• 제목/요약/키워드: Feature representation

검색결과 410건 처리시간 0.023초

얼굴과 얼굴 특징점 자동 검출을 위한 탄력적 특징 정합 (A flexible Feature Matching for Automatic Face and Facial Feature Points Detection)

  • 박호식;배철수
    • 한국정보통신학회논문지
    • /
    • 제7권4호
    • /
    • pp.705-711
    • /
    • 2003
  • 본 논문에서는 자동적으로 얼굴과 얼굴 특징점(FFPs:Facial Feature Points)을 검출하는 시스템을 제안하였다. 얼굴은 Gabor 특징에 의하여 지정된 특징점의 교점 그래프와 공간적 연결을 나타내는 에지 그래프로 표현하였으며 제안된 탄력적 특징 정합은 모델과 입력 영상에 상응하는 특징을 취하였다. 또한, 정합 모델은 국부적으로 경쟁적이고 전체적으로 협력적인 구조를 이룸으로서 영상공간에서 불규칙 확산 처리와 같은 역할을 하도록 하였으며, 복잡한 배경이나 자세의 변화, 그리고 왜곡된 얼굴 영상에서도 원활하게 동작하는 얼굴 식별 시스템을 구성함으로서 제안된 방법의 효율성을 증명하였다.

Feature Voting for Object Localization via Density Ratio Estimation

  • Wang, Liantao;Deng, Dong;Chen, Chunlei
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제13권12호
    • /
    • pp.6009-6027
    • /
    • 2019
  • Support vector machine (SVM) classifiers have been widely used for object detection. These methods usually locate the object by finding the region with maximal score in an image. With bag-of-features representation, the SVM score of an image region can be written as the sum of its inside feature-weights. As a result, the searching process can be executed efficiently by using strategies such as branch-and-bound. However, the feature-weight derived by optimizing region classification cannot really reveal the category knowledge of a feature-point, which could cause bad localization. In this paper, we represent a region in an image by a collection of local feature-points and determine the object by the region with the maximum posterior probability of belonging to the object class. Based on the Bayes' theorem and Naive-Bayes assumptions, the posterior probability is reformulated as the sum of feature-scores. The feature-score is manifested in the form of the logarithm of a probability ratio. Instead of estimating the numerator and denominator probabilities separately, we readily employ the density ratio estimation techniques directly, and overcome the above limitation. Experiments on a car dataset and PASCAL VOC 2007 dataset validated the effectiveness of our method compared to the baselines. In addition, the performance can be further improved by taking advantage of the recently developed deep convolutional neural network features.

A Novel Perceptual Hashing for Color Images Using a Full Quaternion Representation

  • Xing, Xiaomei;Zhu, Yuesheng;Mo, Zhiwei;Sun, Ziqiang;Liu, Zhen
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제9권12호
    • /
    • pp.5058-5072
    • /
    • 2015
  • Quaternions have been commonly employed in color image processing, but when the existing pure quaternion representation for color images is used in perceptual hashing, it would degrade the robustness performance since it is sensitive to image manipulations. To improve the robustness in color image perceptual hashing, in this paper a full quaternion representation for color images is proposed by introducing the local image luminance variances. Based on this new representation, a novel Full Quaternion Discrete Cosine Transform (FQDCT)-based hashing is proposed, in which the Quaternion Discrete Cosine Transform (QDCT) is applied to the pseudo-randomly selected regions of the novel full quaternion image to construct two feature matrices. A new hash value in binary is generated from these two matrices. Our experimental results have validated the robustness improvement brought by the proposed full quaternion representation and demonstrated that better performance can be achieved in the proposed FQDCT-based hashing than that in other notable quaternion-based hashing schemes in terms of robustness and discriminability.

