Lung field defines a region-of-interest in which specific radiologic signs such as septal lines, pulmonary opacities, cavities, consolidations, and lung nodules are searched by a chest radiographic computer-aided diagnostic system. Thus, its precise segmentation is extremely important. To precisely segment it, numerous methods have been developed during the last four decades. However, no exclusive survey consolidating the advancements in these methods has been presented till date, thus indicating a void and the need. This study fills the void by presenting a comprehensive survey of these methods with a focus on their underlying principle, the dataset used, reported performance, and relative merits and demerits. It refrains from doing a hard comparative evaluation by bringing all of them on a common platform, since the datasets used in their development and testing are of varied quality, complexity, and are not publicly available. It also provides a glimpse of deep learning, the present state of deep-learning-based lung field segmentation methods, expectations from it, and the challenges ahead of it.

Removing random valued impulse noise (RVIN) is a challenging task in corrupted images. This article aims to study some detection and filtering algorithms which remove RVIN in images. In addition to some state-of-the-art detection and filtering algorithms, a new detection technique, measures of dispersion (MOD) algorithm, for removing very high-density RVIN proposed by authors is also compared with existing methods. In the detection stage, rank order absolute difference, rank order logarithmic difference, adaptive switching median, triangle-based linear interpolation, and MOD algorithms are considered. Median filter, fuzzy switching median filter, and fuzzy switching weighted median filter are used for filtering followed by the detection algorithms. Comparative studies in terms of peak signal-to-noise ratio and structural similarity have been devised to evaluate the performance of various filtering schemes.

In order to deal with facial occlusion effectively, the authors propose a powerful but simple face representation method, called adaptive Weberfaces (AdapWeber), based on human visual perception change model and the Weber ratio R implied in Weber's law. Specifically, human perception is naturally highly selective and robust to occlusions, and the Weber ratio R is very important to enhance feature redundancy. As feature redundancy and locality are two guiding principles against facial occlusion, they further develop eight variants of AdapWeber, collectively referred to as single-scale and single-orientation (SSSO) AdapWeber, by shrinking the kernel locality and varying the kernel orientation of the original AdapWeber, and integrate them to formulate a multi-scale and multi-orientation (MSMO) AdapWeber. A natural by-product of MSMO AdapWeber is MSMO Weberfaces. Experiments on four benchmark databases, including Extended Yale B, AR, UMB-DB, and LFW, showed that MSMO AdapWeber/Weberfaces, rather than any variant of SSSO AdapWeber/Weberfaces, outperformed several popular feature extraction approaches in many scenarios, especially when the occlusion level is very high or the image dimension is very low. This result demonstrates that several occlusion-weak features can be combined together to construct an occlusion-robust feature.

Intensity inhomogeneity is one of the major obstacles for intensity-based segmentation in many applications. The recently proposed kernel mapping (KM) method has exhibited excellent performance on segmenting various types of noisy images while it is not effective to handle intensity inhomogeneity. To overcome this drawback, this study presents a localised KM (LKM) method based on the fact that intensity inhomogeneity can be ignored in a local neighbourhood. The authors’ method first reconstructs the KM formulation of image segmentation in a neighbourhood of each pixel, and then such formulations for all pixels can be integrated together to derive the LKM energy functional. Minimisation of the energy functional is implemented by solving an equivalent convex-relaxed problem whose optimisation can be quickly achieved via the split Bregman method. Experimental results on two-phase segmentation and multiphase segmentation demonstrate competitive performance of the LKM method in the presence of intensity inhomogeneity and severe noise.

Magnifying micro-movements from natural video has recently been investigated by several computer vision researchers, due to its impact in numerous applications. In this study, the authors analyse video signals and try to magnify micro-movements/vibrations to make them visible. These micro-movements are typically undetectable and cannot be seen by basic human vision. They utilise complex wavelets to analyse sequential frames and detect any minor change in object's spatial position. They magnify some specific complex wavelet frequency bands by a multiplication factor and reconstruct back the video signal after some manipulation and modification to make these micro-movements seen and observable. They compare their work with recent techniques in micro-motion magnification (Freeman et al.) and try to show the merits of each technique. These micro-movements can later be utilised in different applications such as medical imaging, structural engineering, mechanical engineering, physical feature analysis and industrial engineering, as will be seen in their experiments.

