Mammogram enhancement is a key step to detect breast cancer using digital mammogram. The present study investigates mesh-free radial basis function (RBF) collocation method to solve linear diffusion equation for image enhancement of mammograms. The proposed algorithm is compared with the mesh-based finite difference method as well as other existing enhancement methods such as unsharp masking, histogram equalisation, and contrast limited adaptive histogram equalisation. Specifically, figure-of-merits with emphasis on image contrast and computational time are assessed and compared with different image processing techniques. The proposed algorithm has been applied towards the enhancement of all 322 sample mammogram images of Mini-Mammographic Image Analysis Society and randomly selected 300 sample images from Digital Database for Screening Mammography databases. Finally, mean and standard deviation of contrast improvement index and peak signal-to-noise ratio have been estimated and presented. The outcome of this study indicates that the mesh-free-based RBF collocation method proves to be a computationally efficient and valuable contrast enhancement technique in an area of mammography.

A technique based on Schur decomposition to supress the multiplicative (speckle) noise from medical ultrasound images is presented in this study. An image which carries the speckle noise is divided into small overlapping segments, size of these segments depends on the nature of speckle carried by the image and a global covariance matrix is calculated for the whole image by averaging the covariances of all segments. The global covariance matrix is decomposed through Schur decomposition to obtain the orthogonal vectors. A subset of these orthogonal vectors that correspond to largest magnitudes of eigenvalues are selected to filter out the speckle noise from the image. The proposed approach is compared with four benchmark filtering techniques, homomorphic wavelet despeckling, Wiener, Frost and Gamma. Two types of simulated ultrasound images and five types of real ultrasound images of foetal neck, left kidney, right kidney, musculo skeletal nerve and lymph node are tested. The proposed approach performed maximum suppression of speckle noise in all types of the images with optimal resolution and edge detection. The despeckling performance of the proposed approach is even better compared with the benchmark schemes once the speckle noise is rough, which is usually the case for soft tissue.

Colour vision deficiency (CVD) is a genetic condition that has troubled people for a long time. This study proposes an improved colour-to-grey method for CVD using image segmentation and a colour difference model. In this method, the colour image is first segmented using a region growing method so that each region corresponds to one colour. Next, the colour difference is computed between arbitrary segmented region pairs. Finally, the greyscale image is obtained by minimising a target function. Experimental results show that compared with state-of-the-art colour-to-grey methods, the proposed algorithm can improve the E-score by about 10.99%.

Cancer tissues in mammography images exhibit abnormal regions; it is of great clinical importance to label a mammography image as having cancerous regions or not, perform the corresponding image segmentation. However, the detailed annotation of the cancer region is often an ambiguous and challenging task. The authors describe a fully automatic computer-aided detection and diagnosis (CAD) system to detect and classify breast cancer as malignant or benign, by using mammography and building on the multiple-instance learning (MIL) algorithms, which has been confirmed beneficial for radiologist decision sustenance. Traditional learning methods require great effort to annotate the training data by costly manual labelling and specialised computational models to detect these annotations during the test. The proposed CAD system simultaneously performs pixel-level segmentation (suspicious versus normal tissue) and image-level classification (benign versus malignant image). The set-up of the proposed system is in order: automatically segmented regions of interest (ROIs). Then, features derived from ROIs detected such as textural features and shape features are selected and extracted from each region and combined them to classify ROIs as ‘benign’ or ‘malignant’, by implementing MIL algorithms. Experimental results demonstrate the efficiency and robustness of the proposed CAD system compared with previous work in the literature.

