Online ISSN
1751-9667
Print ISSN
1751-9659
IET Image Processing
Volume 6, Issue 1, February 2012
Volumes & issues:
Volume 6, Issue 1
February 2012
-
- Author(s): C.W. Bong and M. Rajeswari
- Source: IET Image Processing, Volume 6, Issue 1, p. 1 –10
- DOI: 10.1049/iet-ipr.2010.0122
- Type: Article
- + Show details - Hide details
-
p.
1
–10
(10)
This study reviews the state-of-the-art multiobjective optimisation (MOO) techniques with metaheuristic through clustering approaches developed specifically for image segmentation problems. The authors treat image segmentation as a real-life problem with multiple objectives; thus, focusing on MOO methods that allow a trade-off among multiple objectives. A reasonable solution to a multiobjective (MO) problem is to investigate a set of solutions, each of which satisfies the objectives at an acceptable level without being dominated by any other solution. The primary difference of MOO methods from traditional image segmentation is that instead of a single solution, their output is a set of solutions called Pareto-optimal solution. This study discusses the evolutionary and non-evolutionary MO clustering techniques for image segmentation. It diagnoses the requirements and issues for modelling MOO via MO clustering technique. In addition, the potential challenges and the directions for future research are presented. - Author(s): J. Wen ; B. Zhang ; C. Pan ; X. Zhang
- Source: IET Image Processing, Volume 6, Issue 1, p. 11 –21
- DOI: 10.1049/iet-ipr.2009.0129
- Type: Article
- + Show details - Hide details
-
p.
11
–21
(11)
This study proposes a unified method for a wide variety of image composition tasks. The proposed method is developed by constraining the responses of a set of filters to a target image. Each filter describes an attribute of the target image. Also, each attribute field is assumed to be equal to the corresponding attribute field of an input source. The constraints imposed by all those attributes are weighted heterogeneously and formulated into a minimisation problem. For different tasks, the required attributes (e.g. gradient, texture and colour constraints) can be specified by different sources (e.g. from a given image, constructed from several images or specified by users). The framework is flexible and can be configured to meet a variety of image editing tasks. To validate the effectiveness of this method, a variety of applications have been presented, including face data illumination removal, remote-sensing images fusion, texture transfer, multi-focus image fusion, seamless texture tiling and text layer transfer. The experimental results illustrate that the proposed method is effective in performance for the presented image editing tasks with comparisons to classical methods for the specified tasks. - Author(s): P.Y. Lau ; P.L. Correia ; P. Fonseca ; A. Campos
- Source: IET Image Processing, Volume 6, Issue 1, p. 22 –30
- DOI: 10.1049/iet-ipr.2009.0426
- Type: Article
- + Show details - Hide details
-
p.
22
–30
(9)
Video technology has been playing an increasing role in marine science, both for habitat mapping and estimating commercial species abundance. However, when quantification is needed, it is usually based on manual counting, a subjective and time-consuming task. The present work proposes a methodology to automatically quantify the abundance of Norway lobsters, Nephrops norvegicus, by counting lobsters or their burrows from video sequences, as a reliable complement to the currently used operator-based approach. The methodology is validated using a set of test video sequences captured at the Portuguese continental slope, using a monochrome camera mounted on a trawl gear, being characterised by non-uniform illumination, artefacts at image border, noise and marine snow. The analysis includes, after a pre-processing stage, the segmentation of regions of interest and the corresponding classification into one of the three targeted classes: Norway lobsters, burrows and others (including trawl impact marks). The developed software prototype, named IT-IPIMAR N. norvegicus (I2N2), is able to provide an objective, detailed and comprehensive analysis to complement manual evaluation, for lobster and burrow density estimation. - Author(s): A. Schuchter and A. Uhl
- Source: IET Image Processing, Volume 6, Issue 1, p. 31 –42
- DOI: 10.1049/iet-ipr.2009.0055
- Type: Article
- + Show details - Hide details
-
p.