The bag of visual words (BOW) model has been widely applied in the field of image recognition and image classification. However, all scale-invariant feature transform (SIFT) features are clustered to construct the visual words which result in a substantial loss of discriminative power for the visual words. The corresponding visual phrases will further render the generated BOW histogram sparse. In this study, the authors aim to improve the classification accuracy by extracting high discriminative SIFT features and feature pairs. First, high discriminative SIFT features are extracted with the within- and between-class correlation coefficients. Second, the high discriminative SIFT feature pairs are selected by using minimum spanning tree and its total cost. Next, high discriminative SIFT features and feature pairs are exploited to construct the visual word dictionary and visual phrase dictionary, respectively, which are concatenated to a joint histogram with different weights. Compared with the state-of-the-art BOW-based methods, the experimental results on Caltech 101 dataset show that the proposed method has higher classification accuracy.

This study presents a lossless robust data hiding scheme based on significance-bit-difference expansion. The original cover image can be recovered without any distortion after the hidden data have been extracted if the stego image remains intact, on the other hand, the hidden data can be robust against unintentional changes applying to the stego image, such as image compression and sometimes unavoidable addition of random noise which is below a certain level and does not change the content of an image. The proposed scheme decomposes pixels in a cover image into two parts, that is, the higher significant bits (HSB) and the least significant bits (LSB), and calculates the HSB difference between adjacent pixels. Bits are embedded into HSBs by shifting the HSB difference value histogram bins. The shift and shifting rule are fixed for all HSB difference values, and reversibility is achieved. Furthermore, owing to the separation of HSBs and LSBs, minor alteration applying to the stego image generated by non-malicious attacks such as Joint Photographic Experts Group (JPEG) compression, which will not change the HSB values as well as the HSB difference values, and robustness is achieved. Experimental results show that, compared with previous works, the performance of the proposed scheme is significantly improved.

In the field of dentistry, prospective clinical study reports affirm the need for approximate growth analysis of endodontic tooth post treatment. There is no difference in the frequency, appearance or extent of root resorption in the teeth. It is necessary to elucidate the role of endodontic treatment in the root resorption. Differences between the two samples (radiographs), which are taken with specified period of intervals, in terms of the frequency of growth changes in treated teeth is needed to observe accurately. This study mainly aims at this requirement by utilising slightly modified region-based growing active contour model for quantitative growth analysis of tooth. Recall radiographs of endodontic regeneration involving immature permanent teeth with pulp necrosis have been considered as input in this research. Image enhancing techniques such as dilation and erosion of mathematical morphology are then performed sequentially to emphasise the outlying pixels. Finally, the criterions which include the root length, apical diameter and the dentinal wall thickness are calibrated and given in experimental results. The visual sample results and along with its measurements proved the efficiency of the proposed algorithm.

In this study, the authors present a secured transfer method for medical images, using smartphone, based on a proposed images encryption algorithm using the matrix product and the exclusive addition. The novelty of this study is to propose a low-complexity encryption algorithm running in real time on embedded system. Experimental results demonstrate that the proposed encryption method can achieve high security with a good performance.

A novel bitrate model with low complexity is proposed for perceived compression distortion assessment of mobile video with low resolution, which is extremely useful in intermediate network nodes for quality monitoring. Without fully decoding, parameters are extracted by bitstream analysing, such as bitrate, frame type, quantisation parameter, DCT coefficient, motion vector. Bitrate is regarded as an essential parameter meanwhile the bitrate–MOS curve is determined by video content. Respectively, spatial factor is estimated using quantisation parameter and DCT coefficient and temporal factor is estimated using motion vector. Apart from bitrate, the spatial and temporal factors, which reflect the characteristic of video content, are considered in the proposed model to obtain a more accurate evaluation. Experimental results show that the overall performance of proposed model significantly outperforms that of the other five bitrate models in terms of widely used performance criteria, including the Pearson correlation coefficient (PCC), the Spearman rank-order correlation coefficient (SROCC), the root-mean-squared error (RMSE) and the outlier ratio (OR).

