63results about How to "Improve denoising ability" patented technology

A medical ultrasound image denoising method based on wavelet transform and quick bilateral filtering comprises the following steps of the first step of establishing a medical ultrasound image model, the second step of carrying out wavelet transform on an image obtained in the first step after logarithm transformation to obtain four frequency domains (LL1, LH1, HL1and HH1), continuously carrying out wavelet transform on the low frequency domain LL1 to obtain four frequency domains (LL2, LH2, HL2 and HH2) again and then repeating the step until resolving the maximum layer number, the third step of carrying out quick bilateral filtering on the low frequency portion (LLJ) at the last layer, the fourth step of carrying out threshold value method shrinkage on wavelet coefficients of the high frequency portions (LHj, HLj and HHj) of all layers and the fifth step of carrying out wavelet inverse transformation to obtain the denoised medical ultrasound image. In addition, the J is 1, 2, ..., J. If denoised ultrasound envelope signals are wanted, exponential transformation is carried out on the ultrasound image obtained in the fifth step.

The invention discloses a traditional Chinese medicinal material microscopic image noise filtering system and method adopting a pulse coupling neural network. A pulse coupling neural network model suitable for processing tissue image information is adopted for detecting traditional Chinese medicinal material microscopic images. When small-density pulse noise pollution happens to the traditional Chinese medicinal material microscopic images, adaptive weighted filtering processing is carried out; when large-density pulse noise pollution happens to the traditional Chinese medicinal material microscopic images, the introduction dual-structure element mathematical morphology with edge detailed information kept is adopted for secondary filtering. Earlier foundations are laid for further improving quality testing, recognition and identification of traditional Chinese medicinal materials; higher noisy point detection performance is achieved, the noise fallout ratio and omission ratio are low, and the noise detection precision is high; detection time is short, and automatism is high; noise is removed, meanwhile, noise interference can be effectively filtered out, and image edge details and other information can be protected well.

The invention discloses a shearlet transform and fast bilateral filter image denoising method, which comprises the steps of: 1) acquiring an envelope signal of a noise image by using a noise imaging system, and establishing a medical ultrasonic image model; 2) carrying out multiscale and multidirectional decomposition on the medical ultrasonic image model after logarithmic transformation obtained in the step 1) by utilizing a pyramid filter bank; 3) performing threshold method contraction processing on a two-dimensional discrete shearlet transform coefficient of a high-frequency part in each subband image obtained in the step 2); 4) using a fast bilateral filter for filtering shearlet coefficients of low-frequency parts in the step 2); 5) and conducting shearlet inverse transform processing on all the coefficients processed in the step 3) and the step 4), so as to obtain a denoised medical ultrasound images. The introduction of the fast bilateral filter in the shearlet transform and fast bilateral filter image denoising method can effectively improve the denoising performance, and greatly increase the processing efficiency.

The invention discloses a transmission line icing thickness identification method based on an unmanned aerial vehicle binocular parallax image and belongs to the field of image processing technology.The method comprises the steps of relevant information collection, icing image acquisition, parallax image solving, parallax image preprocessing, image binarization, contour extraction, icing thickness calculation, etc. According to the method, an icing image is processed to extract icing contours, a foreground and a background are separated by use of distance information, and therefore the separation effect is good; the icing image is preprocessed according to the characteristic that adjacent intervals of the icing image have approximate gray values, so that image gray levels are distributedmore uniformly; a binary threshold calculation method is proposed, a binary threshold is automatically determined, and therefore the method has high adaptability; and icing thickness is calculated bycalculating the specific value of the quantity of pixels contained in an iced wire contour to the quantity of pixels contained in a non-iced wire contour within a fixed column interval range, the possibility that a large measurement error is generated due to an icing shape change is reduced, and therefore the method is high in adaptability and precision.

The invention discloses a robust image double-watermarking method, which mainly solves the problem that the prior methods of the same type are poor in robustness and fully utilizes two image characteristics, namely inherent texture and edges to form double watermarks. When the watermarks are embedded, a zero watermark is structured by utilizing the edge characteristics of an original host image; an intensive-texture region of the host image is obtained by an empirical mode decomposition method; and a direction with maximum energy on a Contourlet domain is selected to embed binary watermarks. When the watermarks are extracted, the edge characteristics of a synthetic image is first extracted to detect the zero watermark; then a watermark-embedding position is quickly positioned by utilizing specific keys; and the binary watermarks are extracted. The method has the advantages of high capability of resisting geometric attacks, good transparency and high security, and can be used for protecting the copyright security of digital multimedia products.

