Bidimensional Intrinsic Mode Functions Research Articles

Selection of the Discriming Feature Using the BEMD’s BIMF for Classification of Breast Cancer Mammography Image

Mammogram exam images are useful in identifying diseases, such as breast cancer, which is one of the deadliest cancers, affecting adult women around the world. Computational image analysis and machine learning techniques can help experts identify abnormalities in these images. In this work we present a new system to help diagnose and analyze breast mammogram images. To do this, the system a method the Selection of the Most Discriminant Attributes of the images preprocessed by BEMD “SMDA-BEMD”, this entails picking the most pertinent traits from the collection of variables that characterize the state under study. A reduction of attribute based on a transformation of the data also called an extraction of characteristics by extracting the Haralick attributes from the Co-occurrence Matrices Methods “GLCM” this reduction which consists of replacing the initial set of data by a new reduced set, constructed at from the initial set of features extracted by images decomposed using Bidimensional Empirical Multimodal Decomposition “BEMD”, for discrimination of breast mammogram images (healthy and pathology) using BEMD. This decomposition makes it possible to decompose an image into several Bidimensional Intrinsic Mode Functions “BIMFs” modes and a residue. The results obtained show that mammographic images can be represented in a relatively short space by selecting the most discriminating features based on a supervised method where they can be differentiated with high reliability between healthy mammographic images and pathologies, However, certain aspects and findings demonstrate how successful the suggested strategy is to detect the tumor. A BEMD technique is used as preprocessing on mammographic images. This suggested methodology makes it possible to obtain consistent results and establishes the discrimination threshold for mammography images (healthy and pathological), the classification rate is improved (98.6%) compared to existing cutting-edge techniques in the field. This approach is tested and validated on mammographic medical images from the Kenitra-Morocco reproductive health reference center (CRSRKM) which contains breast mammographic images of normal and pathological cases.

A novel fusion method for X-ray phase contrast imaging based on fast adaptive bidimensional empirical mode decomposition.

X-ray phase contrast imaging (XPCI) can separate the attenuation, refraction, and scattering signals of the object. The application of image fusion enables the concentration of distinctive information into a single image. Some methods have been applied in XPCI field, but wavelet-based decomposition approaches often result in loss of original data. To explore the application value of a novel image fusion method for XPCI system and computed tomography (CT) system. The means of fast adaptive bidimensional empirical mode decomposition (FABEMD) is considered for image decomposition to avoid unnecessary information loss. A parameter δ is proposed to guide the fusion of bidimensional intrinsic mode functions which contain high-frequency information, using a pulse coupled neural network with morphological gradients (MGPCNN). The residual images are fused by the energy attribute fusion strategy. Image preprocessing and enhancement are performed on the result to ensure its quality. The effectiveness of other image fusion methods has been compared, such as discrete wavelet transforms and anisotropic diffusion fusion. The δ-guided FABEMD-MGPCNN method achieved either the first or second position in objective evaluation metrics with biological samples, as compared to other image fusion methods. Moreover, comparisons are made with other fusion methods used for XPCI. Finally, the proposed method applied in CT show expected results to retain the feature information. The proposed δ-guided FABEMD-MGPCNN method shows potential feasibility and superiority over traditional and recent image fusion methods for X-ray differential phase contrast imaging and computed tomography systems.

Noise suppression in the reconstructed image of digital holography based on the BEMDV method using improved particle swarm optimization.

In digital holography, the speckle noise caused by the coherent nature of the light source and the light scattering generated by the light path system degrade the quality of the reconstructed image seriously. Therefore, in this paper, we propose what we believe to be is a novel noise reduction method combining bidimensional empirical mode decomposition (BEMD) with the variational method, termed BEMDV. The reconstructed image is first decomposed into a series of bidimensional intrinsic mode function (BIMF) components with different frequencies using the BEMD method, and then a certain number of BIMF components are selected for noise reduction by the variational method. An improved particle swarm optimization algorithm is adopted to optimize the key parameters of the proposed method, so as to further improve its noise reduction performance. A reflective off-axis digital holographic imaging system is used to collect the holograms of the coin and optical resolution plate, and the experimental research on noise reduction is carried out. The results with qualitative and quantitative analyses show that the proposed method achieves a better performance on noise reduction and detail preservation than other general methods, enormously enhancing the image quality of holographic reconstruction.

