Information Of Neighboring Pixels Research Articles

Novel modified kernel fuzzy c-means algorithm used for cotton leaf spot detection

Image segmentation is a significant and difficult subject that is a prerequisite for both basic image analysis and sophisticated picture interpretation. In image analysis, picture segmentation is crucial. Several different applications, including those related to medicine, facial identification, Cotton disease diagnosis, and map object detection, benefit from image segmentation. In order to segment images, the clustering approach is used. The two types of clustering algorithms are Crisp and Fuzzy. Crisp clustering is superior to fuzzy clustering. Fuzzy clustering uses the well-known FCM approach to enhance the results of picture segmentation. KFCM technique for image segmentation can be utilized to overcome FCM’s shortcomings in noisy and nonlinear separable images. In the KFCM approach, the Gaussian kernel function transforms high-dimensional, nonlinearly separable data into linearly separable data before applying FCM to the data. KFCM is enhancing noisy picture segmentation results. KFCM increases the accuracy rate but ignores neighboring pixels. The Modified Kernel Fuzzy C-Means approach is employed to get over this problem. The NMKFCM approach enhances picture segmentation results by including neighboring pixel information into the objective function. This suggested technique is used to find “blackarm” spots on cotton leaves. A fungal leaf disease called “blackarm” leaf spot results in brown leaves with purple borders. The bacterium can harm cotton plants, causing angular leaf blotches that range in color from red to brown.

Transmission Line Segmentation Solutions for UAV Aerial Photography Based on Improved UNet

The accurate and efficient detection of power lines and towers in aerial drone images with complex backgrounds is crucial for the safety of power grid operations and low-altitude drone flights. In this paper, we propose a new method that enhances the deep learning segmentation model UNet algorithm called TLSUNet. We enhance the UNet algorithm by using a lightweight backbone structure to extract the features and then reconstructing them with contextual information features. In this network model, to reduce its parameters and computational complexity, we adopt DFC-GhostNet (Dubbed Full Connected) as the backbone feature extraction network, which is composed of the DFC-GhostBottleneck structure and uses asymmetric convolution to capture long-distance targets in transmission lines, thus enhancing the model’s extraction capability. Additionally, we design a hybrid feature extraction module based on convolution and a transformer to refine deep semantic features and improve the model’s ability to locate towers and transmission lines in complex environments. Finally, we adopt the up-sampling operator CARAFE (Content-Aware Re-Assembly of FEature) to improve segmentation accuracy by enhancing target restoration using contextual neighborhood pixel information correlation under feature decoding. Our experiments on public aerial photography datasets demonstrate that the improved model requires only 8.3% of the original model’s computational effort and has only 21.4% of the original model’s parameters, while achieving a reduction in inference speed delay by 0.012 s. The segmentation metrics also showed significant improvements, with the mIOU improving from 79.75% to 86.46% and the mDice improving from 87.83% to 92.40%. These results confirm the effectiveness of our proposed method.

Correlation between Blood Oxygen Level-Dependent Magnetic Resonance Imaging Images and Prognosis of Patients with Multicenter Diabetic Nephropathy on account of Artificial Intelligence Segmentation Algorithm.

This study was aimed to analyze the correlation between blood oxygen level-dependent magnetic resonance imaging (BOLD-MRI) images and prognosis of patients with diabetic nephropathy (DN) based on artificial intelligence (AI) segmentation algorithm, so as to provide references for diagnosis and treatment as well as prognosis analysis of patients DN. In this study, a kernel function-based fuzzy C-means algorithm (KFCM) model was proposed, and the FCM algorithm based on neighborhood pixel information (BCFCM) and the FCM algorithm based on efficiency improvement (EnFCM) were introduced for comparison to analyze the image segmentation effects of three algorithms. The results showed that the partition coefficient (Vpc) and partition entropy (Vpe) of the KFCM algorithm were 0.801 and 0.602, respectively, which were better than those of the traditional FCM, BCFCM, and EnFCM algorithm. At the same time, the effects of correlation between renal cortex R2∗ (RC-R2∗), renal medulla R2∗ (RM-R2∗), renal cortex D (RC-D), renal medulla D (RM-D) and renal function on the prognosis were compared. The results showed that the correlation coefficients between RC-R2∗, RM-R2∗, RC-D, RM-D and renal function were 0.57, 0.62, 0.49, and 0.38, respectively; among them, RC-R2∗ and RM-R2∗ were negatively correlated to the estimated glomerular filtration rate (eGFR), and the difference between the groups was statistically significant (P <0.05). Among the factors affecting the prognosis of DN patients, the GFR, hemoglobin (Hb), RC-R2∗, RM-R2∗, and RC-D were all related to the prognosis of DN, and the difference between groups was statistically obvious (P <0.05). It suggested that the KFCM algorithm proposed in this study showed the relatively best segmentation effect on BOLD-MRI images for DN patients; an increase in R2∗ indicated a poor prognosis, and an increase in the RC-D value indicated a better prognosis.

