scispace - formally typeset
Search or ask a question

Showing papers in "Iet Image Processing in 2013"


Journal ArticleDOI
TL;DR: The concept of matched filtering is improved, and the proposed blood vessel segmentation approach is at least comparable with recent state-of-the-art methods, and outperforms most of them with an accuracy of 95% evaluated on the new database.
Abstract: Automatic assessment of retinal vessels plays an important role in the diagnosis of various eye, as well as systemic diseases. A public screening is highly desirable for prompt and effective treatment, since such diseases need to be diagnosed at an early stage. Automated and accurate segmentation of the retinal blood vessel tree is one of the challenging tasks in the computer-aided analysis of fundus images today. We improve the concept of matched filtering, and propose a novel and accurate method for segmenting retinal vessels. Our goal is to be able to segment blood vessels with varying vessel diameters in high-resolution colour fundus images. All recent authors compare their vessel segmentation results to each other using only low-resolution retinal image databases. Consequently, we provide a new publicly available high-resolution fundus image database of healthy and pathological retinas. Our performance evaluation shows that the proposed blood vessel segmentation approach is at least comparable with recent state-of-the-art methods. It outperforms most of them with an accuracy of 95% evaluated on the new database.

371 citations


Journal ArticleDOI
TL;DR: Experimental results show that the proposed multi-focus image fusion algorithm can not only extract more important detailed information from source images, but also avoid the introduction of artificial information effectively.
Abstract: In this study, a new multi-focus image fusion algorithm based on the non-subsampled shearlet transform (NSST) is presented. First, an initial fused image is acquired by using a conventional multi-resolution image fusion method. The pixels of those source multi-focus images, which have smaller square error with the corresponding pixels of the initial fused image, are considered in the focused regions. Based on this principle, the focused regions are determined, and the morphological opening and closing are employed for post-processing. Then the focused regions and the focused border regions in each source image are identified and used to guide the fusion process in NSST domain. Finally, the fused image is obtained using the inverse NSST. Experimental results show that this proposed method can not only extract more important detailed information from source images, but also avoid the introduction of artificial information effectively. It significantly outperforms the discrete wavelet transform (DWT)-based fusion method, the non-subsampled contourlet-transformbased fusion method and the NSST-based fusion method (see Miao et al. 2011) in terms of both visual quality and objective evaluation.

139 citations


Journal ArticleDOI
TL;DR: This survey attempts to cover the blind techniques that have been proposed for exposing forgeries, focusing on the detection techniques for three of the most common forgery types, namely copy/move, splicing and retouching.
Abstract: With the mushroom growth of state-of-the-art digital image and video manipulations tools, establishing the authenticity of multimedia content has become a challenging issue. Digital image forensics is an increasingly growing research field that symbolises a never ending struggle against forgery and tampering. This survey attempts to cover the blind techniques that have been proposed for exposing forgeries. This work dwells on the detection techniques for three of the most common forgery types, namely copy/move, splicing and retouching.

111 citations


Journal ArticleDOI
TL;DR: The internal noise of an image has been utilised to produce a noise-induced transition of a dark image from a state of low contrast to that of high contrast.
Abstract: In this study, a dynamic stochastic resonance (DSR)-based technique in spatial domain has been proposed for the enhancement of dark- and low-contrast images. Stochastic resonance (SR) is a phenomenon in which the performance of a system (low-contrast image) can be improved by addition of noise. However, in the proposed work, the internal noise of an image has been utilised to produce a noise-induced transition of a dark image from a state of low contrast to that of high contrast. DSR is applied in an iterative fashion by correlating the bistable system parameters of a double-well potential with the intensity values of a low-contrast image. Optimum output is ensured by adaptive computation of performance metrics - relative contrast enhancement factor ( F ), perceptual quality measures and colour enhancement factor. When compared with the existing enhancement techniques such as adaptive histogram equalisation, gamma correction, single-scale retinex, multi-scale retinex, modified high-pass filtering, edge-preserving multi-scale decomposition and automatic controls of popular imaging tools, the proposed technique gives significant performance in terms of contrast and colour enhancement as well as perceptual quality. Comparison with a spatial domain SR-based technique has also been illustrated.