This study presents a fast intra-prediction algorithm for a high-profile H.264 encoder. First, a pre-decision algorithm is proposed to reject the impossible block size based on image variance. Then a fast 4 × 4 block prediction algorithm is proposed to select four possible modes from nine predicted modes based on the edge-filtering detection. With a hierarchical approach, the 8 × 8 block prediction is based on the result of the chosen 4 × 4 block mode. This approach selects only one to five modes of H.264 coding from nine prediction modes. Following the prediction of the 16 × 16 luminance block and 8 × 8 chrominance block is mapped by the result of the 8 × 8 luminance block by checking only one to two modes. The pre-decision algorithm, the fast 4 × 4, 8 × 8 and 16 × 16 block prediction algorithms can be combined to improve the coding speed. Simulations demonstrate that the proposed algorithm can save about 70% coding time at most for intra-frame coding in the H.264 system while increasing only about 1% bit-rate with a negligible peak signal-to-noise ratio drop.

Robust and reliable features with noise immunity, rotation-invariance, and low-dimensionality are the challenging aspects of pattern recognition. In this study, the authors presented a novel low-dimensional binary feature descriptor local diagonal Laplacian pattern (LDLP) for medical image registration. LDLP method is developed by defining the local relationship between a centre pixel and its diagonal neighbours and encoding it to a binary feature vector. The idea of centre-diagonal pixel correlation has drastically reduced the length of the feature vector without compromising the quality of local texture analysis. In the proposed work, first, the LDLP feature histograms of computed tomography (CT), magnetic resonance (MR), and ultrasound images are obtained. Further, these LDLP features of individual medical images are considered as target/fixed objects while their corresponding rotated and noisy features are considered as moving/floating objects to perform mono-modal rigid registration using an improved Procrustes analysis-based affine transform. The registration quality is examined by calculating the squared intensity error and the results are compared with the existing binary patterns such as local binary patterns, local tetra patterns, and local diagonal extrema patterns. The proposed LDLP feature descriptor-based rigid registration has attained relatively better performance in terms of registration accuracy and computational complexity.

For many image fusion problems, the most used technique is selecting features with rich information. The robust image fusion method based on block compressive sensing principle is studied here. Compressive sensing is known to provide an effective method with high accuracy. The framework of the proposed method is given in various perspectives: block sparse representations, restoration algorithms, feature extraction, online dictionary learning, and fusion rules. In terms of restoration of fused images, the split Bregman iteration is adopted. The proposed method can acquire well fusion image from source images and remove some degradations simultaneously, such as noises and blurring effect. In addition, both ‘maximum selection’ and ‘weighted mean’ are investigated as fusion rules, which can preserve more information. Generally, the proposed method can achieve better fusion result from the source images. The experiments with or without noise source images both illustrate that the proposed method has relatively comparative fusion results.

In Wyner–Ziv (WZ) video coding, side information (SI), which is a decoder estimation of the original frame, plays a key role in overall compression performance. Many researchers have focused on SI in the past decade to develop efficient SI generation algorithms. In this study, the authors propose an algorithm combined with naive Bayesian theory to create a generic model that can complete the generation of SI in the WZ video coding framework. The proposed scheme first utilises samples to build the initial model, after which the algorithm filters the samples and models according to the threshold . Then, the algorithm takes the filtered samples and models as conditions to build the generic model. Finally, the proposed scheme completes the generation of SI with the motion vectors obtained from the generated model. Experimental results show that the proposed algorithm achieves better rate-distortion performance and improves peak signal-to-noise ratio by up to 0.5 and 2 dB compared with state-of-the-art techniques.

The vanishing point is the converging point at which the road boundaries extend to the distance. It can be used to estimate the road region in a complicated environment. As the vanishing point detection algorithms for the unstructured road often take long time and they could not adapt to the image with complex environment of the road, in this study, the authors propose a vanishing point estimation method based on road boundaries region estimation. This method uses the boundary direction of the voting points in the border region to estimate the vanishing point by the line-soft-voting based on maximum weight. This method has fast calculation speed, and it can overcome the influence of the shadow and the complex environment on the surface of the road in many cases.

