Neighboring Pixels Research Articles

Scale and pattern adaptive local binary pattern for texture classification

Local binary pattern (LBP) with a fixed sampling template is sensitive to scale changes. Furthermore, under rotation changes or noise corruptions, one uniform LBP pattern can be corrupted to fall into a non-uniform pattern which loses its discrimination power to describe the corresponding texture feature. To overcome these two main drawbacks, we propose a scale and pattern adaptive local binary pattern (SPALBP). Firstly, in the gradient-based sampling radius adaptive scheme, eight directional adaptive sampling radius of each center pixel can be obtained by using its eight Kirsch gradient values. Secondly, in the noise and rotation robust neighborhood sampling scheme, three neighborhood sampling templates are used to extract three kinds of averaging neighborhood pixels. Thirdly, for each center pixel, three kinds of LBPriu2 patterns can be extracted by sampling these three kinds of averaging neighborhood pixels along eight directional adaptive sampling radius. Finally, an optimal SPALBP uniform pattern can be adaptively selected from these three LBPriu2 patterns. Hence, all SPALBP patterns show more robustness against scale changes, rotation changes and noise corruptions. Extensive experiments are conducted on four standard texture databases: Outex, UIUC, CUReT and XU_HR. Comparing with state-of-the-art LBP-based variants, the proposed SPALBP method consistently shows superior performance both in dramatic environment changes and high-levels of noise conditions, meanwhile it maintains a lower texture feature dimension.

Color Image Recovery Using Generalized Matrix Completion over Higher-Order Finite Dimensional Algebra

To improve the accuracy of color image completion with missing entries, we present a recovery method based on generalized higher-order scalars. We extend the traditional second-order matrix model to a more comprehensive higher-order matrix equivalent, called the “t-matrix” model, which incorporates a pixel neighborhood expansion strategy to characterize the local pixel constraints. This “t-matrix” model is then used to extend some commonly used matrix and tensor completion algorithms to their higher-order versions. We perform extensive experiments on various algorithms using simulated data and publicly available images. The results show that our generalized matrix completion model and the corresponding algorithm compare favorably with their lower-order tensor and conventional matrix counterparts.

Separable and reversible data hiding scheme for medical images using modified Logistic and interpolation

The interpolation technique (IT) is a fundamental tool for image processing and is commonly utilized. Various IT-based reversible data hiding (RDH) schemes for encrypted medical images have been proposed in recent years. However, these schemes have encountered issues such as simplistic encryption, low embedding rate, or incomplete separation. A high-capacity IT-based separable RDH scheme for medical images is proposed to address these issues. First, the original Logistic map is modified by adding extra parameters to increase the complexity of the key. Additionally, an encryption method via bit reorganization and diffusion is presented to encrypt the original image. Second, an improved interpolation method based on the neighbor pixel mean is proposed to interpolate the encrypted (ciphertext) image to generate a cover (interpolated) image for embedding the data. Finally, a new data embedding method is developed using the modulo-operation congruence theorem. Experimental results showed that the modified Logistic map exhibits excellent chaotic characteristics, the metrics of the proposed encryption method are close to the theoretical values, and the proposed data hiding method acquires high embedding capacity and image quality. Furthermore, the proposed scheme is a fully reversible and separable technique that achieves superior performance in comparison to various IT-based encrypted RDH schemes.

Gene expression extraction in cervical cancer by segmentation of microarray images using a novel fuzzy method

ABSTRACT It is necessary to obtain gene expression values to identify gene biomarkers involved in all types of cancers, and microarray data is one of the best data for this purpose. In order to extract gene expression values from microarray images that have different challenges. This article presents a completely automatic and comprehensive method that can deal with the various challenges in these images and obtain gene expression values with high accuracy. A pre-processing approach is proposed for contrast enhancement using a genetic algorithm and for removing noise and artefacts in microarray cells using wavelet transform based on a complex Gaussian scaling model. For each point, the coordinate centre is determined using Self Organising Maps. Then, using a new hybrid model based on the Fuzzy Local Information Gaussian Mixture Model (FLIGMM), the position of each spot is accurately determined. In this model, various features are obtained using local information about pixels, considering the pixel neighbourhood correlation coefficient. Finally, the gene expression values are obtained. The performance of the proposed algorithm was evaluated using real microarray images of cervical cancer from the GMRCL microarray dataset as well as simulated images. The results show that the proposed algorithm achieves 90.91% and 98% accuracy in segmenting microarray spots for noiseless and noisy spots, respectively.