88 citations


Journal ArticleDOI
TL;DR: A generalised contrast enhancement algorithm is proposed which is independent of parameter setting for a given dynamic range of the input image and uses the modified histogram for spatial transformation on grey scale to render a better quality image irrespective of the image type.
Abstract: Histogram equalisation has been a much sought-after technique for improving the contrast of an image, which however leads to an over enhancement of the image, giving it an unnatural and degraded appearance. In this framework, a generalised contrast enhancement algorithm is proposed which is independent of parameter setting for a given dynamic range of the input image. The algorithm uses the modified histogram for spatial transformation on grey scale to render a better quality image irrespective of the image type. Added to this, two variants of the proposed methodology are presented, one of which preserves the brightness of original image while the other variant increases the image brightness adaptively, giving it a better look. Qualitative and quantitative assessments like degree of entropy un-preservation, edge-based contrast measure and structure similarity index measures are then applied to the 500 image data set for comparing the proposed algorithm with several existing state-of-the-art algorithms. Experimental results show that the proposed algorithm produces better or comparable enhanced images than several algorithms.

87 citations


Journal ArticleDOI
TL;DR: Experimental results demonstrate that the proposed iris segmentation algorithm significantly minimises the required time to segment the iris without affecting the segmentation accuracy, and the comparison results show the superiority of the proposed algorithm in terms of segmentsation accuracy and recognition performance.
Abstract: Design a fast and reliable iris segmentation algorithm for less constrained iris images is essential to build a robust iris recognition system. Daugman's integrodifferential operator (IDO) is one of powerful iris segmentation mechanisms, but in contrast consumes a large portion of the computational time for localising the rough position of the iris centre and eyelid boundaries. To address this problem, a fast iris segmentation algorithm is proposed. First, the circular Gabor filter is adopted to find the rough position of the pupil centre. Second, the iris and pupil circles are localised using the IDO taken into account that the real centres of the iris and pupil are in the small area around the rough position of the pupil centre. Third, the upper and lower eyelid boundaries are extracted using the live-wire technique. Experimental results demonstrate that the proposed iris segmentation algorithm significantly minimises the required time to segment the iris without affecting the segmentation accuracy. Moreover, the comparison results with state-of-the-art iris segmentation algorithms show the superiority of the proposed algorithm in terms of segmentation accuracy and recognition performance. The challenging UBIRIS.v1 iris image database is utilised to evaluate the performance of the proposed algorithm.

71 citations


Journal ArticleDOI
TL;DR: The experimental results show that the proposed SVM classifier is able to achieve high segmentation and classification accuracy effectiveness as measured by sensitivity and specificity.
Abstract: A computer software system is designed for segmentation and classification of benign and malignant tumour slices in brain computed tomography images. In this study, the authors present a method to select both dominant run length and co-occurrence texture features of wavelet approximation tumour region of each slice to be segmented by a support vector machine (SVM). Two-dimensional discrete wavelet decomposition is performed on the tumour image to remove the noise. The images considered for this study belong to 208 tumour slices. Seventeen features are extracted and six features are selected using Student's t-test. This study constructed the SVM and probabilistic neural network (PNN) classifiers with the selected features. The classification accuracy of both classifiers are evaluated using the k fold cross validation method. The segmentation results are also compared with the experienced radiologist ground truth. Quantitative analysis between ground truth and the segmented tumour is presented in terms of segmentation accuracy and segmentation error. The proposed system provides some newly found texture features have an important contribution in classifying tumour slices efficiently and accurately. The experimental results show that the proposed SVM classifier is able to achieve high segmentation and classification accuracy effectiveness as measured by sensitivity and specificity.