In this study, the perceptual video quality (PVQ) for the vogue 360-degree video with compression artefacts viewed on the visual reality (VR) head-mounted display (HMD) is obtained for the first time by an elaborately designed subjective experiment. The characteristic of the PVQ of omnidirectional (360-degree) video on the VR HMD and PC monitor is then investigated. The PVQ on the HMD is found to be linearly related to the video coding quality (VCQ) on the PC monitor. A quality evaluation model is then proposed based on the mapping formula and a new assessment parameter, where the impact of the video resolution and display device is involved. In this way, the traditional video quality assessment metrics for two-dimensional video can be extended to assess the PVQ of the 360-degree video viewed on the HMD. At last, the video structural similarity metric is taken as an example to predict the input of the proposed model, i.e. the VCQ of the 360-degree video. Experimental results demonstrate that the proposed model can effectively and conveniently solve the challenge of PVQ assessment for the 360-degree video with compression distortions on the HMD.

Beamlet transform has been widely used for extracting line features from images, which is an excellent multiscale geometric analysis method. However, it has a major drawback that it always performs too slowly due to very much redundant computation. In many application fields, the speed of the original beamlet transform is almost unbearable. To cure the problem, beamlet transform is improved by introducing geometrical flow, which utilises image semantic information in the process of generating beamlets. Besides, to further speed up the algorithm, interesting factor is presented to reduce recursively partitioned boxes. As a result, lots of computation time is saved. Experiments are conducted on various crack images and the results show that the proposed method runs significantly faster than the original beamlet transform. Cracks in an image are detected accurately. Moreover, the proposed method is robustly enough since the performance is hardly affected by crack shape and background texture.

Several diseases can be detected and diagnosed at a very early stage by observing changes in retinal blood vessel features. In order to detect these changes, the major step required is blood vessel segmentation. In this study, an effective method for the segmentation of blood vessels on coloured digital retinal images has been proposed. The proposed method uses linear combination of line detectors at varying scales along with multiple windows of different sizes. By implementing this technique, the drawbacks encountered in multi-scale line detection such as noise and false vessel detection around the optic disk are eliminated. The performance of the proposed method is evaluated on three publicly available datasets DRIVE, STARE and CHASE by considering sensitivity, specificity, accuracy, precision, false discovery rate, F1 score, Matthews correlation coefficient and G-mean. The results were analysed by comparing with most of the other earlier existing methods and have proven to achieve higher accuracy. It has also confirmed its effectiveness and robustness with high-resolution retinal images together with better simplicity and faster implementation for reliable blood vessel segmentation.

In this study, the authors propose a novel framework for top-down (TD) saliency detection, which is well suited to locate category-specific objects in natural images. Saliency value is defined as the probability of a target based on its visual feature. They introduce an effective coding strategy called locality constrained contextual coding (LCCC) that enforces locality and contextual constraints. Furthermore, a contextual pooling operation is presented to take advantages of feature contextual information. Benefiting from LCCC and contextual pooling, the obtained feature representation has high discriminative power, which makes the authors' saliency detection method achieving competitive results with existing saliency detection algorithms. They also include bottom-up cues into their framework to supplement the proposed TD saliency algorithm. Experimental results on three datasets (Graz-02, Weizmann Horse and PASCAL VOC 2007) show that the proposed framework outperforms state-of-the-art methods in terms of visual quality and accuracy.

The author proposes a robust face recognition algorithm called non-linear correlation filter bank (NCFB). NCFB combines the benefits of a sigmoid function such as non-linearities of image pixels and correlation filters (CFs) to achieve better recognition performance. The sigmoid function is used in the spatial domain to extend the uniform dynamic range for enhancing the image contrast. Greyscale images are divided into non-overlapping regions. CFs are designed based on the unconstrained minimum average correlation energy corresponding to each sub-region of images to optimise the overall correlation outputs. NCFB not only takes the differences among face sub-regions into account but also effectively exploits the discriminative information in face sub-regions. The author shows that the proposed method is robust against illumination, pose, and facial expression variations. Experimental results obtained on labelled faces in the wild, Yale B, AR, and FERET face databases demonstrate that the recognition rate in the proposed method is improved compared with other CFs.