31
–42
(12)
In this study, we evaluate fast motion estimation (ME) techniques in the context of a JPEG 2000-based video coding system for surveillance-type videos. The authors have designed a low-complexity algorithm, called block-selective ME, which restricts block matching to certain frames or blocks containing high motion. They compare the performance of our block-selective ME algorithm to a frame-based approach and to a standard fast-motion algorithm (three-step search (TSS)). For surveillance-type videos, the authors show that the block-selective approach achieves the peak signal to noise ratio (PSNR) quality of a full ME scheme for; 70–80% of the blocks. Moreover, this approach delivers a higher visual image quality compared to TSS, if the computational load for a set number of blocks were fixed. The authors have integrated our block-selective approach into different coders (H.264 and MPEG-2) and show that our approach is an outstanding alternative to fast-ME in low-complexity environments. - Author(s): J. Yang ; Y. Sun ; Y. Wu ; S. Sun
- Source: IET Image Processing, Volume 6, Issue 1, p. 43 –52
- DOI: 10.1049/iet-ipr.2009.0366
- Type: Article
- + Show details - Hide details
-
p.
43
–52
(10)
Integrating H.264 scalable video coding (SVC) technology with a multiple input multiple output (MIMO) wireless system can significantly enhance the overall performance of high-quality real-time wireless video transmissions. However, the state-of-the-art techniques in these two areas are largely developed independently. In this research, with the objective to deliver the optimal visual quality and accurate rate regulation for wireless video applications, the authors propose a novel joint H.264/SVC-MIMO rate control (RC) algorithm for video compression and transmission over MIMO systems. The authors first present a systematic architecture for H.264/SVC compression and transmission over MIMO systems. Then, based on MIMO channel properties, the authors use a packet-level two-state Markov model to estimate MIMO channel states and predict the number of retransmitted bits in the presence of automatic repeat request. Finally, an efficient joint rate controller is proposed to regulate the output bit rate of each layer according to the available channel throughput and buffer fullness. The authors' extensive simulation results demonstrate that their algorithm outperforms JVT-W043 RC algorithm, adopted in the H.264/SVC reference software, by providing more accurate output bit rate, reducing buffer overflow, lessen frame skipping, and finally, improves the overall coding quality. - Author(s): B.W. Kim ; J.-H. Jung ; B.G. Kim ; D.-J. Park
- Source: IET Image Processing, Volume 6, Issue 1, p. 53 –59
- DOI: 10.1049/iet-ipr.2009.0415
- Type: Article
- + Show details - Hide details
-
p.
53
–59
(7)
As a result of the rapid development of hardware whose operation has low power requirements, a great deal of interest has been shown in wireless multimedia sensor networks for various applications. In sensor networks in which the sensor nodes are distributed randomly and have low-power cameras, the fields of view of some adjacent sensor nodes may overlap. The authors introduce a scheme for constructing a non-overlapping panoramic mosaic by transmitting partial images. In particular, a solution of the joint cost function for network lifetime and video quality is used to select the boundary lines between adjacent images. The experimental results show that the proposed scheme increases the network lifetime while providing better video quality. - Author(s): M.-C. Chien and P.-C. Chang
- Source: IET Image Processing, Volume 6, Issue 1, p. 60 –71
- DOI: 10.1049/iet-ipr.2010.0149
- Type: Article
- + Show details - Hide details
-
p.
60
–71
(12)
An H.264 video encoder adopts multiple encoding tools to achieve high coding efficiency at the expense of high computational complexity. The allowable computational complexity for real-time video encoding, however, is generally limited in a wireless handset. This research proposes a complexity control mechanism that is composed of two algorithms to minimise the distortion of each encoded video frame under the computational complexity constraint and the rate constraint. The first proposed algorithm performs optimal complexity allocation among encoding tools based on a new complexity–rate–distortion (C–R–D) model. This model precisely describes how each encoding tool influences the C–R–D performance of the encoder with concise formulas. Accordingly, the algorithm obtains the optimal complexity of each encoding tool by a closed-form solution with small complexity overhead. Based on a new C–D model of motion estimation, this work proposes the second algorithm that performs optimal complexity allocation among macro-blocks to further allocate suitable complexity to each macro-block. Experiments performed on a software-optimised source code show that these two algorithms yield superior performance to the existing algorithms. - Author(s): P.-M. Lam ; C.-S. Leung ; T.-T. Wong
- Source: IET Image Processing, Volume 6, Issue 1, p. 72 –86
- DOI: 10.1049/iet-ipr.2009.0134
- Type: Article
- + Show details - Hide details
-
p.