69 citations


Journal ArticleDOI
TL;DR: A technique based on morphological image processing and fuzzy logic to detect hard exudates from DR retinal images, which obtained sensitivity and specificity of detecting hardExudates as 75.43 and 99.99%, respectively.
Abstract: Diabetic retinopathy (DR), that affects the blood vessels of the human retina, is considered to be the most serious complication prevalent among diabetic patients. If detected successfully at an early stage, the ophthalmologist would be able to treat the patients by advanced laser treatment to prevent total blindness. In this study, the authors propose a technique based on morphological image processing and fuzzy logic to detect hard exudates from DR retinal images. At the initial stage, the exudates are identified using mathematical morphology that includes elimination of the optic disc. Subsequently, hard exudates are extracted using an adaptive fuzzy logic algorithm that uses values in the RGB colour space of retinal image to form fuzzy sets and membership functions. The fuzzy output for all the pixels in every exudate is calculated for a given input set corresponding to red, green and blue channels of a pixel in an exudate. This fuzzy output is computed for hard exudates according to the proportion of the area of the hard exudates. By comparing the results with hand-drawn ground truths, the authors obtained sensitivity and specificity of detecting hard exudates as 75.43 and 99.99%, respectively.

55 citations


Journal ArticleDOI
TL;DR: The new techniques of three-dimensional (3D)-optical coherence tomography (OCT) imaging is very useful for detecting retinal pathologic changes in various diseases and determining retinal thickness `abnormalities'.
Abstract: The new techniques of three-dimensional (3D)-optical coherence tomography (OCT) imaging is very useful for detecting retinal pathologic changes in various diseases and determining retinal thickness `abnormalities'. Fundus colour images have been used for several years for detecting retinal abnormalities too. If the two image modalities were combined, the resulted image would be more informative. The first step to combine these two modalities is to register colour fundus images with an en face representation of OCT. In this study, curvelet transform is used to extract vessels for both modalities. Then the extracted vessels from two modalities are registered together in two stages. At first, images are registered using scaling and translation transformations. Then a quadratic transformation model is assumed between two pairs of images; because retina is imaged as a second-order surface. Twenty-two eyes (17 macular and 5 prepapillary), from random patients, were imaged in this study with Topcon 3D OCT1000 instrument. A new registration error is defined which averages the distance between all the corresponding points in two sets of vessels. Results show that registration error after stage one is 6.01 ± 1.82 pixels and after stage two is 1.02 ± 0.02 pixels.

52 citations


Journal ArticleDOI
TL;DR: A new method based on combination of Hadamard matrix and discrete wavelet transform (HDWT) in hue-min-max-difference colour space is proposed and shows that the use of HDWT provides better performance in comparison with Haar discreteWavelet transform, colour layout descriptor, dominant colour descriptor and scalable colour descriptor, Padua point and histogram intersection.
Abstract: Image retrieval is one of the most applicable image processing techniques, which has been used extensively. Feature extraction is one of the most important procedures used for interpretation and indexing images in content-based image retrieval systems. Effective storage, indexing and managing a large number of image collections is a critical challenge in computer systems. There are many proposed methods to overcome these problems. However, the rate of accurate image retrieval and speed of retrieval is still an interesting field of research. In this study, the authors propose a new method based on combination of Hadamard matrix and discrete wavelet transform (HDWT) in hue-min-max-difference colour space. An average normalised rank and combination of precision and recall are considered as metrics to evaluate and compare the proposed method against different methods. The obtained results show that the use of HDWT provides better performance in comparison with Haar discrete wavelet transform, colour layout descriptor, dominant colour descriptor and scalable colour descriptor, Padua point and histogram intersection.

47 citations


Journal ArticleDOI
TL;DR: An analytical relationship is derived between PSNR and SSIM which works for some kinds of common image degradations such as Gaussian blur, additive Gaussian noise, Jpeg and Jpeg2000 compressions and some experimental observations regarding these measures.
Abstract: In this study, the authors analyse two well-known image quality metrics, peak-signal-to-noise ratio (PSNR) as well as structural similarity index measure (SSIM), and the authors derive an analytical relationship between them which works for some kinds of common image degradations such as Gaussian blur, additive Gaussian noise, Jpeg and Jpeg2000 compressions. The analytical relationship brings more clarity on the interpretation of PSNR and SSIM values, explains some differences found between these quality measures in the literature and confirms some experimental observations regarding these measures. A series of tests realised on images from the Kodak database give a better understanding of the performance of SSIM and PSNR in assessing image quality.