적외선 영상에서의 불변 특징 정보를 이용한 목표물 인식 (Object Recognition by Invariant Feature Extraction in FLIR)

  • 권재환;이광연;김성대
    • 대한전자공학회:학술대회논문집
    • /
    • 대한전자공학회 2000년도 추계종합학술대회 논문집(4)
    • /
    • pp.65-68
    • /
    • 2000
  • This paper describes an approach for extracting invariant features using a view-based representation and recognizing an object with a high speed search method in FLIR. In this paper, we use a reformulated eigenspace technique based on robust estimation for extracting features which are robust for outlier such as noise and clutter. After extracting feature, we recognize an object using a partial distance search method for calculating Euclidean distance. The experimental results show that the proposed method achieves the improvement of recognition rate compared with standard PCA.

  • PDF

얼굴 특징점 자동 검출을 위한 탄력적 특징 정합 (A Flexible Feature Matching for Automatic Facial Feature Points Detection)

  • 황선기;배철수
    • 한국정보전자통신기술학회논문지
    • /
    • 제3권2호
    • /
    • pp.12-17
    • /
    • 2010
  • 본 논문에서는 자동적으로 얼굴 특징점을 검출하는 시스템을 제안하였다. 얼굴은 Gabor 특징에 의하여 지정된 특징점의 교점 그래프와 공간적 연결을 나타내는 에지 그래프로 표현하였으며, 제안된 탄력적 특징 정합은 모델과 입력 영상에 상응하는 특징을 취하였다. 정합 모델은 국부적으로 경쟁적이고 전체적으로 협력적인 구조를 이룸으로서 영상공간에서 불규칙 확산 처리와 같은 역할을 하도록 하였다. 복잡한 배경이나 자세의 변화, 그리고 왜곡된 얼굴 영상에서도 원활하게 동작하는 얼굴 식별 시스템을 구성함으로서 제안된 방법의 효율성을 증명하였다.

  • PDF

얼굴과 얼굴 특징점 자동 검출을 위한 탄력적 특징 정합 (A Flexible Feature Matching for Automatic face and Facial feature Points Detection)

  • 박호식;손형경;정연길;배철수
    • 한국정보통신학회:학술대회논문집
    • /
    • 한국해양정보통신학회 2002년도 춘계종합학술대회
    • /
    • pp.608-612
    • /
    • 2002
  • 본 논문에서는 자동적으로 얼굴과 얼굴 특징점을 검출하는 시스템을 제안하였다. 얼굴은 Gabor 특징에 의하여 지정된 특징점의 교점 그래프와 공간적 연결을 나타내는 에지 그래프로 표현하였으며, 제안된 탄력적 특징 정합은 모델과 입력 영상에 상응하는 특징을 취하였다. 정합 모델은 국부적으로 경쟁적이고 전체적으로 협력적인 구조를 이룸으로서 영상공간에서 불규칙 확산 처리와 같은 역할을 하도록 하였다. 복잡한 배경이나 자세의 변화, 그리고 왜곡된 얼굴 영상에서도 원활하게 동작하는 얼굴 식별 시스템을 구성함으로서 제안된 방법의 효율성을 증명하였다.

  • PDF

A Step towards the Improvement in the Performance of Text Classification

  • Hussain, Shahid;Mufti, Muhammad Rafiq;Sohail, Muhammad Khalid;Afzal, Humaira;Ahmad, Ghufran;Khan, Arif Ali
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제13권4호
    • /
    • pp.2162-2179
    • /
    • 2019
  • The performance of text classification is highly related to the feature selection methods. Usually, two tasks are performed when a feature selection method is applied to construct a feature set; 1) assign score to each feature and 2) select the top-N features. The selection of top-N features in the existing filter-based feature selection methods is biased by their discriminative power and the empirical process which is followed to determine the value of N. In order to improve the text classification performance by presenting a more illustrative feature set, we present an approach via a potent representation learning technique, namely DBN (Deep Belief Network). This algorithm learns via the semantic illustration of documents and uses feature vectors for their formulation. The nodes, iteration, and a number of hidden layers are the main parameters of DBN, which can tune to improve the classifier's performance. The results of experiments indicate the effectiveness of the proposed method to increase the classification performance and aid developers to make effective decisions in certain domains.

