Fabric pattern recognition using mean shift algorithm in empirical mode domain

The edge feature extraction of image is one of the research fields of image processing theory and application. The traditional methods of image feature extraction are simple and proficient, but the accurate performance of the feature extracted is not even higher. As such, a new method for extracting image edge feature was proposed by using the two-dimensional Empirical Mode Decomposition (2-D EMD) and Riesz Transform. Firstly, the image was decomposed to multi-level Intrinsic) Mode Function (IMF) by 2-D EMD, and then the Riesz Transform with stronger local preserving ability was used for analyzing their local properties instead of the Hilbert Transform, by which the edge feature extraction with higher resolution was carried on. Finally, simulation shows that the proposed method is feasible and valid.

Traditional two-dimensional empirical mode decomposition (2D-EMD) algorithms generate multiple subband signals, each having the same size of the original signal. Thus, huge amounts of data to be stored may be generated. Moreover, the computational load is massive as the decomposition levels increase. This paper introduces a method to reduce the data generated (i.e. reduce storage requirement) by incorporating decimation into the 2D-EMD, while maintaining perfect reconstruction. Furthermore, it is well established that traditional EMDs can be thought as having the structure of a single dyadic filter bank. The proposed algorithm is applicable into any arbitrary tree structures including octave filter banks, 2D-EMD packets when applied to a full binary tree, etc. The methodology hereby presented builds on the algorithm introduced by the authors in [8].

Digital image processing is an important field in pattern recognition and computer vision, where the process of separating an object with the background acts as one of the crucial roles in executing image processing. This research will talk about mean shift algorithm implementation in processing a set of undersea images to see its effectiveness in separating the background with the object automatically based on pixel distribution and color intensity. How the mean shift algorithm works is by doing a reading process to find the center of a pixel cluster in an image before this algorithm starts to cluster or group pixels with similar characteristics. In this research, a set of image input will be used as a test under mean shift algorithm to give output of an optimal pixel segmentation or grouping, leading to a proof that the mean shift algorithm has the capability to separate a main object from the background, especially in images with intense and high contrast. Even so, in images with less intense and lower contrast, the segmentation is not as accurate. The image input will have to undergo some more pre-processing before the mean shift segmentation is implemented. This research outcome is that the mean shift algorithm is effective for segmenting marine animal images based on colors without having to initialize how many clusters as the conclusion where this method is applicable in many computer vision programs such as object detection or image pattern recognition.

基于二维经验模态分解的五步非等步在线三维检测

Objective. The aim of this work was to study the cerebral protective effect of craniotomy hematoma removal under propofol anesthesia based on the artificial intelligence algorithm analysis of the changes in imaging characteristics of chronic subdural hematoma (CSDH) patients. Methods. A total of 60 CSDH patients who were treated in hospital were recruited and were randomly rolled into an experimental group and a control group, with 30 people in each group. Patients in the experimental group were treated with propofol anesthesia + craniotomy hematoma removal, while those in the control group were treated with conventional anesthesia + craniotomy hematoma removal. Head CT examinations were performed on the next day, one week, one month, three months, and six months after the operation. A two-dimensional empirical mode decomposition (BEMD) algorithm was used for edge detection and denoising of brain CT images of CSDH patients. Then, the amount of hematoma was calculated, and the Markwalder grading was performed to evaluate the neurological function. The number of recurrence and reoperation cases within six months of follow-up was collected. Results. 1. The quality of CT images was remarkably improved after processing with artificial intelligence algorithms. 2. The amount of hematoma in the experimental group was remarkably lower than that in the control group at January, March, and June after surgery (12.89 ± 2.12 VS 20.32 ± 16.41; 7.55 ± 4.13 VS 15.88 ± 14.22; 3.39 ± 3.79 VS 6.55 ± 3.69, P < 0.05 ). 3. The experimental group was remarkably better than the control group in Markwalder grading three months and six months after the operation ( P < 0.05 ). Conclusion. Artificial intelligence algorithm had good effect on the brain CT image processing of CSDH patients, and craniotomy hematoma removal under propofol anesthesia had an ideal brain protection effect.