Journal ArticleDOI
TL;DR: This research work deals with the segmentation of grey scale, colour and texture images using graph-based method that provides effective results for most type of images.
Abstract: This research work deals with the segmentation of grey scale, colour and texture images using graph-based method. A graph is constructed using intensity, colour and texture profiles of image simultaneously. Based on nature of the image, a fuzzy rule-based system is used to find the weight that should be given to a specific image feature during the graph development. The fuzzy rule-based system provides a valuable approximation to cater the fact of imprecise knowledge (in our case knowledge about the involvement of a particular image feature in image). The graph is further used in multilevel graph-partitioning algorithm based on normalised graph cuts framework where it is iteratively bi-partitioned through normalised cuts to obtain optimum partitions. Multilevel algorithm makes the process fast enough to accommodate large databases as segmentation is often used in high-level image processing-techniques (i.e. object classification and recognition). Partitioned graph then results in segmented image. Berkeley segmentation database is used to experiment on the authors algorithm. The segmentation results are evaluated through probabilistic rand index and global consistency error methods. It is shown that the presented segmentation method provides effective results for most type of images.

Journal ArticleDOI
TL;DR: The experimental results indicate that the proposed method achieves higher retrieval accuracy than several previously presented schemes, whereas the computational complexity and processing time of the new method are less than those of other approaches.
Abstract: The aim of this study is to take advantage of both shape and texture properties of image to improve the performance of image indexing and retrieval algorithm. Further, a framework for partitioning image into non-overlapping tiles of different sizes, which results in higher retrieval efficiency, is presented. In the new approach, the image is divided into different regions (tiles). Then, the energy and standard deviation of Hartley transform coefficients of each tile, which serve as the local descriptors of texture, are extracted as sub-features. Next, invariant moments of edge image are used to record the shape features. The shape features and combination of sub-features of texture provide a robust feature set for image retrieval. The most similar highest priority (MSHP) principle is used for matching of textural features and Canberra distance is utilised for shape features matching. The retrieved image is the image which has less MSHP and Canberra distance from the query image. The proposed method is evaluated on three different image sets, which contain about 17 000 images. The experimental results indicate that the proposed method achieves higher retrieval accuracy than several previously presented schemes, whereas the computational complexity and processing time of the new method are less than those of other approaches.

Journal ArticleDOI
TL;DR: The developed fusion system eliminates undesirable effects such as fusion artefacts and loss of visually vital information that compromise their usefulness by means of taking into account the physical meaning of contourlet coefficients.
Abstract: Multi-modal images fusion is one of the most truthful and useful diagnostic techniques in medical imaging system. This study proposes an image fusion system for medical engineering based on contourlet transform and multi-level fuzzy reasoning technique in which useful information from two spatially registered medical images is integrated into a new image that can be used to make clinical diagnosis and treatment more accurate. The system applies pixel-based fuzzy fusion rule to contourlet's coefficients of high-frequency details and feature-based fuzzy fusion to its low-frequency approximations, which can help the development of sophisticated algorithms that consider not only the time cost but also the quality of the fused image. The developed fusion system eliminates undesirable effects such as fusion artefacts and loss of visually vital information that compromise their usefulness by means of taking into account the physical meaning of contourlet coefficients. The experimental results show that the proposed fusion system outperforms the existing fusion algorithms and is effective to fuse medical images from different sensors with applications in brain image processing.