A robust watermarking approach against high‐density salt and pepper noise (RWSPN) to enhance medical image security

AbstractThis paper proposes a robust watermarking method against high‐density salt and pepper noise attacks. Automatic region of interest (ROI) detection, embedding encoded data, removing different densities of noise, data extraction by omitting, and labeling the noisy pixels of Region of Non‐Interest (RONI), and decoding the extracted data using ROI pixel information as a key, are various steps of the presented scheme. The automatic ROI detection method separates the RONI from ROI with four vertices of the smallest rectangle, for the embedding process. The encoded watermark data is embedded into the least significant bits of RONI in four neighbour pixels. Adaptive Removal of high‐density Salt and pepper Noise method can enhance image quality and reduce the effect of salt and pepper noise attacks. The embedded information is preserved from destruction if the host image is impaired through the power of robustness. The best results are obtained through the action of extracting the watermark from RONI pixels, utilizing the same ROI detection method. Omitting and labeling the noisy pixels of the RONI will ensure healthy extracted watermark data, leading to decreased Bit Error Rate (BER) values. Finally, these data are interpreted using the key of ROI pixels, and the watermark data is decoded and retrieved. Due to salt and pepper noise obliterating pixel bits and their corresponding transform coefficients in the transform domain, the spatial domain is employed to enhance robustness against such attacks. The results show the high performance of the presented scheme. The average BER value for five MRI databases in a 97% salt and pepper noise attack is 38.6.

Statistically unbiased prediction enables accurate denoising of voltage imaging data

Here we report SUPPORT (statistically unbiased prediction utilizing spatiotemporal information in imaging data), a self-supervised learning method for removing Poisson–Gaussian noise in voltage imaging data. SUPPORT is based on the insight that a pixel value in voltage imaging data is highly dependent on its spatiotemporal neighboring pixels, even when its temporally adjacent frames alone do not provide useful information for statistical prediction. Such dependency is captured and used by a convolutional neural network with a spatiotemporal blind spot to accurately denoise voltage imaging data in which the existence of the action potential in a time frame cannot be inferred by the information in other frames. Through simulations and experiments, we show that SUPPORT enables precise denoising of voltage imaging data and other types of microscopy image while preserving the underlying dynamics within the scene.

Denoising of Nifti (MRI) Images with a Regularized Neighborhood Pixel Similarity Wavelet Algorithm.

The recovery of semantics from corrupted images is a significant challenge in image processing. Noise can obscure features, interfere with accurate analysis, and bias results. To address this issue, the Regularized Neighborhood Pixel Similarity Wavelet algorithm (PixSimWave) was developed for denoising Nifti (magnetic resonance imaging (MRI)). The PixSimWave algorithm uses regularized pixel similarity detection to improve the accuracy of noise reduction by creating patches to analyze the intensity of pixels and locate matching pixels, as well as adaptive neighborhood filtering to estimate noisy pixel values by allocating each pixel a weight based on its similarity. The wavelet transform breaks down the image into scales and orientations, allowing a sparse image representation to allocate a soft threshold on its similarity to the original pixels. The proposed method was evaluated on simulated and raw T1w MRIs, outperforming other methods in terms of an SSIM value of 0.9908 for a low Rician noise level of 3% and 0.9881 for a high noise level of 17%. The addition of Gaussian noise improved PSNR and SSIM, with the results indicating that the proposed method outperformed other models while preserving edges and textures. In summary, the PixSimWave algorithm is a viable noise-elimination approach that employs both sparse wavelet coefficients and regularized similarity with decreased computation time, improving the accuracy of noise reduction in images.