High-resolution fingerprint identification system (HRFIS) has become a hot topic in the field of academic research. Compared to traditional automatic fingerprint identification system, HRFIS reduces the risk of being faked by using level 3 features, such as pores, which cannot be detected in lower resolution images. However, there is a serious problem in HRFIS: there are hundreds of sweat pores in one fingerprint image, which will spend a considerable amount of time for direct fingerprint matching. The authors propose a method to match pores in two fingerprint images based on deterministic annealing algorithm. In this method, fingerprints are aligned using singular points. Then minutiae are matched based on the alignment result. To reduce the impact of deformation, they build a convex hull for each of these fingerprints. Pores in these convex hulls are used for matching. In the experiments, their method is compared with random sample consensus method, minutia and ICP-based method, and direct pore matching method. The results show that the proposed method is more efficient.

Image fusion is a process to enhance the human perception of different images from the same scene. Nowadays, two popular methods in the signal/image fusion, namely, multi-scale transform (MST) and sparse representation (SR) are being used. This study uses an image energy approach to enhance a fusion rule based on the combination of MST and SR methods. Each source image is first decomposed to its sub-bands using the selected MST method. Then, SR is applied to the low-pass band and maximum absolute (max-abs) rule merges the high-pass bands. The activity level of the sparse coefficients is measured based on the energy differences of the source images. When the gap energy is high enough, a coefficient with maximum L ₂-norm is selected; otherwise, maximum L ₁-norm is considered. Finally, by applying inverse MST to the attained bands, the fused image is reconstructed. The popular MSTs, such as discrete wavelet transform, dual-tree complex wavelet transform and non-sub-sampled contourlet are used. The experiments are carried out on several standard and real-life images. The measurement results confirm that the proposed method has enhanced the contrast, clarity and visual information of the fused results.

This study proposes a supervised orthogonal discriminant projection (SODP) based on double adjacency graphs (DAGs). SODP based on DAG (SODP-DAG) aims to minimise the local within-class scatter and simultaneously maximise both the local between-class scatter and the non-local scatter, where the local between-class scatter and the local within-class scatter are constructed by applying the DAG structure. By doing so, SODP-DAG can keep the local within-class structure for original data and find the optimal discriminant directions effectively. Moreover, four schemes are designed for constructing weight matrices in SODP-DAG. To validate the performance of SODP-DAG, the authors compared it with orthogonal discriminant projection, SODP and others on several publicly available datasets. Experimental results show the feasibility and effectiveness of SODP-DAG.

This study describes improved partial differential equation (PDE)-based formulations for combined global and local contrast operators for underwater image enhancement. The algorithms remove the limitations of conventional closed-form approaches and the problem of optimal stopping time of earlier PDE-based approaches. Main features include improved simultaneous combination, augmentation and control of various individual local and global processes, guided by optimisation of multiple image metrics. This ensures optimal operation of the algorithms in terms of visual and numerical results and proposed approaches ensure faster and fully automated processing of various images. Additional contributions include the incorporation of a colour space converter, fuzzy homomorphic and post-contrast enhancement processes for certain problematic images. Experimental comparisons indicate that the improved approaches yield better results than several of the proposed works from the literature for underwater image enhancement.

Facial retouching has been increasingly applied in current social media and entertainment industries. In this study, the authors propose an efficient approach to automatically detect and retouch the facial flaws by using discriminative structure tensor. First, a non-linear structure tensor associated with saliency model is exploited to discriminatively and automatically detect the significant facial flaws. Then, a Gaussian skin model is constructed in YCbCr space and the OSTU operation is simultaneously utilised to precisely mark the facial skin regions, in which the mouth, eyebrows and nostril parts are excluded. Subsequently, diverse structure tensor is employed to discriminatively adjust the inpainting priority and propose a structure tensor-based inpainting algorithm to retouch the detected flaws. Without manual intervention, the extensive experiments have shown its effectiveness in marking the freckles, blemishes and moles in face images, and the retouching performance is visually pleasing in comparison with state-of-the-art counterparts.