RBM을 이용한 언어의 분산 표상화 (RBM-based distributed representation of language)

  • 유희조;남기춘;남호성
    • 인지과학
    • /
    • 제28권2호
    • /
    • pp.111-131
    • /
    • 2017
  • 연결주의 모델은 계산주의적 관점에서 언어 처리를 연구하는 한 가지 접근법이다. 그리고 연결주의 모델 연구를 진행하는데 있어서 표상(representation)을 구축하는 것은, 모델의 학습 수준 및 수행 능력을 결정한다는 점에서 모델의 구조를 만드는 것만큼이나 중요한 일이다. 연결주의 모델은 크게 지역 표상(localist representation)과 분산 표상(distributed representation)이라는 두 가지 서로 다른 방식으로 표상을 구축해 왔다. 하지만 종래 연구들에서 사용된 지역 표상은 드문 목표 활성화 값을 갖고 있는 출력층의 유닛이 불활성화 하는 제한점을, 그리고 과거의 분산 표상은 표상된 정보의 불투명성에 의한 결과 확인의 어려움이라는 제한점을 갖고 있었으며 이는 연결주의 모델 연구 전반의 제한점이 되어 왔다. 본 연구는 이와 같은 과거의 표상 구축의 제한점에 대하여, 제한된 볼츠만 머신(restricted Boltzmann machine)이 갖고 있는 특징인 정보의 추상화를 활용하여 지역 표상을 가지고 분산 표상을 유도하는 새로운 방안을 제시하였다. 결과적으로 본 연구가 제안한 방법은 정보의 압축과 분산 표상을 지역 표상으로 역변환하는 방안을 활용하여 종래의 표상 구축 방법이 갖고 있는 문제를 효과적으로 해결함을 보였다.

Shock Graph for Representation and Modeling of Posture

  • Tahir, Nooritawati Md.;Hussain, Aini;Abdul Samad, Salina;Husain, Hafizah
    • ETRI Journal
    • /
    • 제29권4호
    • /
    • pp.507-515
    • /
    • 2007
  • Skeleton transform of which the medial axis transform is the most popular has been proposed as a useful shape abstraction tool for the representation and modeling of human posture. This paper explains this proposition with a description of the areas in which skeletons could serve to enable the representation of shapes. We present algorithms for two-dimensional posture modeling using the developed simplified shock graph (SSG). The efficacy of SSG extracted feature vectors as shape descriptors are also evaluated using three different classifiers, namely, decision tree, multilayer perceptron, and support vector machine. The paper concludes with a discussion of the issues involved in using shock graphs to model and classify human postures.

  • PDF

Precision shape modeling by z-map model

  • Park, Jung-Whan;Chung, Yun-Chan;Choi, Byoung-Kyn
    • International Journal of Precision Engineering and Manufacturing
    • /
    • 제3권1호
    • /
    • pp.49-56
    • /
    • 2002
  • The Z-map is a special farm of discrete non-parametric representation in which the height values at grid points on the xy-plane are stored as a 2D array z[ij]. While the z-map is the simplest farm of representing sculptured surfaces and is the most versatile scheme for modeling non-parametric objects, its practical application in industry (eg, tool-path generation) has aroused much controversy over its weaknesses, namely its inaccuracy, singularity (eg, vertical wall), and some excessive storage needs. Much research or the application of the z-map can be found in various articles, however, research on the systematic analysis of sculptured surface shape representation via the z-map model is rather rare. Presented in this paper are the following: shape modeling power of the simple z-map model, exact (within tolerance) z-map representation of sculptured surfaces which have some feature-shapes such as vertical-walls and real sharp-edges by adopting some complementary z-map models, and some application examples.