The invention relates to a statistical model based bridge health monitoring data wavelet denoising method. The method includes the following steps: firstly, establishing a bridge monitoring signal model; secondly, subjecting an obtained structure monitoring signal to wavelet decomposition to obtain two frequency domains, namely a low frequency domain A1 and a high frequency domain D1, continuing performing wavelet decomposition on the low frequency domain A1 to obtain two frequency domains, namely a low frequency domain A2 and a high frequency domain D2, and repeating the step till maximum layers are decomposed; thirdly, subjecting the actual monitoring signal to wavelet decomposition and establishing a statistical model of wavelet decomposition coefficients; fourthly, deducing a wavelet threshold contracting function and subjecting the wavelet coefficients of a high-frequency part (Dj,j=1,2,...J) of each layer to thresholding method contracting processing; fifthly, performing wavelet inverse transformation processing to obtain denoised bridge structure monitoring data. Denoising is performed effectively, quality of the monitoring data is improved, and signal smoothness is improved.

The invention provides a medical ultrasonic image denoising method based on wavelet transform and a trilateral filter. The medical ultrasonic image denoising method comprises the following steps that step 1) a medical ultrasonic image model is established; and step 2) wavelet decomposition is performed on an image obtained in the step 1 after logarithmic transform so that four frequency domains (LL1, LH1, HL1 and HH1) are obtained. Wavelet decomposition is continuously performed on the low frequency domain LL1 so that four frequency domains (LL2, LH2, HL2 and HH2) are obtained again; then the step is repeated until the maximum number J of layers of decomposition; step 3) threshold method contraction processing is performed on the wavelet coefficient of the high frequency part (LHj, HLj and HHj, j=1,2,...,J) of each layer; step 4) filtering processing is performed on the wavelet coefficient of the low frequency part (LLJ) of the last layer by utilizing the trilateral filter; and step 5) inverse wavelet transform processing is performed so that a denoised medical ultrasonic image is obtained.

The invention discloses a method for de-noising a medical ultrasonic image based on wavelet transformation and a guide filter, and the method comprises the following steps of: step 1) creating a medical ultrasonic image model; step 2) performing wavelet decomposition to the logarithm transformation image in the step 1) to obtain four frequency domains (LL1, LH1, HL1 and HH1); performing wavelet decomposition to LL1 in the low frequency domain so as to obtain four frequency domains (LL2, LH2, HL2 and HH2); repeating the step until to decompose the maximum layer J; step 3) performing filter processing to a wavelet coefficient in the final-layer low-frequency part (LLJ) by the guide filter; step 4) performing threshold valve method contraction treatment to the wavelet coefficient in each-layer high-frequency part (LHj, HLj and HHj, j=1, 2, ......, J); step 5) performing wavelet inverse transformation treatment to gain the de-noised medical ultrasonic image; performing exponential transformation to the medical ultrasonic image obtained in the step 5) to obtain de-noised ultrasonic envelope signals.

The invention discloses a gather optimized processing method. The gather optimized processing method comprises the following steps of carrying out noise attenuation processing on actually-obtained pre-stack gathers by adopting a Radon conversion filtering method; carrying out gather leveling processing on the pre-stack gathers which are subjected to the noise attenuation processing by adopting a static correction method; carrying out amplitude correction processing on the pre-stack gathers which are subjected to the gather leveling processing by adopting a background tendency energy compensation method based on model AVO (Amplitude Variation with Offset) characteristics. According to the gather optimized processing method, the Radon conversion filtering method can be used for removing multiple waves, linear interference, random noises and the like in the gathers; the gather optimized processing method has a strong noise elimination capability and is less damage to signals; the gather leveling adopts the static correction method so that the gathers can be leveled better; furthermore, the amplitude correction adopts background tendency energy compensation based on the model AVO characteristics, and the characteristic that the amplitude of the gathers are changed along the offset distance is accurately corrected.