Saliency-based marker-controlled watershed method was proposed to detect and segment phytoplankton cells from microscopic images of non-setae species. This method first improved IG saliency detection method by combining saturation feature with colour and luminance feature to detect cells from microscopic images uniformly and then produced effective internal and external markers by removing various specific noises in microscopic images for efficient performance of watershed segmentation automatically. The authors built the first benchmark dataset for cell detection and segmentation, including 240 microscopic images across multiple phytoplankton species with pixel-wise cell regions labelled by a taxonomist, to evaluate their method. They compared their cell detection method with seven popular saliency detection methods and their cell segmentation method with six commonly used segmentation methods. The quantitative comparison validates that their method performs better on cell detection in terms of robustness and uniformity and cell segmentation in terms of accuracy and completeness. The qualitative results show that their improved saliency detection method can detect and highlight all cells, and the following marker selection scheme can remove the corner noise caused by illumination, the small noise caused by specks, and debris, as well as deal with blurred edges.

Structured light systems have become an effective tool for reconstructing three-dimensional models of objects due to the advent of low-price, high-speed depth cameras such as Kinect. However, this kind of active depth sensor extracts low-quality depth maps because of its inaccurate image matching process. This study proposes a depth extraction method based on image rectification for accurate image matching. Due to the sizes of the projected patterns and the captured images are usually different, a virtual camera is defined, through which the rectified images are generated to match the images in the real camera at pixel level. Experiments on simulated and hardware platforms demonstrate that the proposed method achieves efficient rectification and obtains better-quality depth maps.

As a significant tool, finite mixture models (FMMs) have been widely used for image segmentation. However, there are two problems with standard FMMs: first, the conditional probability is sensitive to outliers. Second, the robustness to image noise is inadequate. In this study, the authors present a novel hierarchical Student's-t MM (HSMM), which includes standard FMMs as a sub-problem. Additionally, to incorporate more image spatial information, they apply a mean template not only to the prior/posterior probability, but also to the sub-conditional distribution. Thus, their HSMM is more robust to outliers and image noise owing to the spatial constraints from the mean template. In the standard SMM, a t-distribution is used to calculate the conditional probability. In this study, the authors present a novel hierarchical student's-t mixture model (HSMM), which includes the standard FMM as a sub-problem. Finally, though they use Student's-t-distribution to solve the image segment problems of this study, their HSMM achieves excellent performance, is elastic and can encompass any other model that is based on FMMs. Experimental results demonstrate that their proposed method is robust and effective.

Saliency detection has shown a great role in many image processing applications. This study introduces a new Bayesian framework for saliency detection. In this framework, image saliency is computed as product of three saliencies: location-based, feature-based and centre-surround saliencies. Each of these saliencies is estimated using statistical approaches. The centre-surround saliency is estimated using Dirichlet process mixture model. The authors evaluate their method using five different databases and it is shown that it outperform state-of-the-art methods. Also, they show that the proposed method has a low computational cost.

A three-dimensional (3D) representation of the linear structures in a breast has been constructed by utilising information of the ridges in the craniocaudal (CC) and the mediolateral oblique (MLO) mammographic views of the breast. Blood vessels and ducts appear as ridges in the mammogram. The position and shape of the ridges in the breast are an indicator of malignancy. In the first stage of the proposed 3D reconstruction problem, an algorithm has been developed to find out which linear structure in the CC view and a linear structure in the MLO view correspond to the same 3D structure in the breast. The 3D view of the linear structures is constructed from the abovementioned correspondences. The positional error (per unit length of the reconstructed linear structure) between the manual reconstruction and the algorithmic reconstruction of a linear structure turns out to be better by 20% than a competing approach.