• Title, Summary, Keyword: descriptors

Search Result 475, Processing Time 0.041 seconds

A Survey of Shape Descriptors in Computer Vision (컴퓨터비전에서 사용되는 모양표시자의 현황)

  • 유헌우;장동식
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.9 no.2
    • /
    • pp.131-139
    • /
    • 2003
  • Shape descriptors play an important role in systems for object recognition, retrieval, registration, and analysis. Seven well-known descriptors including MPEG-7 visual descriptors arebriefly reviewed and a new robust pattern recognition descriptor is proposed. Performance comparison among descriptors are presented. Experiments show that the newly proposed descriptor yields better performance results than Fourier, invariant moment, and edge histogram descriptors.

Prediction of Thermal Decomposition Temperature of Polymers Using QSPR Methods

  • Ajloo, Davood;Sharifian, Ali;Behniafar, Hossein
    • Bulletin of the Korean Chemical Society
    • /
    • v.29 no.10
    • /
    • pp.2009-2016
    • /
    • 2008
  • The relationship between thermal decomposition temperature and structure of a new data set of eighty monomers of different polymers were studied by multiple linear regression (MLR). The stepwise method was used in order to variable selection. The best descriptors were selected from over 1400 descriptors including; topological, geometrical, electronic and hybrid descriptors. The effect of number of descriptors on the correlation coefficient (R) and F-ratio were considered. Two models were suggested, one model having four descriptors ($R^2$ = 0.894, $Q^2_{cv}$ = 0.900, F = 172.1) and other model involving 13 descriptors ($R^2$ = 0.956, $Q^2_{cv}$ = 0.956, F = 125.4).

Qualitative Elicitation of Multidimensional Korean Sensory Descriptors and Their Definitions Using Focus Group Interview (Focus Group Interview (FGI)를 통한 다차원적 감각 특성 용어 및 정의의 질적 도출)

  • Hong, Jae-Hee
    • Journal of the Korean Society of Food Culture
    • /
    • v.31 no.1
    • /
    • pp.96-104
    • /
    • 2016
  • Recently, food industries are increasingly interested in launching ethnic foods in the global market, but communicating sensory information to target consumers has been complicated due to the ambiguity and complexity of Korean sensory descriptors. This study was conducted to elicit various multidimensional sensory descriptors and their definitions using focus group interviews (FGI). Two consumer groups, consisting of 10 panelists in their 20s and 10 panelists in their 30-40s respectively, participated in the FGI. A total of 14 commonly used multidimensional sensory descriptors, including gamchilmat (감칠맛), gaeun (개운), goso (고소), gusu (구수), kkal-kkeum (깔끔), neu-kki (느끼), dambaek (담백), birin (비린), siwon (시원), sikeum (시큼), ssapssarae (쌉싸래), eolkeun (얼큰), jjapjoreum (짭조름), and kalkal (칼칼), were elicited. Their definitions showed that these descriptors not only were constructed using several sensory elements but also contained hedonic connotations. Descriptors such as gaeun, siwon, and kkal-kkeum were more closely associated with overall sensory impressions, including aftersensations and post-ingestive effects rather than sensory concepts. As individuals tend to weigh different elements to construct the concept for each multidimensional descriptor, further studies are required to identify elements consisting of these descriptors to develop better test methods and gain a clearer understanding of the sensory profiles of Korean foods.

A Study of the Kinds and Frequency Characteristics of Descriptors in the Articles Related to Scientific Literacy (과학적 소양 관련 논문에서 서술자의 종류와 빈도 특성 연구)