Journal ArticleDOI
TL;DR: Experimental results show that the proposed scheme can significantly improve image fusion performance, performs very well in fusion and outperforms conventional methods such as traditional discrete wavelet transform, dual tree complex wavelet and PCNN in terms of objective criteria and visual appearance.
Abstract: Image fusion combines information from multiple images of the same scene to obtain a composite image which is more suitable for further image processing tasks. This study presented an image fusion scheme based on the modified dual pulse coupled neural network (PCNN) in non-subsampled contourlet transform (NSCT) domain. NSCT can overcome the lack of shift invariance in contourlet transform. Original images were decomposed to obtain the coefficients of low-frequency subbands and high-frequency subbands. In this fusion scheme, a new sum-modified Laplacian of the low-frequency subband image, which represents the edge-feature of the low-frequency subband image in NSCT domain, is presented and input to motivate modified dual PCNN. For fusion of high-frequency subband coefficients, spatial frequency will be used as the gradient features of images to motivate dual channel PCNN and to overcome Gibbs phenomena. Experimental results show that the proposed scheme can significantly improve image fusion performance, performs very well in fusion and outperforms conventional methods such as traditional discrete wavelet transform, dual tree complex wavelet and PCNN in terms of objective criteria and visual appearance.

Journal ArticleDOI
TL;DR: With automatic conjugate image-matching capability, the developed system is suitable for volumetric data collection in establishing web-based LBS applications integrated with GSV panoramas and Google Maps/Earth in which positional accuracy is not primarily concerned.
Abstract: Location-based services (LBS) on web-based maps and images have come into real-time since Google launched its street view imaging services in 2007. This research employs Google Maps API and Web Service, GAE for JAVA, AJAX, Proj4js, cascading style sheets and HyperText markup language in developing a platform for accessing the orientation parameters of Google street view (GSV) panoramas in order to determine the three-dimensional (3D) position of points of interest (POIs) by intersection between two nearby GSV images and to validate the 3D position of a GSV panorama by resection from three known POIs. Extracted 3D positional information of the features are then packed in keyhole markup language format and stored in GAE Servlet for future LBS applications integrated with Google Maps and Google Earth. Experimental results from two tests on intersection and one test on resection of GSV panoramas in National Chung Hsing University campus were examined with error reports and source analyses. With automatic conjugate image-matching capability, the developed system is suitable for volumetric data collection in establishing web-based LBS applications integrated with GSV panoramas and Google Maps/Earth in which positional accuracy is not primarily concerned.

Journal ArticleDOI
TL;DR: The quasi- Lossless and improved quasi-lossless fractal coding algorithms are found to outperform standard fractal coded thereby proving the possibility of using fractal-based image compression algorithms for medical image compression.
Abstract: In this study, the performance of fractal-based coding algorithms such as standard fractal coding, quasi-lossless fractal coding and improved quasi-lossless fractal coding are evaluated by investigating their ability to compress magnetic resonance images (MRIs) based on compression ratio, peak signal-to-noise ratio and encoding time. For this purpose, MRI head scan test sets of 512 × 512 pixels have been used. A novel quasi-lossless fractal coding scheme, which preserves important feature-rich portions of the medical image, such as domain blocks and generates the remaining part of the image from it, has been proposed using fractal transformations. One of the biggest tasks in fractal image compression is reduction of encoding computation time. A machine learning-based model is used for reducing the encoding time and also for improving the performance of the quasi-lossless fractal coding scheme. The results show a better performance of improved quasi-lossless fractal compression method. The quasi-lossless and improved quasi-lossless fractal coding algorithms are found to outperform standard fractal coding thereby proving the possibility of using fractal-based image compression algorithms for medical image compression. The proposed algorithm allows significant reduction of encoding time and also improvement in the compression ratio.

Journal ArticleDOI
TL;DR: This study describes a novel generalised guided image filtering method with the reference image generated by signal sub space projection (SSP) technique that adopts refined parallel analysis with Monte Carlo simulations to select the dimensionality of signal subspace in the patch-based noisy images.
Abstract: There are various image filtering approaches in computer vision and image processing that are effective for some types of noise, but they invariably make certain assumptions about the properties of the signal and/or noise which lack the generality for diverse image noise reduction. This study describes a novel generalised guided image filtering method with the reference image generated by signal subspace projection (SSP) technique. It adopts refined parallel analysis with Monte Carlo simulations to select the dimensionality of signal subspace in the patch-based noisy images. The noiseless image is reconstructed from the noisy image projected onto the significant eigenimages by component analysis. Training/test image are utilised to determine the relationship between the optimal parameter value and noise deviation that maximises the output peak signal-to-noise ratio (PSNR). The optimal parameters of the proposed algorithm can be automatically selected using noise deviation estimation based on the smallest singular value of the patch-based image by singular value decomposition (SVD). Finally, we present a quantitative and qualitative comparison of the proposed algorithm with the traditional guided filter and other state-of-the-art methods with respect to the choice of the image patch and neighbourhood window sizes.