The invention discloses a denoising method for a partial discharge ultrahigh-frequency signal of a transformer based on the improved variational mode and SVD (singular value decomposition). The methodcomprises the following steps: collecting a partial discharge signal of oil-paper insulation of the transformer by using an ultra-high frequency detection method, performing the variational mode decomposition of the collected partial discharge signal; optimizing the parameters of the variational mode decomposition algorithm through using the evolutionary algorithm, and introducing a kurtosis indicator to filter out narrowband noise; performing the SVD of a signal with the narrow-band noise being filtered; improving a singular value screening process in the SVD algorithm through using a clustering algorithm, thereby achieving the better filtering of white noise. The method has the characteristics of high precision, good denoising effect and small distortion, and is suitable for real-time monitoring of oil-paper insulation of the transformer, partial discharge signal detection and the like.

The invention discloses a sea surface flow inversion method based on an X waveband radar image. The method comprises the following steps that: (1), sea clutter images in a time-space domain are collected and are used as a sequence, so that a sub-image sequence is obtained; (2), three-dimensional fourier transform is carried out on the sub-image sequence; (3), a band pass filer is constructed according to a dispersion relation; (4), correction is carried out on a non-linear influence of an image spectrum; (5), a degree of membership is calculated; (6), weighted calculation is carried out; (7),initial flow estimation carried out; (8), iteration flow estimation is carried out. Compared with a current flow inversion algorithm, the sea surface flow inversion method enables a flow inversion accuracy to be improved and especially a flow inversion accuracy at a slow flow speed to be improved; moreover, stability on an inversion result is improved. According to the invention, a dispersion relation band bass filter that depends on a maximum flow speed is utilized to carry out noise filtering on an image spectrum and the denoising capability is strong; besides, correction is carried out on the image spectrum to obtain a sea state spectrum, so that real sea state information can be reflected; and then, the sea state spectrum is utilized as one of weights of a least square method to calculate a flow, so that a flow inversion result approaches a real sea state.

The invention provides a medical ultrasonic image denoising method based on a statistical model. The medical ultrasonic image denoising method comprises the following steps that step 1) a medical ultrasonic image model is established; step 2) wavelet decomposition is performed on an image after logarithmic transformation obtained in the first step so that four frequency domains (LL1, LH1, HL1 and HH1) are obtained; wavelet decomposition is continuously performed on the low frequency domain LL1 and then four frequency domains (LL2, LH2, HL2 and HH2) are obtained; and then the step is repeated until the maximum number J of layers of decomposition; step 3) threshold method contraction processing is performed on the wavelet coefficient of the high frequency part (LHj, HLj and HHj, j=1,2,...,J) of each layer; step 4) filtering processing is performed on the wavelet coefficient in the low frequency part (LLJ) of the last layer by utilizing a guidance filter; and step 5) wavelet inverse transformation processing is performed so that a denoised medical ultrasonic image is obtained.

The invention discloses a translation invariance shearler transformation medical image denoising method. The method comprises the following steps that 1, a noise imaging system is used for collecting envelope signals of a noise image, and a medical ultrasound image model is built; 2, the medical ultrasound image model obtained after logarithm transformation is subjected to a multi-scale multi-direction decomposition through a pyramid filter bank; 3, the two-dimensional discrete shearlet transformation coefficient of each subband image medium-high frequency part obtained in the step 2 is subjected to threshold value method self-adaptive shrinkage; 4, a guider filter is used for filtering the shearlet coefficient of the low-frequency part in the step 2; 5, all the coefficients processed in the steps 3 and 4 are subjected to shearlet inverse transformation, and a denoised medical ultrasound image is obtained. The guide filter is used for filtering the low-frequency part, and the operation time problem of a trilateral filter is solved.