Heart sounds classification: Application of a new CyTex inspired method and deep convolutional neural network with transfer learning

Analysis of heart sounds is an effective means for the early diagnosis of cardiac pathologies. Heart sound classification is a challenging multi-disciplinary field that attracts many machine learning researchers. This paper proposes a new CyTex-inspired transform to convert heart sound signals to textured images. In our proposed method, the neighboring pixels have meaningful relationships that result in semi-periodic patterns in the output image. This method has two significant benefits. Firstly, this makes it possible to apply deep convolutional neural networks (DCNN) to heart sound classification. Consequently, correlative moving masks of the convolutional layers can extract short-term and long-term information from these images in vertical and horizontal directions. Secondly, by converting the heart sound signal to images as a compatible input for DCNNs, we can employ a transfer learning scheme to reduce the risk of overfitting. The performance of four popular pre-trained DCNNs – AlexNet, VGG16, InceptionV3, and ResNet50 – has been tested. Furthermore, data augmentation, hyper-parameter optimization, and drop-out techniques are employed. The performance of the proposed system is verified on the heart sounds dataset PhysioNet. Results were obtained using cross-validation techniques. Our experiments demonstrate the potential of our proposed method for achieving excellent performance compared to previous methods on the same dataset with a score of over 0.9200 at a sensitivity of 0.8775 and specificity of 0.9637 using the ResNet with data augmentation, hyperparameter optimization, and dropout techniques.

Deep Slice-Crossed Network With Local Weighted Loss for Brain Metastases Segmentation

Cognitive deficits occur in up to 90% of patients with brain metastases, can be caused by the tumor itself and whole brain radiation therapy. Latest treatment options to reduce cognitive decline require high-precision metastases segmentation. This asks existing metastases segmentation models to be further improved as their limited ability to micro lesion perception. To reduce the segmentation error on brain tissues and improve the accuracy on micro metastases, a deep slice-crossed network and a local weighted loss are proposed, respectively. The slice-crossed network contains a gated feature fusion module where the "gate" is learned individually from the slice-crossed label to roughly localize metastases. Then in tumor regions, this "gate" allows intra-slice information to pass for metastases enhancement, while in other regions, it allows inter-slice information to pass for vascular screening. The local weighted loss is proposed to address the inconsistency in size of intra-class objects. Unlike existing weighting approaches, it calculates the weight of each pixel from its neighbourhood pixel distribution to enhance the learning of pixels within small tumours, which can be applied to common losses. To evaluate them, two datasets containing 1000 and 368 patients, respectively, were collated. Experimental results demonstrate that the proposed method perform satisfactorily compared with state-of-the-art brain metastasis segmentation models.

A Second-Order Method for Removing Mixed Noise from Remote Sensing Images.

Remote sensing image denoising is of great significance for the subsequent use and research of images. Gaussian noise and salt-and-pepper noise are prevalent noises in images. Contemporary denoising algorithms often exhibit limitations when addressing such mixed noise scenarios, manifesting in suboptimal denoising outcomes and the potential blurring of image edges subsequent to the denoising process. To address the above problems, a second-order removal method for mixed noise in remote sensing images was proposed. In the first stage of the method, dilated convolution was introduced into the DnCNN (denoising convolutional neural network) network framework to increase the receptive field of the network, so that more feature information could be extracted from remote sensing images. Meanwhile, a DropoutLayer was introduced after the deep convolution layer to build the noise reduction model to prevent the network from overfitting and to simplify the training difficulty, and then the model was used to perform the preliminary noise reduction on the images. To further improve the image quality of the preliminary denoising results, effectively remove the salt-and-pepper noise in the mixed noise, and preserve more image edge details and texture features, the proposed method employed a second stage on the basis of adaptive median filtering. In this second stage, the median value in the original filter window median was replaced by the nearest neighbor pixel weighted median, so that the preliminary noise reduction result was subjected to secondary processing, and the final denoising result of the mixed noise of the remote sensing image was obtained. In order to verify the feasibility and effectiveness of the algorithm, the remote sensing image denoising experiments and denoised image edge detection experiments were carried out in this paper. When the experimental results are analyzed through subjective visual assessment, images denoised using the proposed method exhibit clearer and more natural details, and they effectively retain edge and texture features. In terms of objective evaluation, the performance of different denoising algorithms is compared using metrics such as mean square error (MSE), peak signal-to-noise ratio (PSNR), and mean structural similarity index (MSSIM). The experimental outcomes indicate that the proposed method for denoising mixed noise in remote sensing images outperforms traditional denoising techniques, achieving a clearer image restoration effect.