Empirical mode decomposition and power spectrum filtering for detection of frequency channels related to multi-scale geochemical anomalies: Metal exploration targeting in Moalleman district, NE Iran

Geochemical anomaly patterns for metal exploration targeting usually reveal non-stationarity due mainly to the non-linear synthesis of ore-forming processes. The spectrum–area (S–A) multifractal filtering and the bidimensional empirical mode decomposition (BEMD) are robust methodologies for detecting geochemical anomalies with different scaling properties. The former portrays the generalized scale invariance characteristics of a geochemical image in the two-dimensional Fourier frequency domain. It relies on estimating scaling exponents of power-law functions in the spectral energy density plane to design filter functions that amplify a geochemical signal in specific frequency channels. The BEMD decomposes a geochemical image into a number of bidimensional intrinsic mode functions (BIMFs). It represents the spatial–frequency–energy distribution of a given image that suits non-stationary geochemical signals arising from non-linear Earth systems. This paper gauges the relevance of BEMD and S–A in signalizing frequency channels that correspond to regional- and local-scale geochemical anomalies through a comparative experiment in the Moalleman district, NE Iran. The BEMD filtered the multi-element anomaly map adaptively into a set of BIMFs (BIMF1, BIMF2, and BIMF3) and a residual signal, in order of decreasing frequency, yielding geochemical patterns with scaling characteristics from local to regional. The S–A model filtered the multi-element anomaly map into very high, high, and low frequency channels that characterize noise signatures and geochemical anomalies associated with local and regional ore-forming processes, respectively. The results indicate that the high frequency channel derived from the BEMD filtering (i.e., BIMF1) can portray more effectively local-scale metal-vectoring anomalies distributed at/around ore-controlling faults/fractures. However, the low frequency channel yielded by S–A filtering has enhanced effectively geochemical anomaly architectures that were developed through regional metallogenesis. Therefore, we considered the local-scale geochemical anomalies (i.e., BIMF1) to delimit metal-vectoring targets, whereby four exploration priorities were defined as new areas for further metal prospecting within the study area.

Radial Basis Approximations Based BEMD for Enhancement of Non-Uniform Illumination Images

An image can be degraded due to many environmental factors like foggy or hazy weather, low light conditions, extra light conditions etc. Image captured under the poor light conditions is generally known as non-uniform illumination image. Non-uniform illumination hides some important information present in an image during the image capture Also, it degrades the visual quality of image which generates the need for enhancement of such images. Various techniques have been present in literature for the enhancement of such type of images. In this paper, a novel architecture has been proposed for enhancement of poor illumination images which uses radial basis approximations based BEMD (Bi-dimensional Empirical Mode Decomposition). The enhancement algorithm is applied on intensity and saturation components of image. Firstly, intensity component has been decomposed into various bi-dimensional intrinsic mode function and residue by using sifting algorithm. Secondly, some linear transformations techniques have been applied on various bidimensional intrinsic modes obtained and residue and further on joining the transformed modes with residue, enhanced intensity component is obtained. Saturation part of an image is then enhanced in accordance to the enhanced intensity component. Final enhanced image can be obtained by joining the hue, enhanced intensity and enhanced saturation parts of the given image. The proposed algorithm will not only give the visual pleasant image but maintains the naturalness of image also.

BEMD based adaptive Lee filter for despeckling of SAR images

Synthetic aperture radar (SAR) image processing finds application in gathering features to detect the ecological changes in earth observatory. But the speckle noise in the acquired image degrades the quality of detection. This paper explains a new method to minimize speckle noise in SAR images using bidimensional empirical mode decomposition (BEMD) based adaptive Lee filter. The main innovation of this proposed work is the use of the BEMD technique on SAR images. The decomposed levels are called bidimensional intrinsic mode functions (BIMF). By this decomposition algorithm, the high-frequency noise component gets separated in the first level of BIMF, which is further filtered by the proposed adaptive filter and reconstructed. In this paper, we are proposing a BEMD based adaptive Lee filter. The BEMD based Lee filter with different window sizes is used. The designed filter algorithm is validated by calculating the performance parameters to demonstrate its denoising performance.