  • Lee, Myeong-Je
    • Journal of Korean Elementary Science Education
    • /
    • v.29 no.4
    • /
    • pp.401-413
    • /
    • 2010
  • This study analyzed the kinds and frequencies of descriptors in 154 articles in ERIC data base on the 4th day of January in 2010. The titles of the articles includes the words, 'scientific literacy'. As each descriptor is constituted of two words and over, in this study the first word in the descriptor was defined as 'restrictive word' and the rest word(s) as 'target word(s)'. The results are as follows. First, the descriptors which show high frequencies of target words are the traditionally important themes of scientific literacy education. Target words which show relatively high frequency are 'education', 'literacy', 'instruction' and 'countries'. Low frequency word is 'curriculum', which has various restrictive words and represents wide differentiation. Second, among the descriptors which show low frequencies of target words, relatively high frequency descriptors are '(and)society', 'change', 'secondary education', 'concepts', and 'biology', which have been given more attention in scientific literacy research than the rest descriptors. Third, the number of the descriptors that shows largely distributed pattern A, which happens over 15 years continuously, is over the half of all analyzed descriptors, which shows that they have been the major objectives in researches about scientific literacy. Most descriptors of pattern A shows normal distribution of frequency or the trends of increasing frequency as the time is nearer. Fourth, The descriptors are divided into four groups according to the time span. Each research trends are as follows. In later 80s, the research which emphasizes the importance of the sociality and technology in all level school science curriculum. In later 90s the research for educational change of inquiry-centered science curriculum which considers technological literacy in social contexts. In earlier 2000s the research that scientists and science teachers develop science curricula mostly related to scientific principles and thinking in chemistry and biology especially. In later 2000s case studies which relates teaching methods and science process activities to students' attitudes, scientific concepts and curricula.

  • PDF

Branch Length Similarity Entropy-Based Descriptors for Shape Representation

  • Kwon, Ohsung;Lee, Sang-Hee
    • Journal of the Korean Physical Society
    • /
    • v.71 no.10
    • /
    • pp.727-732
    • /
    • 2017
  • In previous studies, we showed that the branch length similarity (BLS) entropy profile could be successfully used for the shape recognition such as battle tanks, facial expressions, and butterflies. In the present study, we proposed new descriptors, roundness, symmetry, and surface roughness, for the recognition, which are more accurate and fast in the computation than the previous descriptors. The roundness represents how closely a shape resembles to a circle, the symmetry characterizes how much one shape is similar with another when the shape is moved in flip, and the surface roughness quantifies the degree of vertical deviations of a shape boundary. To evaluate the performance of the descriptors, we used the database of leaf images with 12 species. Each species consisted of 10 - 20 leaf images and the total number of images were 160. The evaluation showed that the new descriptors successfully discriminated the leaf species. We believe that the descriptors can be a useful tool in the field of pattern recognition.

Exploring Level Descriptors of Geometrical Thinking

  • Srichompoo, Somkuan;Inprasitha, Maitree;Sangaroon, Kiat
    • Research in Mathematical Education
    • /
    • v.15 no.1
    • /
    • pp.81-91
    • /
    • 2011
  • The aim of this study was to explore the grade 1-3 students' geometrical thinking level descriptors based on van Hiele level descriptors. The data were collected through collection of geometric curriculum materials such as indicators and learning standards in Basic Education Core Curriculum and mathematics textbook for grades 1-3. The findings were found that 1) Inconsistency between descriptors appeared on mathematics curriculum and Thai mathematics textbooks. 2) Using topics on textbooks as criterion for exploring 5 of 7 descriptors appeared on Thai mathematics textbook indicated geometrical thinking levels based on van Hiele's model merely level 0 (Visualization) across textbooks for grades 1-3.

Prediction Models of P-Glycoprotein Substrates Using Simple 2D and 3D Descriptors by a Recursive Partitioning Approach