WELDP: Weighed Edge Local Directional Pattern for expression recognition from facial images

At present, the local appearance-based texture descriptors in Facial Expression Recognition have limited accuracy due to the inability to encode the discriminative edges. The major cause is the presence of distorted and weak edges due to noise. Hence, this paper proposes new Expression Descriptor called as Weighted Edge Local Directional Pattern (WELDP) which can discriminate the weak and strong edges. Unlike the conventional local descriptors, WELDP searches for the support of neighbor pixels in the determination of Facial expression attributes such as Edges, Corners, Lines, and Curved Edges. WELDP encodes only Strong edge responses and discards weaker edge responses after extracting them through edge detection masks. This work adapted two masks for edge detection: they are Robinson Compass Mask and Kirsch Compass Mask. Moreover, the WELDP aims at code redundancy and encode each pixel only with seven bits (one sign bit and six directional bits). Then the WELDP image is described by a histogram and then processed through SVM (Support Vector Machine) for expression identification. From the simulation experiments, the proposed WELDP is found as better than several existing methods.

Water index and Swin Transformer Ensemble (WISTE) for water body extraction from multispectral remote sensing images

ABSTRACT Automatic surface water body mapping using remote sensing technology is greatly meaningful for studying inland water dynamics at regional to global scales. Convolutional neural networks (CNN) have become an efficient semantic segmentation technique for the interpretation of remote sensing images. However, the receptive field value of a CNN is restricted by the convolutional kernel size because the network only focuses on local features. The Swin Transformer has recently demonstrated its outstanding performance in computer vision tasks, and it could be useful for processing multispectral remote sensing images. In this article, a Water Index and Swin Transformer Ensemble (WISTE) method for automatic water body extraction is proposed. First, a dual-branch encoder architecture is designed for the Swin Transformer, aggregating the global semantic information and pixel neighbor relationships captured by fully convolutional networks (FCN) and multihead self-attention. Second, to prevent the Swin Transformer from ignoring multispectral information, we construct a prediction map ensemble module. The predictions of the Swin Transformer and the Normalized Difference Water Index (NDWI) are combined by a Bayesian averaging strategy. Finally, the experimental results obtained on two distinct datasets demonstrate that the WISTE has advantages over other segmentation methods and achieves the best results. The method proposed in this study can be used for improving regional to continental surface water mapping and related hydrological studies.

Analysis of the adjacency effect on retrieval of land surface temperatures based on multimodal images from unmanned aerial vehicles

Land surface temperatures (LSTs) critically govern urban thermal environments. While algorithms have been proposed to retrieve LSTs from high-spatial-resolution images derived from unmanned aerial vehicles, efforts to explore urban geometry and adjacency effects on such retrieved LSTs are faced with challenges. In this study, a new urban radiative transfer model was proposed, which incorporated the emitted radiance from a target pixel and the atmosphere, the scattered radiance of the target pixel itself and its neighboring pixels, and the reflected atmospheric downwelling radiance. Based on the model and UAV-derived orthophotos, urban LSTs that considered the contributions of the surroundings were accurately retrieved. Depending on the emissivity and the surroundings of the target pixel, the magnitude of the adjacency effect on retrieved LSTs almost varied from 0.0 K to 3.0 K. Validation based on in-situ LSTs demonstrated that the absolute biases between the retrieved and measured temperatures were below 1.0 K. These findings have collectively underlined the necessity to consider the adjacency effect for the retrieval of urban LSTs from high-spatial-resolution images.

The role of textural parameters of industrial core CT scan images in detecting the petrophysical characteristics of carbonate reservoirs, Permian Dalan Formation, the central Persian Gulf

Digital petrophysics investigates the properties of rocks from images, especially core computed tomography (CT scan). The purpose of these investigations is to develop new methods for petrophysical evaluation of porous materials. In this article, textural parameters have been calculated from computed tomography images of the cores in Permian Dalan Formation in the central Persian Gulf. We tried to find more evidence that industrial CT scan images are useful in identifying the geological and petrophysical characteristics of hydrocarbon reservoirs. For this purpose, the textural parameters of the image, including contrast, correlation, homogeneity, energy and entropy were calculated and analyzed and a gray level co-occurrence matrix has been created. These parameters were compared with geological and petrophysical data obtained from laboratory measurements and thin section studies. Analysis of the thin sections under the microscope led to the identification of 12 microfacies. They range from mudstone to wackestone, packstone and grainstone. Some samples have been completely dolomitized and recognition of their primary microfacies is not possible. This group called crystalline carbonate. Results showed that various features in CT scan images can be differentiated using the arrangement of pixels, the gray intensity of each pixel and the relationship of each pixel to its neighboring pixels. Increasing porosity and permeability reduces the image heterogeneity. This is also the case for uniformly distributed pore types, including moldic and intercrystalline. Textural parameters were also compared with microfacies and diagenetic processes. Results indicate that they can increase heterogeneity with decreasing reservoir quality and vice versa. Finally, using numerical values of image textural parameters, three petrophysical classes were defined in the studied reservoir. As a result, various parts of the reservoir can be identified using CT scan images of the cores.