Two-Dimensional and Three-Dimensional Time-of-Flight Secondary Ion Mass Spectrometry Image Feature Extraction Using a Spatially Aware Convolutional Autoencoder.

Feature extraction algorithms are an important class of unsupervised methods used to reduce data dimensionality. They have been applied extensively for time-of-flight secondary ion mass spectrometry (ToF-SIMS) imaging─commonly, matrix factorization (MF) techniques such as principal component analysis have been used. A limitation of MF is the assumption of linearity, which is generally not accurate for ToF-SIMS data. Recently, nonlinear autoencoders have been shown to outperform MF techniques for ToF-SIMS image feature extraction. However, another limitation of most feature extraction methods (including autoencoders) that is particularly important for hyperspectral data is that they do not consider spatial information. To address this limitation, we describe the application of the convolutional autoencoder (CNNAE) to hyperspectral ToF-SIMS imaging data. The CNNAE is an artificial neural network developed specifically for hyperspectral data that uses convolutional layers for image encoding, thereby explicitly incorporating pixel neighborhood information. We compared the performance of the CNNAE with other common feature extraction algorithms for two biological ToF-SIMS imaging data sets. We investigated the extracted features and used the dimensionality-reduced data to train additional ML algorithms. By converting two-dimensional convolutional layers to three-dimensional (3D), we also showed how the CNNAE can be extended to 3D ToF-SIMS images. In general, the CNNAE produced features with significantly higher contrast and autocorrelation than other techniques. Furthermore, histologically recognizable features in the data were more accurately represented. The extension of the CNNAE to 3D data also provided an important proof of principle for the analysis of more complex 3D data sets.

Quantum Statistical Information Grid Clustering for Early Esophageal Adenocarcinoma Detection

Recent advances in the field of digital endoscopy have recognized as a primary key knowledge for medical screening of presence of diseases at its earlier stages and minimal invasive surgery. Many research works are done on automatic analyzing and detection of early esophageal adenocarcinoma which is not easy to detect at its primary stage. Because the esophageal images are naturally indeterministic and it is uncertain to detect its earliest appearance more precisely at its right stage of diagnosis. Thus, in this present research work the statistical information-based grid clustering is developed by empowering its clustering capability using Quantum mechanism. The conventional STatistical INformation Grid Clustering (STING) reduces the computation complexity of the clustering process, but outlier detection and uncertainty handling are very challenging, because it partitions the Eshophageal image in the layer by layer levels. Each layer is divided into cells and they are known as child cells. The relevant child cells alone are used to determine the statistical information about the entire image and based on the spatial information the similarity measure among two images are determined. The distance measure and the neighborhood pixel information are computing using quantum theory to overcome the uncertainty and parallel processing is done for concurrency based early esophageal adenocarcinoma prediction. The Barret’s Esophageal images are used for clustering the cancerous and noncancerous images. The simulation results proved that the proposed Quantum STatistical INformation Grid Clustering produce better result in detection of Early Esophageal Adenocarcinoma detection compared to other standard clustering models.

A Novel Kernelized Total Bregman Divergence-Driven Possibilistic Fuzzy Clustering With Multiple Information Constraints for Image Segmentation

Aiming at the problem that existing robust fuzzy clustering algorithms are still sensitive to high noise, a total Bregman divergence-driven possibilistic fuzzy clustering with multiple information constraints and kernel metric (TSKFLICM) is proposed in this article. First, we introduce total Bregman divergence (TBD) to overcome the shortcoming that Bregman divergence is variant with rotation. Second, polynomial kernel function is used to kernelize TBD, and kernelized TBD is embedded with neighborhood information of pixels to further enhance its ability to suppress noise. Finally, kernelized TBD with spatial information constraints is combined with possibilistic typicality to construct the novel objective function of possibilistic fuzzy clustering, and a TBD-driven kernel possibilistic fuzzy clustering with multiple information constraints is obtained through optimization theory. The effectiveness of the proposed algorithm for noisy image segmentation is explained by means of sample weighted clustering method. Experimental results show that compared with other algorithms, the Jaccard score, segmentation accuracy, and peak signal-to-noise ratio of the proposed algorithm are improved by 0.017–0.481, 1.327%–41.260%, and 2.416–11.765, respectively. Therefore, the TSKFLICM algorithm has better segmentation performance and stronger antinoise ability than the existing state-of-the-art fuzzy clustering algorithm.

