect of Yeongyupaedog-san (YGPDS) on mouse Thl and Th2 cells' differentiation and ovalbumin (OVA)-induced allergic inflammation. The proliferation of mouse CD4 T cells and the secretion of Th1/Th2 cytokines under the influence of YGPDS extract were measured as well as the amount of ${\beta}-hexosaminidase$ in RBL-2H3 cells and the levels of $TNF-{\alpha}$ and 1L-6 secretion in Raw264.7 cells. BALB/c mice were orally administered with YGPDS extract and simultaneously inoculated with OVA to induce allergic reaction and measure the level of total IgE, OVA-specific IgE and the production of IFN- g, IL-4, IL-5 by the spleen cells. When mouse CD4 T cell were stimulated with anti-CD3 and anti-CD28 for 48 hours in various concentrations of YGPDS extract, it increased proliferation of CD4 cells by 11% in $100\;{\mu}g/^{ml}$ concentration but it showed an inhibition by 37% at $200\;{\mu}g/^{ml}$ CD4 T cells under Th1/Th2 polarizing conditions for 3 days with YGPDS resulted in mild decrease of IFN- g in Thl cells and significant decrease of IL-4 in Th2 cells at $500\;{\mu}g/^{ml}\;and\;100\;{\mu}g/^{ml}$ by 18% and 21%, respectively. YGPDS extract had a dose-dependent inhibitory effect on antigen-induced release of ${\beta}-hexosaminidase$ in RBL-2H3 cells. Treatment of YGPDS extract on LPS stimulated Raw 264.7 cells showed dose-dependent decrease in TNF-n production. Oral administration of YGPDS extract on OVA-induced allergic mice showed an inhibitory effect on the levels of total serum IgE and OVA-specific IgE by 25% and 34% , respectively. Culture of spleen cells with OVA resulted in significant increase of IFN- g by 44% and significant decrease of IL-4 and IL-5 by 56%, and 24%, respectively. The results show that YGPDS does not strongly induce mouse T cells to transform into Thl or Th2 but it has an anti-allergic effect in vitro, and that it also corrects the unbalance between the reactions of Th cells in allergic diseases.

The Effects of the Perceived Motivation Type toward Corporate Social Responsibility Activities on Customer Loyalty (기업사회책임활동적인지인지동기류형대고객충성도적영향(企业社会责任活动的认知认知动机类型对顾客忠诚度的影响))

  • Kim, Kyung-Jin;Park, Jong-Chul
    • Journal of Global Scholars of Marketing Science
    • /
    • v.19 no.3
    • /
    • pp.5-16
    • /
    • 2009
  • Corporate social responsibility (CSR) activities have been shown to be potential factors that can improve corporate image and increase the ability of corporations to compete. However, most previous studies related to CSR activities investigated how these activities influence product and corporate evaluation, as well as corporate image. In addition, some researchers treated consumers' perceptions of corporate motives as moderator variables in evaluating the relationship between corporate social responsibilities and consumer response. However, motive-based theories have some weaknesses. Corporate social responsibility activities cause two motives(egoistic vs. altruistic) for consumers, but recently, Vlachos et al. (2008) argued that these motives should be segmented. Thus, it is possible to transform the original theory into a modified theory model (persuasion knowledge model, PKM). Vlachos et al. (2008) segmented corporate social responsibility motives into four types and compared the effects of these motives on customer loyalty. Prior studies have proved that CSR activities with positive motives have positive influences on customer loyalty. However, the psychological reasons underlying this finding have not been determined empirically. Thus, the objectives of this research are twofold. First, we attempt to determine why most customers favor companies that they feel have positive motives for their corporate social responsibility activities. Second, we attempt to measure the effects of consumers' reciprocity when society benefits from corporate social responsibility activities. The following research hypotheses are constructed. H1: Values-driven motives for corporate social responsibility activities have a positive influence on the perceived reciprocity. H2: Stakeholder-driven motives for corporate social responsibility activities have a negative influence on the perceived reciprocity. H3: Egoistic-driven motives for corporate social responsibility activities have a negative influence on perceived reciprocity. H4: Strategic-driven motives for corporate social responsibility activities have a negative influence on perceived reciprocity. H5: Perceived reciprocity for corporate social responsibility activities has a positive influence on consumer loyalty. A single company is selected as a research subject to understand how the motives behind corporate social responsibility influence consumers' perceived reciprocity and customer loyalty. A total sample of 200 respondents was selected for a pilot test. In addition, to ensure a consistent response, we ensured that the respondents were older than 20 years of age. The surveys of 172 respondents (males-82, females-90) were analyzed after 28 invalid questionnaires were excluded. Based on our cutoff criteria, the model fit the data reasonably well. Values-driven motives for corporate social responsibility activities had a positive effect on perceived reciprocity (t = 6.75, p < .001), supporting H1. Morales (2005) also found that consumers appreciate a company's social responsibility efforts and the benefits provided by these efforts to society. Stakeholder-driven motives for corporate social responsibility activities did not affect perceived reciprocity (t = -.049, p > .05). Thus, H2 was rejected. Egoistic-driven motives (t = .3.11, p < .05) and strategic-driven (t = -4.65, p < .05) motives had a negative influence on perceived reciprocity, supporting H3 and H4, respectively. Furthermore, perceived reciprocity had a positive influence on consumer loyalty (t = 4.24, p < .05), supporting H5. Thus, compared with the general public, undergraduate students appear to be more influenced by egoistic-driven motives. We draw the following conclusions from our research findings. First, value-driven attributions have a positive influence on perceived reciprocity. However, stakeholder-driven attributions have no significant effects on perceived reciprocity. Moreover, both egoistic-driven attributions and strategic-driven attributions have a negative influence on perceived reciprocity. Second, when corporate social responsibility activities align with consumers' reciprocity, the efforts directed towards social responsibility activities have a positive influence on customer loyalty. In this study, we examine whether the type of motivation affects consumer responses to CSR, and in particular, we evaluate how CSR motives can influence a key internal factor (perceived reciprocity) and behavioral consumer outcome (customer loyalty). We demonstrate that perceived reciprocity plays a mediating role in the relationship between CSR motivation and customer loyalty. Our study extends the research on consumer CSR-inferred motivations, positing them as a direct indicator of consumer responses. Furthermore, we convincingly identify perceived reciprocity as a sub-process mediating the effect of CSR attributions on customer loyalty. Future research investigating the ultimate behavior and financial impact of CSR should consider that the impacts of CSR also stem from perceived reciprocity. The results of this study also have important managerial implications. First, the central role that reciprocity plays indicates that managers should routinely measure how much their socially responsible actions create perceived reciprocity. Second, understanding how consumers' perceptions of CSR corporate motives relate to perceived reciprocity and customer loyalty can help managers to monitor and enhance these consumer outcomes through marketing initiatives and management of CSR-induced attribution processes. The results of this study will help corporations to understand the relative importance of the four different motivations types in influencing perceived reciprocity.

  • PDF