By Topic

Image Processing, IET

Issue 6 • Date Sept. 2011

Filter Results

Displaying Results 1 - 5 of 5
  • Relevance feedback approach for image retrieval combining support vector machines and adapted gaussian mixture models

    Publication Year: 2011 , Page(s): 531 - 540
    Cited by:  Papers (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (377 KB)  

    A new relevance feedback (RF) approach for content-based image retrieval (CBIR) is presented, which uses Gaussian mixture (GM) models as image representations. The GM of each image is obtained as an adaptation of a universal GM which models the probability distribution of the features of the image database. In each RF round, the positive and negative examples provided by the user until the current round are used to train a support vector machine (SVM) to distinguish between the relevant and irrelevant images according to the preferences of the user. In order to quantify the similarity between two images represented as GMs, Kullback-Leibler (KL) approximations are employed, the computation of which can be further accelerated taking advantage from the fact that the GMs of the images are all refined from a common model. An appropriate kernel function, based on this distance between GMs, is used to make possible the incorporation of GMs in the SVM framework. Finally, comparative numerical experiments that demonstrate the merits of the proposed RF methodology and the advantages of using GMs for image modelling are provided. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive scalar and vector median filtering of noisy colour images based on noise estimation

    Publication Year: 2011 , Page(s): 541 - 553
    Cited by:  Papers (2)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (769 KB)  

    To address the problem of removing impulsive noise with different density from colour images, a new filtering algorithm is proposed based on noise estimation as well as adaptive scalar (SMF) and vector median filter (VMF). Two-level noise estimation scheme is adopted for noise detection, where the first-level estimation is based on maximum and minimum intensity value of each colour channel, and the second-level estimation uses weighted directional operators. For noise restoration, the uncorrupted pixels are remained unchanged, and the corrupted pixels of low-to-medium density are restored by the double weighted VMF, where the term double weighted means that the pixels' spatial distance and magnitude value are weighted together for the vector ordering in the computation of vector median filtering. In addition, the corrupted pixels of high density are restored by the SMF based on M estimator and the neighbourhood processed pixels. According to the estimated noise density, the proposed SMF and VMF are switched adaptively. The experimental results show that the new algorithm can filter the noise effectively while protecting the image colour, contrast and fine details well for the impulsive noise of different density (even as high as 99%). View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Texture segmentation in the joint photographic expert group 2000 domain

    Publication Year: 2011 , Page(s): 554 - 559
    Cited by:  Papers (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (477 KB)  

    Image segmentation is an important task in many image processing systems. For efficient transmission over a band-limited channel, original images are often compressed before being stored in databases. In order to avoid the burden of decompressing an image, it is desirable to extract features directly from a code stream. This approach saves computational time significantly. The look up table used for the MQ coder defined in joint photographic expert group 2000 (JPEG2000) called the MQ table provides probability models for bit-plane coding of wavelet coefficients, the wavelet histogram information can be obtained directly from a JPEG2000 code stream. Thus, the MQ feature based on the MQ table is proposed to segment an image in the JPEG2000 domain directly. Experimental results of clustering these features by using the simple K-means algorithm show the potential of MQ feature. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image registration based on criteria of feature point pair mutual information

    Publication Year: 2011 , Page(s): 560 - 566
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (413 KB)  

    Similarity measurement based on mutual information maximisation has been successful applied in image registration. However, it costs a lot of computation time and the interference of local maxima in the search process always makes the registration search into local maxima that may cause misregistration. In order to eliminate these shortcomings, a novel image registration method is presented in this study. In the method wavelet multi-scale product is calculated to extract the feature points and angle information of the two input images, then a new criterion of registration criterion of feature point pair mutual information is defined to acquire corresponding matching points. In the experiments, our method and image registration methods based on correlation criteria and alignment metric criteria are tested for comparison. Experimental results show that the registration of our method outperforms that of the other two methods and the registration errors are obviously reduced. The errors of coordinates are lower compared to the errors of 78% of the other two methods and the errors of rotation angle are lower compared to the errors of 6% of the other two methods. The seams of the registration image results are very smooth and the transition zones are very uniform. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image enlargement via interpolatory subdivision

    Publication Year: 2011 , Page(s): 567 - 571
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (283 KB)  

    A novel image enlargement method based on a modified interpolatory subdivision scheme is proposed in this study. The subdivision scheme is a modification from the 4-point interpolatory subdivision by substituting the interpolation rule for a tangent-constrained Hermite interpolation and in surface case the subdivision is derived from a Ferguson patch. By estimating the gradients of the Ferguson patch, the authors present an image enlargement algorithm preserving the sharp edges. Benefit from the advantages of subdivision, this algorithm runs fast. Numerical experiments illustrate the efficiency of the novel method. View full abstract»

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

Aims & Scope

The range of topics covered by IET Image Processing includes areas related to the generation, processing and communication of visual information.

Full Aims & Scope

Meet Our Editors

Publisher
IET Research Journals
iet_ipr@theiet.org