An Automatic High Confidence Sets Selection Strategy for SAR Images Change Detection

Change detection result is usually obtained by clustering or classifying; however, the spatial information of pixels is rarely considered during the classification process. In this letter, we propose a practical method to improve the performance of existing change detection algorithms on remote-sensing images without prior information. First, the existing detection result is regarded as an initial result. Second, it takes advantage of this initial result with neighborhood information of pixels to select the training data, then a random forest classifier is trained for precise classification. Finally, the median filtering is used to eliminate singular points for further improvement of detection performance. Corresponding experiments on three real synthetic aperture radar (SAR) data sets demonstrate the effectiveness of the proposed method.

Handling non-linearity between classes using spectral and spatial information with kernel based modified possibilistic c-means classifier

In this research work, non-linearity in data has been handled by incorporating kernel with the Modified Possibilistic c-Means (MPCM) algorithm. Nine different types of kernel function have been proposed to classify nine different classes and have non-linearity among them. Gaussian has been identified as the best performing kernel at an optimized fuzzified value m = 1.5 with an overall accuracy 92.45%. The composite kernels have been generated with an aim of improvement of accuracy in comparison to single kernel. Further, role of spatial constraints has been analyzed by adding neighboring pixel information to handle the noise. It was observed that overall accuracy depends on the spatial parameter that has been included. Thus, local information having local similarity measure parameters (Sir)in the image produces highest accuracy compared to others. Moreover, the identified best kernel (Gaussian Kernel) has been then used for extraction of the burnt paddy fields in a different test site.

Change Detection in SAR Images Using Multiobjective Optimization and Ensemble Strategy

This letter puts forward a new algorithm, ensemble strategy multiobjective fuzzy clustering method (ESMOFCM). To fully combine the gray information and spatial information of neighbor pixels, a new dividing fluctuant parameter is proposed for producing a difference image. Then, we use a frame based on multiobjective fuzzy clustering to alleviate the contradiction between removing noise and preserving details in images. Ensemble strategy is adopted to integrate all Pareto optimal solutions. The experimental results show that the proposed algorithm is superior to comparison algorithms.

Multifeature-Based Discriminative Label Consistent K-SVD for Hyperspectral Image Classification

Given the chaotic background and complex content of hyperspectral images (HSIs), the complementary information of multiple features is beneficial for HSI classification. Many multifeature-based sparse representation methods have been recently proposed. However, the large-scale dictionary problem and the optimal multifeature combination strategy have remained unsolved. For the aforementioned problem, we propose a multifeature-based discriminative label consistent K-singular value decomposition (MF-LC-KSVD) algorithm for HSI classification. In the training step of the approach, a multifeature dictionary and a combined linear classifier are obtained by jointly utilizing the LC-KSVD algorithm on the extracted features. The multifeature classifier can automatically determine the relative importance of different features for classification. The “discriminative sparse-code error” constraint in the LC-KSVD facilitates the sharing of the same spare pattern of the atoms in a special feature from the same class, thereby increasing the discrimination of the linear classifier. In the testing step, a multifeature sparse matrix is obtained by introducing the above overcomplete multifeature dictionary into multifeature-based adaptive sparse representation. The class label is then predicted by applying the classifier on multifeature sparse codes. In addition, we introduce the shape-adaptive spatial region to incorporate the information of neighbor pixels, hence further improving the classification performance. Compared with other multifeature-based sparse representation methods, our proposed MF-LC-KSVD is proven to have better classification accuracy.