A spatially correlated fractional integral-based method for denoising geiger-mode avalanche photodiode light detection and ranging depth images

Geiger-mode avalanche photodiode (GM-APD) light detection and ranging (LiDAR) target echo signals are susceptible to interference from atmospheric backscatter, daylight, and other noise, and extracted target depth images contain a large amount of anomalous noise. Accordingly, this paper devises a method based on a spatially correlated fractional integral for denoising GM-APD LiDAR depth images. First, a multi-scale superpixel fusion algorithm is employed to perform null-pixel complementation on a target depth image extracted using histogram statistics. Next, a pixel neighborhood spatial correlation kernel function is used to optimize the Grünwald–Letnikov fractional integral operator to correct the large amount of anomalous noise and thus achieve GM-APD depth image denoising. Simulation and experimental results demonstrate that the denoising performance of the algorithm on GM-APD LiDAR depth images is significantly better than that of median filtering and bilateral filtering, with at least 22.8 % and 4.8 % improvements in the target reduction degree (K) and peak signal-to-noise ratio (PSNR), respectively. In addition, the K and PSNR reach 91.36 % and 18.0241 dB, respectively, with 25 statistical frames in an outdoor imaging experiment. This demonstrates that the algorithm can effectively denoise GM-APD LiDAR depth images with few statistical frames and thus improve the frame rate of GM-APD LiDAR imaging.

Circular shift combination local binary pattern (CSC-LBP) method for dorsal finger crease classification

Biometric technology has drawn increasing attention and significance importance in recent years. In biometric security systems, personal identification and verification rely on their physical, behavioral, and biological characteristics. In this study, a new hand-based modality called dorsal finger creases is proposed for biometric classification. This modality is located on the dorsal surface of the finger, between the proximal knuckle and distal knuckle of the finger. However, it requires a specific feature extraction approach to extract the modality information on the selected region. Therefore, we have proposed a method for extracting the underlying features of the dorsal finger creases, called circular shift combination local binary pattern (CSC-LBP). The concept of CSC-LBP is to compute the local binary pattern within a 3 × 3 spatial window for each neighborhood pixel separately. Further, the concept of combination approach is applied on the individually computed eight LBP values to obtain the more discriminative feature vector. A multiclass support vector machine classifier is used for evaluating the effectiveness of the proposed CSC-LBP operator. Extensive experiments on self-collected datasets demonstrate the high classification accuracy and effectiveness of the proposed CSC-LBP method and confirm the usefulness of dorsal finger creases for personal recognition.

A Study on Perception of Visual–Tactile and Color–Texture Features of Footwear Leather for Symmetric Shoes

The study applies Kansei engineering in analyzing the color and texture of leather footwear, utilizing neural network verification to mirror consumers’ visual and tactile imageries onto varieties of leather. This aids in the development of an advanced system for selecting leather footwear based on such impressions. Initially, representative word pairs denoting consumers’ visual and tactile perceptions of leather footwear were delineated. Post-evaluation of these perceptions through a sensibility assessment questionnaire was administered, using 54 samples of leather footwear provided by manufacturers, with each leather type codified in terms of visual and tactile sensibilities. Subsequently, a customized software algorithm was crafted to isolate the primary color and adhesiveness as color features from the leather sample images. Analyzing grayscale values of the images and using pixel neighborhood as a base, the associated calculation methods, such as LBP, SCOV, VAR, SAC, etc., were proposed to extract texture features from the images. The derived color and texture feature values were used as the input layer and the sensory vocabulary quantified values as the output layer. Backpropagation neural network training was conducted on 49 leather samples, with five leather samples used for testing, culminating in the verification of neural network training for three types and 17 combinations. The outcome was an optimal method for leather footwear Kansei engineering and neural network training, establishing a design process for leather footwear characteristics assisted by sensory vocabulary and a backpropagation neural network. Additionally, a computer-aided system for selecting leather footwear, based on these impressions, was designed and validated through footwear design. This study utilized symmetry in footwear design. By using the design of a single shoe to represent the imagery of a pair of symmetrical shoes, we verified whether the leather samples recommended by the leather imagery selection query system met the expected system input settings.

