System Maintenance:
There may be intermittent impact on performance while updates are in progress. We apologize for the inconvenience.
By Topic

Computer Vision, IET

Issue 5 • Date September 2011

Filter Results

Displaying Results 1 - 7 of 7
  • Rotation invariant complex Zernike moments features and their applications to human face and character recognition

    Publication Year: 2011 , Page(s): 255 - 265
    Cited by:  Papers (2)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (339 KB)  

    The magnitude of Zernike moments (ZMs) has been used as rotation invariant features for classification problems in the past. Their individual real and imaginary components and phase coefficients are ignored, because they change with rotation. This study presents a new method to modify the individual real and imaginary components of ZMs which change due to image rotation. The modified real and imaginary components are then used as invariant image descriptors. The performance of the proposed method and magnitude-based ZM method is analysed on grayscale face images and binary character images in application to the fields of face recognition and character recognition, respectively. Experimental results show that the proposed method is robust to image rotation. For classification, the authors use L1-norm as the similarity measure. It is shown that the proposed method gives better recognition rate over the magnitude-based ZM method, comparatively at low orders of moment and thus it is recommended for pose invariant face recognition and also for rotation invariant character recognition. This has been proved by comparing the results of the proposed method with existing prominent methods of feature extraction in face and character recognition. On ORL database, the proposed method achieves the highest recognition rate of 96.5%, whereas a recognition rate of 99.7% is obtained on binary Roman character images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Omni-directional vision system with fibre grating device for obstacle detection

    Publication Year: 2011 , Page(s): 267 - 281
    Cited by:  Papers (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1332 KB)  

    In this study, a new omni-directional vision system is presented for localisation and wide field of view (FOV) mapping of the environment. The vision system includes two charge coupled device (CCD) cameras fitted in front of two rectilinear mirrors to sense the environment in a stereo manner. In order to obtain the points representing the obstacles in the environment, a dot-matrix laser pattern created by a fibre grating device (FGD) was used. With the help of the developed mathematical and error estimation models, the distances between the points on the objects and the vision system were determined; and by using synthetic data, the effects of noise on the error rates were analysed. Although the error rates of X-, Y- and Z-axis were increased according to the distance between the obstacle and the vision system for the same horizontal/vertical plane, the errors for X (range) and Z (height) were decreased with the increasing distance between the vision system and horizontal/vertical planes for real world. The main reasons of errors were the size and location of the laser points, reflection errors on the mirrors, sensitivity of the refractive lenses, alignment of the mirror-camera pairs and limitation of the image resolution. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-object visual tracking based on reversible jump Markov chain Monte Carlo

    Publication Year: 2011 , Page(s): 282 - 290
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (629 KB)  

    Markov chain Monte Carlo-based multi-object visual tracking has been investigated here. To improve the confidence of sampling and perform the iteration effectively, a new approach to multi-object visual tracking is proposed based on reversible jump Markov chain Monte Carlo sampling. The tracking problem is formulated as computing the maximum a posteriori estimation given image observations. Four types of reversible and jump moves are designed for Markov chains dynamics, and prior proposal distributions of objects are developed with the aid of association match matrix. The joint likelihood distribution measurement is presented at two levels of clustered blocks subsets and pixels. Experimental results and quantitative evaluation demonstrate that the proposed approach is effective for challenge situations. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Contour-based iterative pose estimation of 3D rigid object

    Publication Year: 2011 , Page(s): 291 - 300
    Cited by:  Papers (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (502 KB)  

    Estimating pose parameters of a 3D rigid object based on a 2D monocular image is a fundamental problem in computer vision. State-of-the-art methods usually assume that certain feature correspondences are available a priori between the input image and object's 3D model. This presumption makes the problem more algebraically tractable. However, when there is no feature correspondence available a priori, how to estimate the pose of a truly 3D object using just one 2D monocular image is still not well solved. In this article, a new contour-based method which solves both the pose estimation problem and the feature correspondence problem simultaneously and iteratively is proposed. The outer contour of the object is firstly extracted from the input 2D grey-level image, then a tentative point correspondence relationship is established between the extracted contour and object's 3D model, based on which object's pose parameters will be estimated; the newly estimated pose parameters are then used to revise the tentative point correspondence relationship, and the process is iterated until convergence. Experiment results are promising, showing that the authors' method has fast convergence speed and good convergence radius. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature extraction based on fuzzy local discriminant embedding with applications to face recognition

    Publication Year: 2011 , Page(s): 301 - 308
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (411 KB)  

    Recently, local discriminant embedding (LDE) was proposed to manifold learning and pattern classification. LDE achieves good discriminating performance by integrating the information of neighbour and class relations between data points. However, in the real-world applications, the performances of face recognition are always affected by variations in illumination conditions and different facial expressions. LDE still cannot solve illumination problem in face recognition. In this study, the fuzzy local discriminant embedding (FLDE) algorithm is proposed, in which the fuzzy k-nearest neighbour (FKNN) is implemented to reduce these outer effects to obtain the correct local distribution information to persuit good performance. In the proposed method, a membership degree matrix is firstly calculated using FKNN, then the membership degree is incorporated into the definition of the Laplacian scatter matrix to obtain the fuzzy Laplacian scatter matrix. The optimal projections of FLDE can be obtained by solving a generalised eigenfunction. Experimental results on ORL, Yale and AR face databases show the effectiveness of the proposed method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Use of feedback strategies in the detection of events for video surveillance

    Publication Year: 2011 , Page(s): 309 - 319
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (939 KB)  

    The authors present a feedback-based approach for event detection in video surveillance that improves the detection accuracy and dynamically adapts the computational effort depending on the complexity of the analysed data. A core feedback structure is proposed based on defining different levels of detail for the analysis performed and estimating the complexity of the data being analysed. Then, three feedback-based analysis strategies are defined (based on this core structure) and introduced in the processing stages of a typical video surveillance system. A rule-based system is designed to manage the interaction between these feedback-strategies. Experimental results show that the proposed approach slightly increases the detection reliability, whereas highly reduces the computational effort as compared to the initially developed surveillance system (without feedback strategies) across a variety of multiple video surveillance scenarios operating at real time. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Scene classification in compressed and constrained domain

    Publication Year: 2011 , Page(s): 320 - 334
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1167 KB)  

    Holistic representations of natural scenes are an effective and powerful source of information for semantic classification and analysis of images. Despite the technological hardware and software advances, consumer single-sensor imaging devices technology are quite far from the ability of recognising scenes and/or to exploit the visual content during (or after) acquisition time. The frequency domain has been successfully exploited to holistically encode the content of natural scenes in order to obtain a robust representation for scene classification. The authors exploit a holistic representation of the scene in the discrete cosine transform domain fully compatible with the JPEG format. The advised representation is coupled with a logistic classifier to perform classification of the scene at superordinate level of description (e.g. natural against artificial), or to discriminate between multiple classes of scenes usually acquired by a consumer imaging device (e.g. portrait, landscape and document). The proposed method is able to work in constrained domain. Experiments confirm the effectiveness of the proposed method. The obtained results closely match state-of-the-art methods in terms of accuracy outperforming in terms of computational resources. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.

Aims & Scope

IET Computer Vision seeks original research papers in a wide range of areas of computer vision. The vision of the journal is to publish the highest quality research work that is relevant and topical to the field, but not forgetting those works that aim to introduce new horizons and set the agenda for future avenues of research in Computer Vision.

Full Aims & Scope