Skin lesion classification using multi-resolution empirical mode decomposition and local binary pattern.

Skin cancer is the most common type of cancer in many parts of the world. As skin cancers start as skin lesions, it is important to identify precancerous skin lesions early. In this paper we propose an image based skin lesion identification to classify seven different classes of skin lesions. First, Multi Resolution Empirical Mode Decomposition (MREMD) is used to decompose each skin lesion image into a few Bidimensional intrinsic mode functions (BIMF). MREMD is a simplified bidimensional empirical mode decomposition (BEMD) that employs downsampling and upsampling (interpolation) in the upper and lower envelope formation to speed up the decomposition process. A few BIMFs are extracted from the image using MREMD. The next step is to locate the lesion or the region of interest (ROI) in the image using active contour. Then Local Binary Pattern (LBP) is applied to the ROI of the image and its first BIMF to extract a total of 512 texture features from the lesion area. In the training phase, texture features of seven different classes of skin lesions are used to train an Artificial Neural Network (ANN) classifier. Altogether, 490 images from HAM10000 dataset are used to train the ANN. Then the accuracy of the approach is evaluated using 315 test images that are different from the training images. The test images are taken from the same dataset and each test image contains one type of lesion from the seven types that are classified. From each test image, 512 texture features are extracted from the lesion area and introduced to the classifier to determine its class. The proposed method achieves an overall classification rate of 98.9%.

Despeckling of SAR Images Using BEMD-Based Adaptive Frost Filter

In image processing, removal of speckle noise from a satellite image is a challenging task for the researchers. There are various approaches for speckle noise reduction. Generally, the speckle noises are scattered, in satellite images, medical images and synthetic aperture radar (SAR) images. This paper introduces a bidimensional empirical mode decomposition (BEMD)-based adaptive filtering method for despeckling of SAR image. The noisy SAR image is decomposed into different bidimensional intrinsic mode function (BIMF) levels using BEMD and then filtering is performed on the first BIMF level, as it contains the high-frequency noise component. This adaptation process effectively filters out the noisy image component without destroying the original image component. A BEMD-based adaptive Frost filter is introduced in this paper for despeckling of SAR images. The despeckling performances of our proposed filtering method are further analyzed by visual evaluation and also using performance parameters comparatively. Our reconstructed images show better performance quantitatively and qualitatively compared to other filters.

Deep Multiple Instance Learning for Automatic Breast Cancer Assessment Using Digital Mammography

Breast cancer causes serious public health problems; it is the most common cancer among women worldwide. Screening and early detection of signs of breast cancer increase the chance of survival. Early diagnosis is a crucial task for radiologists and physicians. Therefore, many Computer-Aided Detection and Diagnosis (CADx) systems are being developed to ensure the survival of radiologists’ decisions. In this paper, we describe a framework to automate assessment of suspicious regions, detected in screening mammography, without having carried out additional examinations, especially unnecessary biopsies in the case where the suspect regions are benign tumors. The setup of the proposed framework is ordered as follows: Regions of interest (ROIs) have been segmented using a modified K-means algorithm; the Bi-dimensional empirical mode decomposition (BEMD) algorithm is applied to derive many layers (Bi-dimensional Intrinsic Mode Function BIMF) from ROIs. Then, textural features are extracted from the obtained ROIs. First, directly from segmented ROI, second from the ROI and its sub-layers (BIMFs + Residue). The features extracted in the second time have been grouped into a bag descriptive of the ROI under consideration. This bag is the input parameter of the classification algorithm based on the support vector machine (which has been confirmed to be beneficial for the classification of breast cancer). The average obtained sensitivity, specificity, accuracy and AUC rates, are, respectively 98.60%, 98.65%, 98.62%, and 98.23%. Generally, the experimental results in: INbreast, DDSM, and MIAS datasets demonstrate the robustness and the efficiency of the developed framework compared to previous works in the literature and have shown a significant advance.

An optimized pulse coupled neural network image de-noising method for a field-programmable gate array based polarization camera.