Image Segmentation using Improved Imperialist Competitive Algorithm and a Simple Post-processing

Image segmentation is a fundamental step in many of image processing applications. In most cases the image’s pixels are clustered only based on the pixels’ intensity or color information and neither spatial nor neighborhood information of pixels is used in the clustering process. Considering the importance of including spatial information of pixels which improves the quality of image segmentation, and using the information of the neighboring pixels, causes enhancing of the accuracy of segmentation. In this paper the idea of combining the K-means algorithm and the Improved Imperialist Competitive algorithm is proposed. Also before applying the hybrid algorithm, a new image is created and then the hybrid algorithm is employed. Finally, a simple post-processing is applied on the clustered image. Comparing the results of the proposed method on different images, with other methods, shows that in most cases, the accuracy of the NLICA algorithm is better than the other methods.

Edge-Based Demosaicking Method Using Uncorrelatedness With Sensors for CFA

This paper presents a multiple edge detection by computing uncorrelatedness of the neighboring pixels in four locations: up, down, left, and right. To recover missing G in R and missing G in B, we use the derived weightings and the pixel contributions from the neighboring pixel information. When demosaicking the R and B arrays, an interpolation is used for the recovery of the missing R in B and missing B in R. The experimental results show that the proposed overall system outperforms the existing works. The proposed work is especially better than the state-of-the-art method by 1.23 dB in composite peak signal-to-noise ratio (CPSNR) and by −0.15 in a Spatial Extension to the CIE L*a*b* DeltaE Color Difference Metric (S-CIELAB), the lower the better, averaged over a standard image dataset.

A level set method for brain MR image segmentation under asymmetric distributions

Magnetic resonance (MR) image segmentation plays an essential role for brain disease diagnosis; however, suffered from low contrast, intensity inhomogeneity, noise and asymmetry of the intensity distribution, segmentation methods are always difficult to achieve satisfactory results. In this paper, we propose a novel level set method for brain MR image segmentation with consideration of these problems. We firstly generate a new region descriptor based on asymmetric Gaussian distributions in order to fit different shapes of observed nonsymmetric data. Secondly, we utilize the spatial distance and intensity similarity information of neighborhood pixels to extract local anisotropic spatial information to balance the noise reduction and detail preservation. After that, the extracted information and bias field information are combined to improve the asymmetric region descriptor utilized in the level set framework. Finally, we define a maximum likelihood energy functional on the whole image, integrating the local anisotropic spatial information, the bias field information and the asymmetric distributions. The experimental results on synthetic and clinical images demonstrated that our method can achieve desirable performance in spite of the severe noise and intensity inhomogeneity.

Deep learned Inter-Channel Colored Texture Pattern: a new chromatic-texture descriptor

Texture is a dominant tool for feature extraction. Incorporation of inter-channel chromatic information along with the texture feature will improve the accuracy of feature extraction. This paper provides deep learned Inter-Channel Colored Texture Pattern which gives the inter-channel chromatic texture information of an image. The information is extracted individually from the co-occurrent pixel values of various channels. It affords the unique channel-wise information and its relation with neighboring pixel information of opponent space. Deep learning with convolutional neural network is applied for learning the feature based on color and texture. The experiments for content-based image retrieval are carried out on three different databases which vary in nature: CIFAR-10 dataset (DB1) (Krizhevsky in Learning multiple layers of features from tiny images, University of Toronto, 2009), Corel database (DB2) (Corel 1000 and Corel 10000 image database, http://wang.ist.psu.edu/docs/related.shtml) and Facescrub dataset (DB3) (Ng and Winkler in 2014 IEEE international conference on image processing (ICIP), pp 343–347, 2014). Facescrub dataset is used for face recognition. The experimental analysis by applying this descriptor provides considerable improvement from the previous works for content-based image retrieval and face recognition.

Robust superpixels using color and contour features along linear path

Superpixel decomposition methods are widely used in computer vision and image processing applications. By grouping homogeneous pixels, the accuracy can be increased and the decrease of the number of elements to process can drastically reduce the computational burden. For most superpixel methods, a trade-off is computed between 1) color homogeneity, 2) adherence to the image contours and 3) shape regularity of the decomposition. In this paper, we propose a framework that jointly enforces all these aspects and provides accurate and regular Superpixels with Contour Adherence using Linear Path (SCALP). During the decomposition, we propose to consider color features along the linear path between the pixel and the corresponding superpixel barycenter. A contour prior is also used to prevent the crossing of image boundaries when associating a pixel to a superpixel. Finally, in order to improve the decomposition accuracy and the robustness to noise, we propose to integrate the pixel neighborhood information, while preserving the same computational complexity. SCALP is extensively evaluated on standard segmentation dataset, and the obtained results outperform the ones of the state-of-the-art methods. SCALP is also extended for supervoxel decomposition on MRI images.

