• Title/Summary/Keyword: Image representation

Search Result 75, Processing Time 0.354 seconds

Structuring Element Representation of an Image and Its Applications

  • Oh, Jin-Sung
    • International Journal of Control, Automation, and Systems
    • /
    • v.2 no.4
    • /
    • pp.509-515
    • /
    • 2004
  • In this paper we present the linear combination of a fuzzy opening and closing filter with locally adaptive structuring elements that can preserve the geometrical features of an image. Based on the adaptation algorithm of linear combination of the fuzzy opening and closing filter, the optimal structuring element for image representation is obtained. The optimal structuring element is an indicator of the shape and direction of an object's image, which is useful in filtering, multi resolution, segmentation, and recognition of an image.

Dual graph-regularized Constrained Nonnegative Matrix Factorization for Image Clustering

  • Sun, Jing;Cai, Xibiao;Sun, Fuming;Hong, Richang
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.11 no.5
    • /
    • pp.2607-2627
    • /
    • 2017
  • Nonnegative matrix factorization (NMF) has received considerable attention due to its effectiveness of reducing high dimensional data and importance of producing a parts-based image representation. Most of existing NMF variants attempt to address the assertion that the observed data distribute on a nonlinear low-dimensional manifold. However, recent research results showed that not only the observed data but also the features lie on the low-dimensional manifolds. In addition, a few hard priori label information is available and thus helps to uncover the intrinsic geometrical and discriminative structures of the data space. Motivated by the two aspects above mentioned, we propose a novel algorithm to enhance the effectiveness of image representation, called Dual graph-regularized Constrained Nonnegative Matrix Factorization (DCNMF). The underlying philosophy of the proposed method is that it not only considers the geometric structures of the data manifold and the feature manifold simultaneously, but also mines valuable information from a few known labeled examples. These schemes will improve the performance of image representation and thus enhance the effectiveness of image classification. Extensive experiments on common benchmarks demonstrated that DCNMF has its superiority in image classification compared with state-of-the-art methods.

Constrained Sparse Concept Coding algorithm with application to image representation

  • Shu, Zhenqiu;Zhao, Chunxia;Huang, Pu
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.8 no.9
    • /
    • pp.3211-3230
    • /
    • 2014
  • Recently, sparse coding has achieved remarkable success in image representation tasks. In practice, the performance of clustering can be significantly improved if limited label information is incorporated into sparse coding. To this end, in this paper, a novel semi-supervised algorithm, called constrained sparse concept coding (CSCC), is proposed for image representation. CSCC considers limited label information into graph embedding as additional hard constraints, and hence obtains embedding results that are consistent with label information and manifold structure information of the original data. Therefore, CSCC can provide a sparse representation which explicitly utilizes the prior knowledge of the data to improve the discriminative power in clustering. Besides, a kernelized version of our proposed CSCC, namely kernel constrained sparse concept coding (KCSCC), is developed to deal with nonlinear data, which leads to more effective clustering performance. The experimental evaluations on the MNIST, PIE and Yale image sets show the effectiveness of our proposed algorithms.

Skewness based Adaptive Retinex Algorithm for Wide Dynamic Range (영상의 동적영역 확대를 위한 비대칭도 기반 적응적 Retinex 알고리즘)

  • Oh, Jonggeun;Kim, Beomsu;Hong, Min-Cheol
    • Journal of IKEEE
    • /
    • v.17 no.4
    • /
    • pp.478-483
    • /
    • 2013
  • This paper presents an adaptive Retinex algorithm for improving dynamic range of image representation. The proposed Retinex algorithm detects degraded brightness by using skewness and the degraded components are compensated with local statistics. In particular, we propose a new compensation function for dynamic range so that effectinve image representation can be achieved. Experimental results show that the proposed algorithm has the capability to improve the dynamic range with reduction of color degradation.