The quality of polarization images is easy to be affected by the noise in the image acquired by a polarization camera. Consequently, a de-noising method optimized with a Pulse Coupled Neural Network (PCNN) for polarization images is proposed for a Field-Programmable Gate Array (FPGA)-based polarization camera in this paper, in which the polarization image de-noising is implemented using an adaptive PCNN improved by Gray Wolf Optimization (GWO) and Bi-Dimensional Empirical Mode Decomposition (BEMD). Unlike other artificial neural networks, PCNN does not need to be trained, but the parameters of PCNN such as the exponential decay time constant, the synaptic junction strength factor, and the inherent voltage constant play a critical influence on its de-noising performance. GWO is able to start optimization by generating a set of random solutions as the first population and saves the optimized solutions of PCNN. In addition, BEMD can decompose a complicated image into different Bi-Dimensional Intrinsic Mode Functions with local stabilized characteristics according to the input source image, and the decomposition result is able to lower the complexity of heavy noise image analysis. Moreover, the circuit in the polarization camera is accomplished by FPGA so as to obtain the polarization image with higher quality synchronously. These two schemes are combined to attenuate different types of noises and improve the quality of the polarization image significantly. Compared with the state-of-the-art image de-noising algorithms, the noise in the polarization image is suppressed effectively by the proposed optimized image de-noising method according to the indices of peak signal-to-noise ratio, standard deviation, mutual information, structural similarity, and root mean square error.

Combination of ELM and BEMD for Target Recognition of SAR Images

For the problem of target recognition of synthetic aperture radar (SAR) images, a method based on the combination of bidimensional empirical mode decomposition (BEMD) and extreme learning machine (ELM) is proposed. BEMD performs feature extraction for SAR images, producing multi-layer bidimensional intrinsic mode functions (BIMF). These BIMFs covey the discrimination of the original target while effectively eliminating the noises. ELM conducts the classification of each BIMF with high efficiency and robustness. Finally, the decisions from different BIMFs are fused using a linear weighting strategy to reach a reliable decision on the target label. The proposed method compensates the relatively low adaptivity of ELM to noise corruption by BEMD feature extraction. Moreover, the multi-layer BIMFs provide more discriminative information for correct decision. Hence, the overall recognition performance can be improved. As an efficient recognition algorithm, the proposed method can be used in an embedded system for wide applications. Experiments are designed and implemented on the moving and stationary target acquisition and recognition (MSTAR) dataset. The proposed method is tested under both the standard operating condition (SOC) and extended operating conditions (EOCs). The results reflect its effectiveness and robustness via quantitative comparisons.

Multiset Canonical Correlations Analysis of Bidimensional Intrinsic Mode Functions for Automatic Target Recognition of SAR Images.

A novel feature generation algorithm for the synthetic aperture radar image is designed in this study for automatic target recognition. As an adaptive 2D signal processing technique, bidimensional empirical mode decomposition is employed to generate multiscale bidimensional intrinsic mode functions from the original synthetic aperture radar images, which could better capture the broad spectral information and details of the target. And, the combination of the original image and decomposed bidimensional intrinsic mode functions could promisingly provide more discriminative information for correct target recognition. To reduce the high dimension of the original image as well as bidimensional intrinsic mode functions, multiset canonical correlations analysis is adopted to fuse them as a unified feature vector. The resultant feature vector highly reduces the high dimension while containing the inner correlations between the original image and decomposed bidimensional intrinsic mode functions, which could help improve the classification accuracy and efficiency. In the classification stage, the support vector machine is taken as the basic classifier to determine the target label of the test sample. In the experiments, the 10-class targets in the moving and stationary target acquisition and recognition dataset are classified to investigate the performance of the proposed method. Several operating conditions and reference methods are setup for comprehensive evaluation.