The distribution of heavy metals in agricultural soils is affected by various anthropogenic activities and environmental factors occurring at different spatial scales. This paper introduced the two-dimensional empirical mode decomposition (2D-EMD) to separate the spatial variability in soil heavy metals into different scales. Geostatistics and multivariate analysis were also utilized to quantify their spatial structure and identify their potential influencing factors. The study was conducted in an arable land in southeastern China where 260 surface soil samples were collected and measured for total contents of cadmium (Cdtotal), mercury (Hgtotal), and sulfur (TS); pH; and soil organic carbon content (SOC). The results showed that both Cdtotal and Hgtotal had high coefficients of variation. The overall variation in all five soil variables was separated into three intrinsic mode functions (IMFs) and spatial residues. All three IMFs had short-range spatial correlations (1-8km), while the spatial residues had moderate-large spatial ranges (13-39km). IMF1 of Cdtotal was strongly correlated with IMF1 of SOC and TS, which was consistent with the principal component analysis. This indicated that IMF1 of Cdtotal represented local variations which were influenced by agricultural activities. IMFs of Hgtotal showed clustered distributions in the study area, with IMF1 and IMF2 of Hgtotal correlated in one principal component, and IMF3 of Hgtotal and IMF3 of soil pH in another component. This indicated that all three IMFs of Hgtotal might be influenced by different industrial activities or different pathways of the same industrial activities. The residues of Cdtotal and Hgtotal, representing the regional trends, only accounted for 26% of the total variance, whereas IMF1 contributed about half of the total variance. It can be concluded that agricultural activities and industrial activities were the dominant contributors of the overall variations in Cdtotal and Hgtotal in the study area, respectively.

An adaptive denoising method based on 2D empirical mode decomposition (EMD) is proposed to improve the infrared image quality of inspection UNMANNED aerial vehicles (UAVs) and provide guarantee for improving the inspection level of distribution network. Through rapid adaptive two-dimensional empirical mode decomposition algorithm decomposition of a UAV collected for distribution network inspection original noise of infrared image, get more than the IMF component and the residual amount, a forecast noise dominated the IMF component parameters such as threshold value and the variance of noise, using the estimated parameters in combination with the optimal linear interpolation algorithm of noise threshold function of leading the IMF component implementation of threshold denoising. After the denoised IMF component is obtained, the denoised infrared image is obtained after reconstruction with the signal-dominated IMF component, and the adaptive denoising of the infrared image of the distribution network inspection UAV is realized. The experimental results show that the method in this paper can maintain the details of the image, improve the definition, significantly improve the visual effect, the overall denoising performance is stable and feasible, and ensure the quality inspection UAV to collect infrared images.

In 3D shape measurement, because deformed fringes often contain low-frequency information degraded with random noise and background intensity information, a new fringe-projection profilometry is proposed based on 2D empirical mode decomposition (2D-EMD). The fringe pattern is first decomposed into numbers of intrinsic mode functions by 2D-EMD. Because the method has partial noise reduction, the background components can be removed to obtain the fundamental components needed to perform Hilbert transformation to retrieve the phase information. The 2D-EMD can effectively extract the modulation phase of a single direction fringe and an inclined fringe pattern because it is a full 2D analysis method and considers the relationship between adjacent lines of a fringe patterns. In addition, as the method does not add noise repeatedly, as does ensemble EMD, the data processing time is shortened. Computer simulations and experiments prove the feasibility of this method.

(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.

This study addresses the challenges of partial discharge ultra-high frequency pattern recognition under complex data sources. A systematic framework integrating data preprocessing and convolutional neural network techniques is proposed. First, a hierarchical broadcast synchronization algorithm balances synchronization precision and power consumption for sensor networks. Non-structured data such as images and waveforms are unified into phase-resolved pulse sequence matrices through grayscale conversion, binarization, and segmentation. Two-dimensional empirical mode decomposition and Kalman filtering suppress noise, enhancing data quality. Second, an improved LeNet-5 CNN model initializes convolutional layer parameters via unsupervised autoencoder pre-training, strengthening feature extraction. Validated on a 145kV real-type gas-insulated switchgear platform simulating five insulation defects, results demonstrate a minimum measurable discharge magnitude of 60 pC. Training and testing accuracies reach 93.54% and 91.26%, respectively, confirming high robustness for power equipment condition monitoring.