  • Joung, Jong-Young;Kim, Hyoung-Joon;Kim, Hwan-Mook;Ahn, Soon-Kil;Nam, Ky-Youb;No, Kyoung-Tai
    • Bulletin of the Korean Chemical Society
    • /
    • v.33 no.4
    • /
    • pp.1123-1127
    • /
    • 2012
  • P-gp (P-glycoprotein) is a member of the ATP binding cassette (ABC) family of transporters. It transports many kinds of anticancer drugs out of the cell. It plays a major role as a cause of multidrug resistance (MDR). MDR function may be a cause of the failure of chemotherapy in cancer and influence pharmacokinetic properties of many drugs. Hence classification of candidate drugs as substrates or nonsubstrate of the P-gp is important in drug development. Therefore to identify whether a compound is a P-gp substrate or not, in silico method is promising. Recursive Partitioning (RP) method was explored for prediction of P-gp substrate. A set of 261 compounds, including 146 substrates and 115 nonsubstrates of P-gp, was used to training and validation. Using molecular descriptors that we can interpret their own meaning, we have established two models for prediction of P-gp substrates. In the first model, we chose only 6 descriptors which have simple physical meaning. In the training set, the overall predictability of our model is 78.95%. In case of test set, overall predictability is 69.23%. Second model with 2D and 3D descriptors shows a little better predictability (overall predictability of training set is 79.29%, test set is 79.37%), the second model with 2D and 3D descriptors shows better discriminating power than first model with only 2D descriptors. This approach will be used to reduce the number of compounds required to be run in the P-gp efflux assay.

Evaluation of Feature Extraction and Matching Algorithms for the use of Mobile Application (모바일 애플리케이션을 위한 특징점 검출 연산자의 비교 분석)

  • Lee, Yong-Hwan;Kim, Heung-Jun
    • Journal of the Semiconductor & Display Technology
    • /
    • v.14 no.4
    • /
    • pp.56-60
    • /
    • 2015
  • Mobile devices like smartphones and tablets are becoming increasingly capable in terms of processing power. Although they are already used in computer vision, no comparable measurement experiments of the popular feature extraction algorithm have been made yet. That is, local feature descriptors are widely used in many computer vision applications, and recently various methods have been proposed. While there are many evaluations have focused on various aspects of local features, matching accuracy, however there are no comparisons considering on speed trade-offs of recent descriptors such as ORB, FAST and BRISK. In this paper, we try to provide a performance evaluation of feature descriptors, and compare their matching precision and speed in KD-Tree setup with efficient computation of Hamming distance. The experimental results show that the recently proposed real valued descriptors such as ORB and FAST outperform state-of-the-art descriptors such SIFT and SURF in both, speed-up efficiency and precision/recall.

Memory-Efficient NBNN Image Classification

  • Lee, YoonSeok;Yoon, Sung-Eui
    • Journal of Computing Science and Engineering
    • /
    • v.11 no.1
    • /
    • pp.1-8
    • /
    • 2017
  • Naive Bayes nearest neighbor (NBNN) is a simple image classifier based on identifying nearest neighbors. NBNN uses original image descriptors (e.g., SIFTs) without vector quantization for preserving the discriminative power of descriptors and has a powerful generalization characteristic. However, it has a distinct disadvantage. Its memory requirement can be prohibitively high while processing a large amount of data. To deal with this problem, we apply a spherical hashing binary code embedding technique, to compactly encode data without significantly losing classification accuracy. We also propose using an inverted index to identify nearest neighbors among binarized image descriptors. To demonstrate the benefits of our method, we apply our method to two existing NBNN techniques with an image dataset. By using 64 bit length, we are able to reduce memory 16 times with higher runtime performance and no significant loss of classification accuracy. This result is achieved by our compact encoding scheme for image descriptors without losing much information from original image descriptors.

Hybrid Facial Representations for Emotion Recognition

  • Yun, Woo-Han;Kim, DoHyung;Park, Chankyu;Kim, Jaehong
    • ETRI Journal
    • /
    • v.35 no.6
    • /
    • pp.1021-1028
    • /
    • 2013
  • Automatic facial expression recognition is a widely studied problem in computer vision and human-robot interaction. There has been a range of studies for representing facial descriptors for facial expression recognition. Some prominent descriptors were presented in the first facial expression recognition and analysis challenge (FERA2011). In that competition, the Local Gabor Binary Pattern Histogram Sequence descriptor showed the most powerful description capability. In this paper, we introduce hybrid facial representations for facial expression recognition, which have more powerful description capability with lower dimensionality. Our descriptors consist of a block-based descriptor and a pixel-based descriptor. The block-based descriptor represents the micro-orientation and micro-geometric structure information. The pixel-based descriptor represents texture information. We validate our descriptors on two public databases, and the results show that our descriptors perform well with a relatively low dimensionality.