Fast fringe enhancement by improved bidimensional sinusoids-assisted empirical mode decomposition

Fringe enhancement is necessary for optical measurement, which includes the elimination of noise and background from a fringe pattern. Bidimensional empirical mode decomposition (BEMD) algorithms have been used for fringe enhancement, but they usually decompose a fringe pattern into many bidimensional intrinsic mode functions (BIMFs), which is not only inefficient but also leads to difficulties for classifying the BIMFs to distinguish noise, the useful signal and background. In this paper, the bidimensional sinusoids-assisted empirical mode decomposition (BSEMD) algorithm is firstly studied in depth, and a key factor is found in deciding the results. Then an improved BSEMD (iBSEMD) algorithm is proposed, where the key factor is estimated easily and automatically. The proposed method largely reduces the number of BIMFs resulted, making the fringe enhancement become faster and have a more robust effect. Some optimized strategies are given additionally to implement the iBSEMD algorithm by compute unified device architecture (CUDA) for practical applications. Comparison experiments are conducted with state-of-the-art methods to prove the efficiency and effectiveness of our method.

Combining multi-mode representations and ResNet for SAR target recognition

ABSTRACT This letter combines the multi-mode representations extracted by bidimensional empirical mode decomposition (BEMD) and deep residual networks (ResNet) for synthetic aperture radar (SAR) target recognition. Bidimensional intrinsic mode functions (BIMFs) are generated by BEMD to describe the target characteristics in SAR images. A special ResNet is designed and trained for each layer of BIMFs. The decisions from different BIMFs are linearly fused using a random weight matrix. Typical test scenarios are designed on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset to examine the proposed method. The results validate the validity and robustness of the method.

Target Recognition of SAR Images Based on Complex Bidimensional Empirical Mode Decomposition

A target recognition method for synthetic aperture radar (SAR) image based on complex bidimensional empirical mode decomposition (C-BEMD) is proposed. C-BEMD is used to decompose the original SAR image to obtain multilevel complex bidimensional intrinsic mode functions (BIMF), which reflect the two-dimensional time-frequency characteristics of the target. In the classification stage, the decomposed multilevel BIMFs are represented using the multitask sparse representation. Finally, the target category of the test sample is determined according to the reconstruction errors related to different training classes. In the experiment, the standard operating condition (SOC) and extended operating conditions (EOC) are designed based on the MSTAR dataset to test and verify the proposed method. The results confirm the effectiveness and robustness of the method.

Slope instability detection for muddy submarine channels using sub-bottom profile images based on bidimensional empirical mode decomposition

Slope stability is a key problem for safe submarine channel operation on muddy coasts. The early detection and identification of slope instabilities is important to allow safety measures to be taken in a timely manner. Owing to the difficulties in predicting or providing early forecasts of slope collapse in muddy submarine channels, this study introduces a bidimensional empirical mode decomposition (BEMD) with adaptive time–frequency resolution to identify slope instabilities using sound prints of sub-bottom profile images. The results show that three bidimensional intrinsic mode function (BIMF) images decomposed by BEMD with frequencies ranging from high to low can depict the spatial variation in the sound prints. The second and third BIMF images reveal the spatial relationship between the sound prints and the slope abnormalities at the early stage of slope collapse. This approach effectively identifies the early sound prints and the spatial information of the sub-bottom profile images during the process of slope collapse, which can improve abnormal feature recognition. This method will help in the prediction and early forecast of channel slope instability and collapse.

Steel surface defect classification using multi-resolution empirical mode decomposition and LBP

In this work we introduce Multi-Resolution Empirical Mode Decomposition (MREMD) as an image decomposition method that simplifies the implementation of Empirical Mode Decomposition (EMD) for bidimensional data. The proposed method is used in conjunction with the local binary pattern (LBP) to classify the images of six types of defects that can be found on the surface of rolled steel. The process starts by performing MREMD on the training images to obtain the first bidimensional intrinsic mode function (BIMF). Then features are extracted from the images and their first BIMF using the LBP. These features are used to train an artificial neural network (ANN) classifier. After training, given an unknown test image containing a defect, MREMD is applied on it to obtain its first BIMF. Next, LBP features are extracted from the image and its first BIMF and these features are fed to the trained ANN classifier to assign the image to one of the six defect classes. The classification process is carried out on 900 test images of the NEU database of six types of surface defects. The approach achieves an overall accuracy that is better than the result obtained using the LBP features alone. The main contribution of this paper is the introduction of multi resolution envelope interpolation using downsampling and upsampling with a fixed window size that reduces the execution time and decrease the sensitivity of the resulting BIMFs to the positions and number of extrema in the input image.