A feature extraction method based on empirical mode decomposition, approximate entropy is proposed. Firstly, the vibration signals are decomposed into a finite number of intrinsic mode functions by empirical mode decomposition. Then, by the means of approximate entropy, the complexity of the original and its intrinsic oscillation modes can be quantified, thereby the intrinsic mode complexity of reciprocating mechanical vibration signals can be quantitatively evaluated. So, the approximate entropies of intrinsic mode functions can serve as the fault characteristic vectors of support vector machine. Finally, the mechanical working condition and faults are classified. The results of engineering application validate the effectiveness of the method.

In this paper, we propose a novel method for automatic object segmentation from natural scene images. This method is based on saliency map, mean shift segmentation and level set method. First, a histogram based contrast method is used to generate the saliency map of the input image. Second, the input image is segmented into clusters using mean shift. Based on the saliency map, segmented clusters are classified into background and foreground clusters. After that, an initial contour for level set method is determined by applying morphological erosion on foreground clusters. Finally, the level set method is used to evolve the initial contour and find the object of interest. The experimental results have shown that our proposed method is not only able to replace manual labeling of initial contour in level set method but also able to yield more accurate segmentation results than previous segmentation approaches.

Painting style transformation aims to produce a painting in a particular artist’s style from a picture or other paintings. In the previous implementations of example-based painting style transfer, users had to manually select the patches from example patches. It is time-consuming and subjective for a user to select proper patches from a large number of patches. This paper develops a patch-based approach for rendering example-based images without requiring user intervention to find appropriate patches in the synthesis process. We use mean shift segmentation and texture re-synthesis to construct an artistic database which enables users to synthesize images according to a selected painting style. Moreover, seven important painting features are proposed for finding an adequate correspondence between the source image and the database. The synthesized output images are generated by patch-based sampling method after the correspondence has been determined. Experimental results show the feasibility of the proposed approach by demonstrating the synthesis results from different types of source images with the painting style of Vincent van Gogh.

본 논문에서는 최근 급속히 보급되고 있는 스마트폰에서 촬영한 사진 영상을 수채화 효과가 나도록 변환하는 기법에 대하여 제안한다. 제안하는 수채화 효과 변환 기법은 영상처리 분야에서 많이 사용하는 양방향 필터링(bilateral filtering)과 평균 이동 분할(mean shift segmentation)을 이용한다. 먼저 입력 영상을 스마트폰 화면 해상도로 크기 변환한 후 양방향 필터링을 이용하여 사진의 외곽선 부분은 보존하면서 고주파 성분을 약화시키도록 한다. 다음으로 양방향 필터링을 거친 영상에서 평균 이동분할을 수행하여 최종영상을 생성한다. 실험을 통하여 스마트폰의 연산속도를 고려한 평균 이동 분할의 파라미터 값을 설정하여 다양한 사진에 대하여 수채화 효과가 잘 나타나는 것을 확인하였다. We propose a retouching method that converts a photography taken by smartphone to a watercolor painting image using bilateral filtering and mean shift segmentation which are mostly used in image processing. The first step is to convert an input image to fit the screen resolution of smartphone. And next step is to weaken high frequency components of the image, while preserving the edge of image using the bilateral filtering. And after that we perform mean shift segmentation from the bilateral filtered image. We apply parameters of mean shift segmentation considering the processing speed of smartphone. Experimental result shows that our method can be applied to various types of image and bring better result.

Sequence stratigraphy analysis is one of the most important tasks in evaluating and characterizing the reservoir system within a basin. However, it is very hard to identify the system tracts and lithofacies using well logs for the conglomerate reservoirs because of the strong lithology heterogeneity. Based on the fact that the system tracts and lithofacies usually illustrate cycle features within the basin, we decompose the well logs into different intrinsic modes to characterize the sequence units and lithofacies at different scale. First, we analyze the log response to lithologies to determine the well logs used for sequence analysis. Then, we use variational mode decomposition to decompose the selected well logs into an ensemble of different band-limited intrinsic mode functions, each with its center wavenumber. Finally, we interpret the sequence stratigraphy and lithofacies using corresponding decomposed modes. We validate the effectiveness of our method in the lithofacies and sequence identification for a conglomerate reservoir in the Shengli oil field, Bohai Bay Basin, east China. The decomposed intrinsic modes with a larger center wavenumber perfectly characterize the sequence units at a larger scale, whereas the decomposed intrinsic modes with a smaller center wavenumber reveal the lithofacies changes at a smaller scale. The application illustrates that it is much more convenient and easier for sequence stratigraphy analysis to integrate the original and decomposed logs.