Journal ArticleDOI
TL;DR: Interpolation-Based Impulse Noise Removal (IBINR), a fast and simple algorithm is proposed to remove fixed valued impulse noise in this study and has the highest or comparable performance in terms of photographic image denoising power and resource efficiency.
Abstract: Interpolation-Based Impulse Noise Removal (IBINR), a fast and simple algorithm is proposed to remove fixed valued impulse noise in this study. The proposed method removes all noisy pixels from the image and determines their values using non-linear interpolation. Compared with the state-of-the-art noise removal algorithms, IBINR has the highest or comparable performance in terms of photographic image denoising power and resource efficiency: it runs in shorter amount of time and does not have any significant additional memory requirements due to the fact that costly sorting operations are avoided.

Journal ArticleDOI
TL;DR: The experimental results show that the proposed method outperforms both conventional and the state-of-the-art techniques.
Abstract: This study presents a satellite image contrast enhancement technique based on the discrete cosine transform (DCT) pyramid and singular value decomposition (SVD), in contrast to the methods based on wavelet decomposition and SVD which could fail to produce satisfactory results for some low-contrast images. With the proposed method, an input image is decomposed into a low sub-band image and reversed L-shape blocks containing the high-frequency coefficients of the DCT pyramid. The singular value matrix of the equalised low sub-band image is then estimated from the combination between the singular matrix of the low sub-band image and the singular matrix of its global histogram equalisation. The qualitative and quantitative performances of the proposed technique are compared with those of conventional image equalisation such as general histogram equalisation and local histogram equalisation, as well as some state-of-the-art techniques such as singular value equalisation technique. Moreover, the proposed technique is contrasted against the technique based on the discrete wavelet transform (DWT) and SVD (DWT-SVD) as well as the technique based on DCT-SVD. The experimental results show that the proposed method outperforms both conventional and the state-of-the-art techniques.

Journal ArticleDOI
TL;DR: The results show that the proposed algorithm improves the signal-to-noise ratio, whereas preserving the edges and has more advantages on the images containing multi-direction information like OCT heart tube image.
Abstract: Optical coherence tomography (OCT) is becoming an increasingly important imaging technology in the Biomedical field. However, the application of OCT is limited by the ubiquitous noise. In this study, the noise of OCT heart tube image is first verified as being multiplicative based on the local statistics (i.e. the linear relationship between the mean and the standard deviation of certain flat area). The variance of the noise is evaluated in log-domain. Based on these, a joint probability density function is constructed to take the inter-direction dependency in the contourlet domain from the logarithmic transformed image into account. Then, a bivariate shrinkage function is derived to denoise the image by the maximum a posteriori estimation. Systemic comparative experiments are made to synthesis images, OCT heart tube images and other OCT tissue images by subjective assessment and objective metrics. The experiment results are analysed based on the denoising results and the predominance degree of the proposed algorithm with respect to the wavelet-based algorithm. The results show that the proposed algorithm improves the signal-to-noise ratio, whereas preserving the edges and has more advantages on the images containing multi-direction information like OCT heart tube image.

Journal ArticleDOI
TL;DR: Experimental results confirm the superiority of the proposed technique against common attacks in comparison with the recently proposed methods and the optimum parameter in the power-law function is obtained based on minimising the error probability.
Abstract: In this study, a robust image watermarking based on the quantisation index modulation (QIM) method is proposed. Conventional QIM methods employ a fixed quantisation step-size that results in poor robustness of the algorithm. Here, the quantisation step-size in the QIM method is adaptively selected using a power-law function and with the aid of the side information, the proposed method is invariant to gain and rotation attack. To keep the watermark imperceptible and increase its robustness, the low-frequency components of high-entropy image blocks are used for data hiding. The analytical error probability and embedding distortion are derived and assessed by simulations on artificial signals. The optimum parameter in the power-law function is obtained based on minimising the error probability. Experimental results confirm the superiority of the proposed technique against common attacks in comparison with the recently proposed methods.