Colour balancing is an image processing step employed in image signal processing pipeline to adjust colouration of images captured under different illuminations. Most of the existing colour balancing methods that make use of human faces and facial features use skin colour to estimate the chromaticity of the illuminant. This study examines how colour balancing can be performed exploiting the sclera colour extracted from the face automatically detected in the image. Sclera colour can provide enough and correct information to estimate the scene illuminant and reliably perform automatic colour balancing for face images. Experimental results suggest that, in terms of accuracy, the proposed method outperforms most other colour constancy methods on the experimental dataset collected as part of this research, which is a significant result.

Randomised visual secret sharing is an encryption technique that utilises block-based progressive visual secret sharing and discrete cosine transform (DCT) based reversible data embedding technique to recover a secret image. The recovery method is based on progressive visual secret sharing, which recovers the secret image block by block. The existing block based schemes achieve the highest contrast level of 50% for noise-like and meaningful shares. The proposed scheme achieves a contrast level of 70–90% for noise-like and 70–80% for meaningful shares. The enhancement of contrast is achieved by embedding additional information in the shares using DCT-based reversible data embedding technique. Experimental results showed that the proposed scheme restores the secret image with better visual quality in terms of human visual system based parameters.

The gyrator transform is a linear canonical transform, which generates the rotation of an optical signal in position-spatial frequency planes. Gyrator wavelet transform is a relatively newer optical information processing tool obtained by combining the gyrator transform with the wavelet transform. This combination provides multi-resolution analysis of an image which is twisted in spatial frequency planes. The proposed tool satisfies basic algebraic properties, such as the linearity property and Parseval's theorem. Considering the usefulness of this tool, here a study of features, applications, and implementation of the gyrator wavelet transform is presented. This work studies the features of the gyrator wavelet transform, which can find a role in different applications such as edge enhancement, image encryption, image hiding, and watermarking.

Line detection in handwritten documents is an important problem for processing of scanned documents. While existing approaches mainly use hand-designed features or heuristic rules to estimate the location of text lines, the authors present a novel approach that trains a fully convolutional network (FCN) to predict text line structure in document images. A rough estimation of text line, or a line map, is obtained by using FCN, from which text strings that pass through characters in each text line are constructed. Finally, the touching characters should be separated and assigned to different text lines to complete the segmentation, for which line adjacency graph is used. Experimental results on ICDAR2013 Handwritten Segmentation Contest data set show high performance together with the robustness of the system with different types of languages and multi-skewed text lines.

The authors propose a general framework to accelerate the universal histogram-based image contrast enhancement (CE) algorithms. Both spatial and grey-level selective downsampling of digital images are adopted to decrease computational cost, while the visual quality of enhanced images is still preserved and without apparent degradation. Mapping function calibration is proposed to reconstruct the pixel mapping on the grey levels missed by downsampling. As two case studies, the accelerations of histogram equalisation (HE) and the state-of-the-art global CE algorithm, i.e. spatial mutual information and PageRank (SMIRANK), are presented in detail. Both quantitative and qualitative assessment results have verified the effectiveness of their proposed CE acceleration framework. In typical tests, the computational efficiencies of HE and SMIRANK have been increased by about 3.9 and 13.5 times, respectively.

This study is based on improving the visual quality of the images captured under different illumination conditions, i.e. overexposed and underexposed. This study presents a fuzzy image enhancement process based on a finite fuzzy set which is defined to optimise entropy, noise, intensity and edge information. In the proposed fuzzy approach, the overexposed and underexposed images are mapped to form a fuzzy set using membership functions. In the fuzzification process, the degree of belonging of each input to an appropriate fuzzy membership is calculated with respect to intensity, entropy, edge information and background noise. Therefore, the proposed method preserves the details of the image. Indeed, the fuzzy systems are well suited to model the uncertainty that occurs when conflicting operations are performed. Some effective approaches can enhance the image data without increasing noise. However, their ability to reduce the noise during the sharpening process is limited. The proposed method enhances the image by controlling sharpness parameter which affects the visual quality of the image. Both qualitative and quantitative assessments are performed to evaluate the performance of the proposed algorithm.