Super Resolution by Learning Sparse-Neighbor Image Representation (Sparse-Neighbor 영상 표현 학습에 의한 초해상도)

  • Eum, Kyoung-Bae;Choi, Young-Hee;Lee, Jong-Chan
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.18 no.12
    • /
    • pp.2946-2952
    • /
    • 2014
  • Among the Example based Super Resolution(SR) techniques, Neighbor embedding(NE) has been inspired by manifold learning method, particularly locally linear embedding. However, the poor generalization of NE decreases the performance of such algorithm. The sizes of local training sets are always too small to improve the performance of NE. We propose the Learning Sparse-Neighbor Image Representation baesd on SVR having an excellent generalization ability to solve this problem. Given a low resolution image, we first use bicubic interpolation to synthesize its high resolution version. We extract the patches from this synthesized image and determine whether each patch corresponds to regions with high or low spatial frequencies. After the weight of each patch is obtained by our method, we used to learn separate SVR models. Finally, we update the pixel values using the previously learned SVRs. Through experimental results, we quantitatively and qualitatively confirm the improved results of the proposed algorithm when comparing with conventional interpolation methods and NE.

Recognition of Occluded Face (가려진 얼굴의 인식)

  • Kang, Hyunchul
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.23 no.6
    • /
    • pp.682-689
    • /
    • 2019
  • In part-based image representation, the partial shapes of an object are represented as basis vectors, and an image is decomposed as a linear combination of basis vectors where the coefficients of those basis vectors represent the partial (or local) feature of an object. In this paper, a face recognition for occluded faces is proposed in which face images are represented using non-negative matrix factorization(NMF), one of part-based representation techniques, and recognized using an artificial neural network technique. Standard NMF, projected gradient NMF and orthogonal NMF were used in part-based representation of face images, and their performances were compared. Learning vector quantizer were used in the recognizer where Euclidean distance was used as the distance measure. Experimental results show that proposed recognition is more robust than the conventional face recognition for the occluded faces.

Vehicle Recognition using Non-negative Tensor Factorization (비음수 텐서 분해를 이용한 차량 인식)

  • Ban, Jae Min;Kang, Hyunchul
    • Journal of the Institute of Electronics and Information Engineers
    • /
    • v.52 no.5
    • /
    • pp.136-146
    • /
    • 2015
  • The active control of a vehicle based on vehicle recognition is one of key technologies for the intelligent vehicle, and the part-based image representation is necessary to recognize vehicles with only partial shapes of vehicles especially in urban scene where occlusions frequently occur. In this paper, we implemented a part-based image representation scheme using non-negative tensor factorization(NTF) and realized a robust vehicle recognition system using the NTF feature. The result shows that the proposed method gives more intuitive part-based representation and more robust recognition in urban scene.

Layered Depth Image Representation And H.264 Encoding of Multi-view video For Free viewpoint TV (자유시점 TV를 위한 다시점 비디오의 계층적 깊이 영상 표현과 H.264 부호화)

  • Shin, Jong Hong
    • Journal of Korea Society of Digital Industry and Information Management
    • /
    • v.7 no.2
    • /
    • pp.91-100
    • /
    • 2011
  • Free viewpoint TV can provide multi-angle view point images for viewer needs. In the real world, But all angle view point images can not be captured by camera. Only a few any angle view point images are captured by each camera. Group of the captured images is called multi-view image. Therefore free viewpoint TV wants to production of virtual sub angle view point images form captured any angle view point images. Interpolation methods are known of this problem general solution. To product interpolated view point image of correct angle need to depth image of multi-view image. Unfortunately, multi-view video including depth image is necessary to develop a new compression encoding technique for storage and transmission because of a huge amount of data. Layered depth image is an efficient representation method of multi-view video data. This method makes a data structure that is synthesis of multi-view color and depth image. This paper proposed enhanced compression method using layered depth image representation and H.264/AVC video coding technology. In experimental results, confirmed high compression performance and good quality reconstructed image.

H.264 Encoding Technique of Multi-view Video expressed by Layered Depth Image (계층적 깊이 영상으로 표현된 다시점 비디오에 대한 H.264 부호화 기술)

  • Shin, Jong-Hong;Jee, Inn-Ho
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.14 no.2
    • /
    • pp.43-51
    • /
    • 2014
  • Multi-view video including depth image is necessary to develop a new compression encoding technique for storage and transmission, because of a huge amount of data. Layered depth image is an efficient representation method of multi-view video data. This method makes a data structure that is synthesis of multi-view color and depth image. This efficient method to compress new contents is suggested to use layered depth image representation and to apply for video compression encoding by using 3D warping. This paper proposed enhanced compression method using layered depth image representation and H.264/AVC video coding technology. In experimental results, we confirmed high compression performance and good quality of reconstructed image.