Journal ArticleDOI
TL;DR: The experimental results of the proposed wavelet domain still image watermark detection method demonstrate that the proposed method has a robust detection performance for additive spread spectrum watermarks.
Abstract: In this study, the authors propose a wavelet domain still image watermark detection method which uses the Bessel K probability density function to describe the distribution of wavelet coefficients. In this study, watermark detection is formulated as a binary statistical decision problem which is to detect a signal submerged in the noise that follows a Bessel K distribution. Using this formulation, an optimal watermark detector using likelihood ratio test is proposed. The experimental results of the proposed method in a variety of situations demonstrate that the proposed method has a robust detection performance for additive spread spectrum watermarks.

Journal ArticleDOI
TL;DR: The experimental results show that the proposed ALEM image fusion scheme can achieve a higher fusion quality than some existing fusion schemes, and the proposed FCLALM reconstruction algorithm has a higher peak-signal-to-noise ratio and a faster convergence rate as compared with some existing reconstruction methods.
Abstract: In this study, an efficient multifocus image fusion and reconstruction framework based on compressed sensing in the wavelet domain are proposed. The new framework is composed of three phases. Firstly, the source images are represented with their sparse coefficients using the discrete wavelet transform (DWT). Secondly, the measurements are obtained by the random Gaussian matrix from their sparse coefficients, and are then fused by the proposed adaptive local energy metrics (ALEM) fusion scheme. Finally, a fast continuous linearised augmented Lagrangian method (FCLALM) is proposed to reconstruct the sparse coefficients from the fused measurement, which will be converted by the inverse DWT (IDWT) to the fused image. Our experimental results show that the proposed ALEM image fusion scheme can achieve a higher fusion quality than some existing fusion schemes. In addition, the proposed FCLALM reconstruction algorithm has a higher peak-signal-to-noise ratio and a faster convergence rate as compared with some existing reconstruction methods.

Journal ArticleDOI
TL;DR: The authors show various experimental results and conclude that the proposed new models are better than the second-order and third-order PDEs, especially for weakening the blocky effects.
Abstract: In this study, the authors propose two fourth-order partial differential equations (PDEs) to inpaint the image. By analysing those anisotropic fourth-order PDEs and comparing their diffusion images, the authors confirm they are forward diffusion or backward diffusion. A numerical algorithm is presented using a finite-difference method and analyse the stability of discretisation. Finally, they show various experimental results and conclude that the proposed new models are better than the second-order and third-order PDEs, especially for weakening the blocky effects.

Journal ArticleDOI
TL;DR: A TDE processing scheme is derived from previously proposed domain-based fourth-order PDE by adding second time derivative, which results in better edge preservation, whereas yielding better improvement in signal-to-noise ratio and low noise sensitivity.
Abstract: Fourth-order partial differential equations (PDEs) for noise removal are able to provide a good trade-off between noise removal and edge preservation, and can avoid blocky effects often caused by second-order PDE. In this study, the authors propose a fourth-order telegraph-diffusion equation (TDE) for noise removal. In the authors method, a domain-based fourth-order PDE is proposed, which takes advantage of statistic characteristics of isolated speckles in the Laplace domain to segment the image domain into two domains: speckle domain and non-speckle domain. Then, depending on the domain type, they adopt different conductance coefficients in the proposed fourth-order PDE. The proposed method inherits the advantage of fourth-order PDE which is able to avoid the blocky effects widely seen in images processed by second-order PDE. Furthermore, a TDE processing scheme is derived from previously proposed domain-based fourth-order PDE by adding second time derivative, which results in better edge preservation, whereas yielding better improvement in signal-to-noise ratio and low noise sensitivity. Experimental results show the effectiveness of the proposed method.