The invention discloses a laser radar echo signal noise reduction method based on parameter optimization VMD. Firstly, an energy loss coefficient is taken as a fitness function, and a grasshopper optimization algorithm (GOA) is adopted to obtain the optimal parameters of a VMD algorithm, and a noise laser radar echo signal is subjected to VMD decomposition based on the optimal parameters; and thenhausdorff distance is adopted for distinguishing related modality and non-correlation mode, Gaussian white noise in the related modality is further filtered by adopting a wavelet de-noising method, and related modal reconstruction is carried out to obtain the noise-reduced echo signal. The method can effectively avoid the modal aliasing phenomenon, can retain useful information in the original signal while noise reduction is performed, has the advantages of strong self-adaptability, strong robustness, strong reliability and the like, and can effectively carry out noise reduction and filter processing on the echo signal of the laser radar.

The invention discloses a wavelet multi-scale crossover operation based sea-sky background infrared small target detection method and belongs to the technical field of image processing. The wavelet multi-scale crossover operation based sea-sky background infrared small target detection method comprises the steps of firstly conducting wavelet decomposition transformation on infrared images under the sea-sky background, then utilizing the low-frequency images obtained through wavelet decomposition to detect a sea antenna through horizontal edge detection and communication direction judgment, and finally conducting mutual energy crossover operation in a sea antenna region to obtain a target to be detected. The wavelet multi-scale crossover operation based sea-sky background infrared small target detection method has the advantages of being accuracy in sea antenna detection, good in adaptability, high in detection speed and good in sea clutter cloud layer interference eliminating capacity and can be widely applied to sea surface target detection, invasion warning, positioning tracking and other aspects.

The invention discloses a 3D image processing method used for improving the denoising capacity during image rendering. The method comprises the steps of clustering collected 3D point clouds to obtain N categories, wherein N is a positive integer, each category corresponds to a plane, and the 3D point clouds are obtained according to a 3D object; making the value of i an integer from 1 to N and determining the normal vector of the ith plane according to the normal vector of each point in the ith plane to obtain the normal vectors of N planes totally; making the value of i an integer from 1 to N and projecting the points in the ith plane into a plane according to the normal vector of the ith plane, wherein the plane is a detection plane corresponding to the ith plane; obtaining N detection planes; rendering the N detection planes to obtain the 3D image corresponding to the 3D object. The invention further discloses a corresponding electronic device.

The invention belongs to the technical field of radar target echo signal parameter estimation, and discloses an echo signal parameter estimation method based on a scaled-down dictionary. The echo signal parameter estimation method based on the scaled-down dictionary comprises the following steps that 1, an initial parameter set {theta <(1)>} is obtained according to all unknown parameters corresponding to scattering centers in an echo signal model, the dictionary A (theta <(1)>) is formed through the initial parameter set {theta <(1)>}, and the number m of iteration times is set to be one; 2, a new parameter set {theta' <(m)>} is obtained by carrying out Bayes learning for the mth time according to the A (theta <(m)>); 3, if m is equal to M, the step 5 is carried out, or, the value of m increases by one and the step 4 is carried out; 4, a new parameter set {theta <(m)>} is obtained according to a refinement method for a parameter set {theta <(m-1)>}, a dictionary A (theta <(m)>) is formed through the parameter set {theta <(m)>}, and then the step 2 is carried out; 5, the number m* of iteration times meets the set condition and is found out; 6, weighting and clustering are carried out on{theta' <(m*)>} according to a K-means clustering method.

The invention belongs to the technical field of aircrafts, and discloses an aircraft autonomous obstacle avoidance system and method and an aircraft. The autonomous obstacle avoidance system comprisesa solar power supply module, an image acquisition module, an obstacle information detection module, a central control module, an analysis and judgment module, an instruction generation module, a pathplanning module, a stability analysis module and a display module. According to the invention, the path planning module adjusts a flight planning trajectory when judging that another aircraft will collide with the aircraft, so as to ensure that a safe flight trajectory is planned for the aircraft; the flight safety is greatly improved; the stability analysis module can greatly reduce the computational cost while ensuring the prediction accuracy, so that the qualitative and quantitative research on the dynamic stability characteristic of the entire flight domain of the aircraft can be easily carried out; and a design direction which has a guiding significance for the aircraft design is acquired.