Prediction of Soil Nutrients Based on Topographic Factors and Remote Sensing Index in a Coal Mining Area, China

(1) Background: Coal mining operations caused severe land subsidence and altered the distributions of soil nutrients that influenced by multiple environmental factors at different scales. However, the prediction performances for soil nutrients based on their scale-specific relationships with influencing factors remains undefined in the coal mining area. The objective of this study was to establish prediction models of soil nutrients based on their scale-specific relationships with influencing factors in a coal mining area. (2) Methods: Soil samples were collected based on a 1 × 1 km regular grid, and contents of soil organic matter, soil available nitrogen, soil available phosphorus, and soil available potassium were measured. The scale components of soil nutrients and the influencing factors collected from remote sensing and topographic factors were decomposed by two-dimensional empirical mode decomposition (2D-EMD), and the predictions for soil nutrients were established using the methods of multiple linear stepwise regression or partial least squares regression based on original samples (MLSROri or PLSROri), partial least squares regression based on bi-dimensional intrinsic mode function (PLSRBIMF), and the combined method of 2D-EMD, PLSR, and MLSR (2D-EMDPM). (3) Results: The correlation types and correlation coefficients between soil nutrients and influencing factors were scale-dependent. The variances of soil nutrients at smaller scale were stochastic and non-significantly correlated with influencing factors, while their variances at the larger scales were stable. The prediction performances in the coal mining area were better than those in the non-coal mining area, and 2D-EMDPM had the most stable performance. (4) Conclusions: The scale-dependent predictions can be used for soil nutrients in the coal mining areas.

Image Processing Algorithm Based on Bi-dimensional Local Mean Decomposition

Because images contain rich characteristic information, adaptive image decomposition algorithms are necessary to achieve multi-scale extraction of image information in multi-scale image decomposition processing. For this reason, based on local mean decomposition (LMD), which has good self-adaptive characteristics, this paper proposes a new adaptive image processing algorithm, bi-dimensional local mean decomposition (BLMD). BLMD can decompose the original image into multiple bi-dimensional product functions (BPFs). Aiming at the decomposition of BLMD, this paper proposes targeted solutions and designs for the extraction of extremum points, screening process interpolation methods, and decomposition and stop conditions involved in BLMD. After fully recognizing the self-adaptive and multi-scale characteristics of BLMD, this paper proposes a variable neighborhood window method to obtain the extreme points in the decomposition process and uses fractal theory to interpolate the image and obtain the corresponding mean surface and other information. Then, the number of non-coincident extreme points on the zero-valued plane projection between adjacent surfaces in the screening process is counted and analyzed, and a stop condition that matches the characteristics of the image is given to ensure the BPF component obtained by decomposition accurately reflects certain feature information of an image. Finally, the BLMD proposed in this paper is formed. Empirical analysis shows this method can quickly decompose and maintain the characteristics of data-drivenness, adaptability and scale consistency of LMD; it can also avoid the disadvantages of other adaptive processing algorithms, such as the bi-dimensional intrinsic mode function obtained by the decomposition of bi-dimensional empirical mode decomposition and the residual failing to completely contain the feature information of the original image.

Text line segmentation and binarization of handwritten historical documents using the fast and adaptive bidimensional empirical mode decomposition

Text line segmentation is a basic step that can be used to serve several processes in the recognition stage. Image segmentation is thus inevitable. A necessary step for text line segmentation is the image binarization. However, it is challenging due to complex background in such images. In this paper, we present a new text line segmentation and banarization method based on fast and adaptive bidimensional empirical mode decomposition (FABEMD). To achieve this, we use the FABEMD method to decompose each image into two components. The binarization threshold is calculated taking into account the characteristics of each component. The inspiration for the new binarization method was drawn from the standard Niblack's and Sauvola's Algorithms. Then the text line segmentation is performed after eliminating the BIMF1 (bidimensional intrinsic mode functions) which could disrupt the segmentation process. The results show that the proposed approach is less sensitive to noise and provides improved text line segmentation and binarization compared to iterative methods.