A new method to quantify surface urban heat island intensity

Reliable quantification of urban heat island (UHI) can contribute to the effective evaluation of potential heat risk. Traditional methods for the quantification of UHI intensity (UHII) using pairs-measurements are sensitive to the choice of stations or grids. In order to get rid of the limitation of urban/rural divisions, this paper proposes a new approach to quantify surface UHII (SUHII) using the relationship between MODIS land surface temperature (LST) and impervious surface areas (ISA). Given the footprint of LST measurement, the ISA was regionalized to include the information of neighborhood pixels using a Kernel Density Estimation (KDE) method. Considering the footprint improves the LST-ISA relationship. The LST shows highly positive correlation with the KDE regionalized ISA (ISAKDE). The linear functions of LST are well fitted by the ISAKDE in both annual and daily scales for the city of Berlin. The slope of the linear function represents the increase in LST from the natural surface in rural regions to the impervious surface in urban regions, and is defined as SUHII in this study. The calculated SUHII show high values in summer and during the day than in winter and at night. The new method is also verified using finer resolution Landset data, and the results further prove its reliability.

Classification of visible and infrared hyperspectral images based on image segmentation and edge-preserving filtering

The classification of hyperspectral images with a few labeled samples is a major challenge which is difficult to meet unless some spatial characteristics can be exploited. In this study, we proposed a novel spectral-spatial hyperspectral image classification method that exploited spatial autocorrelation of hyperspectral images. First, image segmentation is performed on the hyperspectral image to assign each pixel to a homogeneous region. Second, the visible and infrared bands of hyperspectral image are partitioned into multiple subsets of adjacent bands, and each subset is merged into one band. Recursive edge-preserving filtering is performed on each merged band which utilizes the spectral information of neighborhood pixels. Third, the resulting spectral and spatial feature band set is classified using the SVM classifier. Finally, bilateral filtering is performed to remove “salt-and-pepper” noise in the classification result. To preserve the spatial structure of hyperspectral image, edge-preserving filtering is applied independently before and after the classification process. Experimental results on different hyperspectral images prove that the proposed spectral-spatial classification approach is robust and offers more classification accuracy than state-of-the-art methods when the number of labeled samples is small.

Improved quantum dilation and erosion operations

To reduce the time complexity of quantum morphology operations, two kinds of improved quantum dilation and erosion operations are proposed. Quantum parallelism is well used in the design of these operations. Consequently, the time complexity is greatly reduced compared with the previous quantum dilation and erosion operations. The neighborhood information of each pixel is needed in the process of designing quantum dilation and erosion operations. In order to get the neighborhood information, quantum position shifting transformation is utilized, which can make the neighborhood information store in a quantum image set. In this image set, the neighborhood information of pixel at location ([Formula: see text], [Formula: see text]) is stored at the same location ([Formula: see text], [Formula: see text]) of other images in the image set. All the pixels will be processed simultaneously, which is the performance of quantum parallelism. The time complexity analysis shows that these quantum operations have polynomial-time complexity which is much lower than the exponential-time complexity of the previous version.

An Optimization Clustering Algorithm Based on Texture Feature Fusion for Color Image Segmentation

We introduce a multi-feature optimization clustering algorithm for color image segmentation. The local binary pattern, the mean of the min-max difference, and the color components are combined as feature vectors to describe the magnitude change of grey value and the contrastive information of neighbor pixels. In clustering stage, it gets the initial clustering center and avoids getting into local optimization by adding mutation operator of genetic algorithm to particle swarm optimization. Compared with well-known methods, the proposed method has an overall better segmentation performance and can segment image more accurately by evaluating the ratio of misclassification.

Quality Enhancement of Video Denoising Algorithm with Combined Effect of Different Views

An unwanted factor in digital images and videos called as Noise is responsible for hiding the details and destroying image information. Hence denoising has great importance in the detail restoration and to improve the quality measures. A simple adaptive median filter (SAMF) is one of the most promising algorithm capable of denoising the videos to better extent, but incapable to use all the neighboring pixel information while noise processing and hence quality of the denoised video can be further improved if all neighboring pixel information is considered. To make this possible the SAMF is combined with the multi-view denoising andthen a fusion strategy is used to generate enhanced denoised video sequence. The performance of the combined system is measured through the image quality matrix called as Pick Signal to Noise Ratio (PSNR) at different noise contamination level.