The invention discloses a rank reduction and denoising method for singular value attenuation. The method is applied to the seismic data processing field. In the prior art, noisy seismic data cannot bewell decomposed into a noise subspace and a signal subspace, the effect is not ideal under the condition of low signal-to-noise ratio, for the above problem, the invention provides the method which comprises the following steps: firstly, calculating optimized weight coefficients of left and right singular vectors of a noisy observation matrix; using the characteristic that an optimized weight coefficient only depends on limit singular value distribution of a pure noise matrix to decompose the noisy signal well into the noise subspace and the signal subspace, then adding a regularization operator to constrain the singular value on the above basis so as to obtain more stable low-rank estimation, and finally, obtaining stable estimation of seismic data in a frequency domain by utilizing reverse diagonal average processing. The method has outstanding denoising capability in the application of suppressing seismic random noise.

The invention discloses an impulse noise elimination method of self-adaption normal-inclined double cross window mean filtering and mainly solves the problem of an existing method that the impulse noise elimination effect is poor. The method comprises the realization steps of: (1) utilizing a sub-block ordering difference maximization method and a voting method to obtain upper and lower boundaries of impulse noise, and utilizing the upper and lower boundaries to detect impulse noise points; (2) firstly utilizing 3*3 vertical-horizontal cross (normal cross) windows to carry out 3 times of recursion cutting mean filtering on a noise image to be processed, then utilizing diagonal cross (inclined cross) windows to carry out 3 times of recursion cutting mean filtering, replacing values of the impulse noise points with results of cutting mean filtering, if the noise points are processed, ending meaning filtering, if not, increasing the windows for continuing the similar double cross window recursion cutting mean filtering, and ending the mean filtering when the windows are increased to 7*7windows; and (3) if noise processing is not completed, repeating the step (2) and forming iterated filtering. The impulse noise elimination method has the advantages that the impulse noise point detection is accurate, the impulse noise elimination effect is good, and the denoising speed is high.

magnetic powder inspection is widely used in bearing welding crack detection, but the defect still requires manually visual inspection. In view of longitudinal welding defects (such as cracks, pores,slag inclusion or the like) generated by a metal workpiece in a welding process, a magnetic mark image on the surface of the metal workpiece is captured by using an industrial camera, the features ofa suspected defect area are extracted by using the digital image processing technology, and then the automatic identification and defect location positioning of cylindrical surface cracks are completed on the basis of these features by using the neural network classifier (MLP) technology. Experimental results show that the method not only has a relatively high identification rate for true and false defects such as welding defects, metal cutting, metal heat treatment and the like, but also improves the detection efficiency, thereby having certain application research significance.

The invention discloses a fluorescent magnetic powder-based intelligent defect identification system. The system mainly comprises scene depth information collection, magnetic trace image preprocessing, color image segmentation based on a support vector machine (SVM) algorithm and a fuzzy C-mean (FCM) clustering algorithm, morphological processing and feature extraction, and crack identification based on a naive Bayesian classifier (NBC).

The invention relates to a medical ultrasound image noise reduction method based on thresholding improved wavelet transform and guide filter. The medical ultrasound image noise reduction method based on thresholding improved wavelet transform and guide filter comprises the following steps: step one, establishing a medical ultrasound image model; step two, carrying out wavelet decomposition on images after logarithmic transformation obtained in the first step to obtain four frequency domains (LL1, LH1, HL1 and HH1); carrying out wavelet decomposition on the low frequency domain LL1, and then obtaining four frequency domains (LL2, LH2, HL2 and HH2); then repeating the step until the maximum number of layers J is decomposed; step three, carrying out threshold value method shrinkage treatment on wavelet coefficients of high frequency parts (LHj, HLj and HHj, j is equal to 1, 2,..., J) on each layer; step four, carrying out filtering processing on wavelet coefficients of low frequency part (LLJ) on the last layer by utilizing the guide filter; step five, carrying out wavelet inverse transformation to obtain medical ultrasound images after noise reduction.

The invention discloses a low-dose PET image reconstruction algorithm based on ADMM (Amplitude Division Multiplexing Model) and deep learning, which solves a maximum likelihood reconstruction model into three sub-problems, namely a reconstruction layer, a denoising layer and a multiplier layer, nests an iterative reconstruction framework, and optimizes and reconstructs low-dose PET projection data by utilizing a deep learning thought. The reconstruction layer uses a traditional EM reconstruction kernel, the denoising layer uses a residual convolutional neural network for representation, the neural network is embedded into a traditional iterative reconstruction framework, reconstruction and training are realized at the same time, and a high-quality low-dose reconstructed image is obtained. According to the method, the traditional reconstruction and the neural network are successfully combined, and the problems of end-to-end learning lack of a reconstruction kernel and low traditional iteration speed of the neural network are solved.