Coarse2Fine: Local Consistency Aware Re-prediction for Weakly Supervised Object Localization

Weakly supervised object localization aims to localize objects of interest by using only image-level labels. Existing methods generally segment activation map by threshold to obtain mask and generate bounding box. However, the activation map is locally inconsistent, i.e., similar neighboring pixels of the same object are not equally activated, which leads to the blurred boundary issue: the localization result is sensitive to the threshold, and the mask obtained directly from the activation map loses the fine contours of the object, making it difficult to obtain a tight bounding box. In this paper, we introduce the Local Consistency Aware Re-prediction (LCAR) framework, which aims to recover the complete fine object mask from locally inconsistent activation map and hence obtain a tight bounding box. To this end, we propose the self-guided re-prediction module (SGRM), which employs a novel superpixel aggregation network to replace the post-processing of threshold segmentation. In order to derive more reliable pseudo label from the activation map to supervise the SGRM, we further design an affinity refinement module (ARM) that utilizes the original image feature to better align the activation map with the image appearance, and design a self-distillation CAM (SD-CAM) to alleviate the locator dependence on saliency. Experiments demonstrate that our LCAR outperforms the state-of-the-art on both the CUB-200-2011 and ILSVRC datasets, achieving 95.89% and 70.72% of GT-Know localization accuracy, respectively.

Similarity-Driven Fine-Tuning Methods for Regularization Parameter Optimization in PET Image Reconstruction.

We present an adaptive method for fine-tuning hyperparameters in edge-preserving regularization for PET image reconstruction. For edge-preserving regularization, in addition to the smoothing parameter that balances data fidelity and regularization, one or more control parameters are typically incorporated to adjust the sensitivity of edge preservation by modifying the shape of the penalty function. Although there have been efforts to develop automated methods for tuning the hyperparameters in regularized PET reconstruction, the majority of these methods primarily focus on the smoothing parameter. However, it is challenging to obtain high-quality images without appropriately selecting the control parameters that adjust the edge preservation sensitivity. In this work, we propose a method to precisely tune the hyperparameters, which are initially set with a fixed value for the entire image, either manually or using an automated approach. Our core strategy involves adaptively adjusting the control parameter at each pixel, taking into account the degree of patch similarities calculated from the previous iteration within the pixel's neighborhood that is being updated. This approach allows our new method to integrate with a wide range of existing parameter-tuning techniques for edge-preserving regularization. Experimental results demonstrate that our proposed method effectively enhances the overall reconstruction accuracy across multiple image quality metrics, including peak signal-to-noise ratio, structural similarity, visual information fidelity, mean absolute error, root-mean-square error, and mean percentage error.

Multi-color complex spatial light modulation with a single digital micromirror device.

Spatial light modulators enabling complex light field manipulation has opened up many opportunities in biomedical imaging, holographic display, and adaptive optics. However, traditional spatial light modulators do not allow multi-color operations simultaneously due to their physical constraints, while multi-color modulations are highly desirable in many applications. To overcome this limitation, we demonstrate a multi-color spatial complex light field modulation with a single binary hologram on digital micromirror devices (DMD). This method combines several neighboring micro-mirror pixels into a giant single superpixel, in which the light field's amplitude and phase can be individually determined by internal pixel combinations, and the dynamic range of phase modulation can exceed 2π for the single wavelength. As a result, this extra phase modulation range offers an additional degree of freedom for independent multi-wavelength light modulation. Based on this scheme, multi-color light modulations have been demonstrated in a 2D plane as well as in multiple 3D holographic planes. Moreover, a dual-colored Airy beam has been realized using the same technique. These results bring complex light modulation into a multi-color regime, paving the way for practical applications in information display, imaging, and optical trapping.