Journal ArticleDOI
TL;DR: Instead of registering two images, the authors proceed to registration of the bidimensional intrinsic mode functions (BIMFs) that results from the FABEMD decomposition that contains a tone of grey levels lower than that of the original image, which reduces execution time of the registration.
Abstract: Image registration plays a crucial role in several areas, yet iconic registration methods are more efficient than those in geometrical registration, but they require great execution time. Regarding reduction in the execution time of iconic registration, the authors have proposed a new method based on mutual information while exploiting adaptive multiresolution decomposition, bidimensional empirical mode decomposition (BEMD) in its fast and adaptive version fast and adaptive BEMD (FABEMD). The idea is that instead of registering two images, the authors proceed to registration of the bidimensional intrinsic mode functions (BIMFs) that results from the FABEMD decomposition. The BIMF selected by the authors' algorithm is characterised by preservation of the general form of the image, and it contains a tone of grey levels lower than that of the original image, thus the number of combinations of the grey levels, used while calculating entropy is reduced, which in turn reduces execution time of the registration.

Journal ArticleDOI
Shuyuan Yang1, Wang Xiuxiu1, Min Wang, Yue Han1, Licheng Jiao1 
TL;DR: A new semi-supervised low-rank representation graph for pattern recognition is proposed using the calculated LRR coefficients of both labelled and unlabelled samples as the graph weights, established in a parameter-free manner under the framework of semi- supervised learning.
Abstract: In this study, the authors propose a new semi-supervised low-rank representation graph for pattern recognition. A collection of samples is jointly coded by the recently developed low-rank representation (LRR), which better captures the global structure of data and implements more robust subspace segmentation from corrupted samples. By using the calculated LRR coefficients of both labelled and unlabelled samples as the graph weights, a low-rank representation graph is established in a parameter-free manner under the framework of semi-supervised learning. Some experiments are taken on the benchmark database to investigate the performance of the proposed method and the results show that it is superior to other related semi-supervised graphs.

Journal ArticleDOI
TL;DR: This study proposes a pixel-wise skin colour detection method based on the flexible neural tree (FNT) without considering the problem of selecting a suitable colour space and achieves state of the art performance in skin pixel classification and better performance in terms of accuracy and FPRs.
Abstract: Skin colour detection plays an important role in image processing and computer vision. Selection of a suitable colour space is one key issue. The question that which colour space is most appropriate for pixel-wise skin colour detection is not yet concluded. In this study, a pixel-wise skin colour detection method is proposed based on the flexible neural tree (FNT) without considering the problem of selecting a suitable colour space. A FNT-based skin model is constructed by using large skin data sets which identifies the important components of colour spaces automatically. Experimental results show improved accuracy and false positive rates (FPRs). The structure and parameters of FNT are optimised via genetic programming and particle swarm optimisation algorithms, respectively. In the experiments, nine FNT skin models are constructed and evaluated on features extracted from RGB, YCbCr, HSV and CIE-Lab colour spaces. The Compaq and ECU datasets are used for constructing FNT-based skin model and evaluating its performance compared with other skin detection methods. Without extra processing steps, the authors method achieves state of the art performance in skin pixel classification and better performance in terms of accuracy and FPRs.

Journal ArticleDOI
TL;DR: An efficient image fusion framework for multi-focus images is proposed based on compressed sensing, and the dual-channel pulse coupled neural network model is used in the image sampling part as an important weighting factor in the fusion scheme.
Abstract: In this study, an efficient image fusion framework for multi-focus images is proposed based on compressed sensing. The new fusion framework consists of three parts: image sampling, measurement fusion and image reconstruction. First, the dual-channel pulse coupled neural network model is used in the image sampling part as an important weighting factor in the fusion scheme. Second, the result from the measurement fusion part is reconstructed through a new reconstruction algorithm called self-adaptively modified Landwebber filter. Finally, computer simulation-based experiment is conducted, showing that the novel fusion framework is capable of saving computational resource and enhancing the fusion result and is easy to implement.