The present invention discloses a cable partial discharge period narrow-band interference denoising method based on a Gaussian scale space. The method comprises the following steps of: collecting cable particle discharge signals by an oscillatory wave system, performing Fourier transform of the collected particle discharge signals, performing smooth filtering of the Gaussian scale space for the frequency spectrum, finding period narrow-band interference on the frequency spectrum and the particle maximum value of the particle discharge signals through multiple projection, extracting and eliminating the center frequency of the period narrow-band interference according to a kurtosis, and finally discharging the signals through IFFT reconstruction. The cable partial discharge period narrow-band interference denoising method is suitable for occasions of cable particle discharge detection.

The invention belongs to the technical field of nursing workload allocation, and discloses a nursing workload allocation assisting system. The system is provided with a patient information acquisitionmodule, a video monitoring module, a main control module, a nursing allocation module, a nursing recording module, a cloud service module and a workload statistics module. Accordingly, by means of the workload statistics module, quantized values of workload of all nursing projects are determined, the nursing projects currently needing statistics are input, according to the nursing projects needing to be executed currently and the quantized values of the workload of all the corresponding nursing projects, the current total nursing workload is counted, so that statistics on the workload of thenursing module and the nursing monomer is achieved, and a scientific management method is provided for evaluating the department workload by a nursing manager, scientifically allocating nurses and effectively controlling the nursing quality; meanwhile, by means of the cloud service module, the nursing workload statistics and allocation speed can be greatly increased, the allocation efficiency is improved, and it is guaranteed that patients are nursed in time.

The invention discloses a Monte Carlo rendering graph denoising model based on a generative adversarial network and a construction method of the Monte Carlo rendering graph denoising model. The methodcomprises the steps that a training sample is constructed, a generative adversarial network is constructed, the generative adversarial network comprises a denoising network and a discrimination network, the denoising network is used for denoising an input noise rendering graph and auxiliary features and outputting the denoising rendering graph, and the discrimination network is used for classifying the input denoising rendering graph and a target rendering graph corresponding to the noise rendering graph and outputting a classification result; according to the Monte Carlo rendering graph denoising method and device, the network parameters of the generative adversarial network are adjusted and optimized through the training sample, the denoising network determined through the network parameters serves as the Monte Carlo rendering graph denoising model, the Monte Carlo rendering graph denoising method and device are further disclosed, and denoising of the Monte Carlo rendering graph containing noise can be achieved.

The invention discloses a double threshold blood vessel image processing method based on a random direction histogram ratio, and belongs to the technical field of image processing. According to the method, a random probe detects the index, namely the direction histogram ratio, of an image property in a blood vessel image subwindow, the noise pollution area and the blood vessel area in a blood vessel image can be identified according to the value of the direction histogram ratio, thresholding processing is carried out on the noise pollution area with a high threshold value, and therefore noise pixels can be eliminated as much as possible; thresholding processing is carried out on the blood vessel area with a small threshold value, and therefore blood vessel pixels can be retained as much as possible, wherein the high threshold value and the low threshold value are obtained through a three-level Otsu algorithm. According to the blood vessel detection result obtained through the method, noise in the blood vessel image can be effectively removed.

The invention discloses a tensor compression method based on energy gathering dictionary learning, and belongs to the field of signal processing. The method comprises the following steps: 1, respectively carrying out Tacker decomposition and sparse representation on tensor to obtain a dictionary, a sparse coefficient and a kernel tensor; 2, obtaining a new sparse representation form about the tensor according to the relationship between the sparse coefficient of the tensor and the kernel tensor; And 3, carrying out dimensionality reduction on the dictionary in the mapping matrix by utilizing an energy-gathered dictionary learning algorithm so as to realize tensor compression. According to the tensor compression algorithm based on energy gathering dictionary learning, tensor effective compression is achieved, compared with other compression algorithms, information of an original tensor can be more effectively reserved, and a better denoising effect is achieved.