72
–86
(15)
The spherical harmonic (SH) basis has been widely used for representing relighting data. However, under some situations, the magnitudes of the estimated SH coefficients could be very large. Hence, relit images are very sensitive to quantisation (or compression) noise of these estimated SH coefficients. To tackle this issue, this study proposes a new spherical basis, namely eigen hemispherical harmonic (EHSH) basis. Its approximation ability is the same as that of the SH basis. With this new basis, the magnitudes of the estimated coefficients are controllable. Hence, the artefacts in the relit images can be suppressed. Besides, the transform from the classical hemispherical SH coefficients to the EHSH coefficients is discussed. Finally, the authors present the way to relight images based on the EHSH basis. - Author(s): L. Sui ; J. Zhang ; L. Zhuo ; Y.C. Yang
- Source: IET Image Processing, Volume 6, Issue 1, p. 87 –93
- DOI: 10.1049/iet-ipr.2011.0005
- Type: Article
- + Show details - Hide details
-
p.
87
–93
(7)
In order to recognise and filter pornographic images, visual-word-based image representation has attracted more and more attention. An image can be represented as a bag of visual words, which is analogous to the bag-of-words representation of text documents. However, most of the existing approaches create visual words from images in the pixel domain, which requires extra processing time to decompress images, since most images are stored in compressed formats. A novel pornographic images recognition method based on visual words in a compressed domain is proposed in this study. There are four steps in this method: (i) low-resolution image is constructed from compressed data; (ii) scale-invariant feature transform (SIFT) descriptors are extracted from this low-resolution image; (iii) a visual vocabulary is created based on SIFT descriptors; (iv) pornographic images are identified by using a support vector machine (SVM) classifier. The experimental results indicate that the proposed method can recognise pornographic images accurately with much less computational time.
Multiobjective clustering with metaheuristic: current trends and methods in image segmentation
Image composition by constraining responses of filters
Estimating Norway lobster abundance from deep-water videos: an automatic approach
Fast motion estimation approaches for surveillance-type videos in an inter-frame JPEG 2000-based adaptive video coding system
Joint H.264/scalable video coding-multiple input multiple output rate control for wireless video applications
Construction of a non-overlapping panoramic mosaic in wireless multimedia sensor networks
Optimal model-based complexity control for H.264 video encoding
Noise-resistant hemispherical basis for image-based relighting
Research on pornographic images recognition method based on visual words in a compressed domain
Most viewed content for this Journal
Article
content/journals/iet-ipr
Journal
5
Most cited content for this Journal
-
Medical image segmentation using deep learning: A survey
- Author(s): Risheng Wang ; Tao Lei ; Ruixia Cui ; Bingtao Zhang ; Hongying Meng ; Asoke K. Nandi
- Type: Article
-
Block-based discrete wavelet transform-singular value decomposition image watermarking scheme using human visual system characteristics
- Author(s): Nasrin M. Makbol ; Bee Ee Khoo ; Taha H. Rassem
- Type: Article
-
Classification of malignant melanoma and benign skin lesions: implementation of automatic ABCD rule
- Author(s): Reda Kasmi and Karim Mokrani
- Type: Article
-
Digital image watermarking method based on DCT and fractal encoding
- Author(s): Shuai Liu ; Zheng Pan ; Houbing Song
- Type: Article
-
Tomato leaf disease classification by exploiting transfer learning and feature concatenation
- Author(s): Mehdhar S. A. M. Al‐gaashani ; Fengjun Shang ; Mohammed S. A. Muthanna ; Mashael Khayyat ; Ahmed A. Abd El‐Latif
- Type: Article