166 results about "Preprocessing algorithm" patented technology

A system and method for recording and/or monitoring data by forwarding it, with or without analyzing or otherwise filtering the data itself. According to preferred embodiments of the present invention, the system and method are operative over IP networks. According to a preferred embodiment of the present invention, there is provided a system and method for forwarding data according to at least one characteristic of the data, such as the session's metadata for example, without analyzing or otherwise filtering the data itself. According to another preferred embodiment of the present invention, before the data is forwarded to the recording device, pre-processing algorithms are performed according to a system preset or according to one or more rules.

A method and apparatus are disclosed for an image preprocessing device that automatically detects chestwall laterality; removes border artifacts; and segments breast tissue and pectoral muscle from digital mammograms. The algorithms in the preprocessing device utilize the computer cache, a vertical Sobel filter and a probabilistic Hough transform to detect curved edges. The preprocessing result, along with a pseudo-modality normalized image, can be used as input to a CAD (computer-aided detection) server or to a mammography image review workstation. In the case of workstation input, the preprocessing results improve the protocol for chestwall-to-chestwall image hanging, and support optimal image contrast display of each segmented region.

A method of digitally equalising the sound from a loudspeaker that is placed in a certain room, said room having varying acoustic properties affecting the way a user perceive the sound, is corrected in a certain part of the room, by measuring one or more impulse responses through a microphone, said impulse responses being processed in a pre-processing algorithm, in at least two parallel frequency band correction algorithms and a post processing algorithm. As an option a pre-correction algorithm can be coupled between the pre-processing algorithm and the frequency band correction filters. The pre-correction algorithm is adapted to receive input representing measured loudspeaker characteristics under ideal condition in an anarchic room, and/or parameters from a reflections attenuation algorithm. From the post processing algorithm the final filter parameters are stored and used for correcting sound from a source connected to the amplifier feeding the loudspeaker to the acoustic behaviour of the actual room the loudspeaker is placed in. If any parameters in the room are changed then the correction method according to the invention can be repeated in order to set up new filter parameters.

Method and apparatus for determining alternans data of an ECG signal. The method can include determining at least one value representing at least one morphology feature of each beat of the ECG signal and generating a set of data points based on a total quantity of values and a total quantity of beats. The data points can each include a first value determined using a first mathematical function and a second value determined using a second mathematical function. The method can also include several preprocessing algorithms to improve the signal to noise ratio. The method can also include separating the data points into a first group of points and a second group of points and generating a feature map by plotting the first group of points and the second group of points in order to assess an alternans pattern of variation. The feature map can be analyzed by statistical tests to determine the significance difference between groups and clusters.

The invention discloses a pose identifying and grabbing device and method based on binocular vision. The device comprises a workpiece conveying module, an image collecting module and a target workpiece grabbing module. The workpiece conveying module is used for conveying a target workpiece to the position below a binocular camera through a conveying belt, when a proximity sensor installed below abinocular vision camera support receives an arrival signal of the workpiece, the conveying belt stops working, and a left industrial camera and a right industrial camera can collect images conveniently. The image collecting module collects the images and then transmits the images to a computer, pose information of the target workpiece is obtained after an image preprocessing algorithm and a pose identifying algorithm are used for processing, then the pose information is processed, track planning is conducted, and data are transmitted to the grabbing device; and a mechanical hand in the grabbing device is used for grabbing the workpiece and placing the workpiece to a designated area. By means of the pose identifying and grabbing device and method based on binocular vision, the pose information of the target workpiece can be detected, track planning is conducted, the grabbing device is used for grabbing the target workpiece, and efficiency is improved.

The invention provides a method for detecting the defects of a cosmetic paper label. The method judges whether a label is adhered on a correct position or not, whether the Chinese character identification is correct or not, whether the data is printed on a correct position or not, and whether the date identification is correct or not. A Chinese character extraction algorithm and an identificationalgorithm for different color information of a cosmetic label are designed. A pretreatment algorithm and a high precision identification algorithm for machine printed characters on a cosmetic label are designed. The algorithms are stable, thus the maintenance of the system is convenient, in production, the related control parameters are adjusted, then a start button is pressed down, and then the detection is automatically carried out without artificial monitoring.

The invention discloses an electrocardiogram signal feature detection algorithm based on wavelet transformation lifting and approximate envelope improving and belongs to a weak bioelectrical signal processing technology field. The current electrocardiogram signal detection technology applied clinically can not give consideration to both a detection precision requirement and a real time requirement. Electrocardiogram signal pretreatment algorithm based on wavelet lifting for improving semi-soft threshold denoising and approximate envelope improving and electrocardiogram feature detection algorithm based on a slope threshold are provided in the invention. Detection criterions are set based on waveform characteristics and time domain distribution characteristics of the electrocardiogram signals. Position detections of R wave, start-stop points of the QRS waves, P wave and T wave are carried out respectively to the electrocardiogram signals. The electrocardiogram signal feature detection algorithm provided in the invention is easy, quick and suitable for parallel processing, and occupies little memory space and is convenient for DSP chip realization. Even in strong noise and P/T wave interference circumstances, R point position can be accurately detected through the algorithm provided in the invention. An R wave false detecting rate of 105 data containing serious noise disturbance is only 0.27% compared with MIT-BIH Database annotation.

The present invention is a method and system for interactive rendering of large polygonal environments on commodity PC hardware. The system allows a user to walk through a large model at interactive frame rates on machines with limited memory. It works by first creating a hierarchical spatial decomposition of the model on disk using a fast and incremental out-of-core preprocessing algorithm. At running time, the system and method uses an approximate from-point visibility algorithm to dynamically determine which parts of the model to retrieve from disk. Multiple threads and a speculative prefetching algorithm are used to improve frame rates.

The invention discloses a channel state information transmission method and equipment, aiming at solving the problems that the accuracy of channel state information that can be provided is limited dueto the limitation of a codebook structure in the prior art and a transmission scheme that a base station adopts an advanced preprocessing algorithm is not adapted. The method includes the following steps: a terminal determines a basis matrix according to a candidate beam vector set, wherein the basis matrix is a matrix formed by N beam vectors in the candidate beam vector set, and N is a positiveinteger; the terminal determines a merging coefficient matrix according to the basis matrix and channel state parameters; and the terminal feeds back identification information of the basis matrix and the merging coefficient matrix to the base station. Thereby, the accuracy of channel state information feedback can be effectively improved, and the performance of multi-antenna transmission, especially MU-MIMO transmission can be improved.

The invention belongs to the technical field of sleep monitoring, and relates to a single-lead electroencephalography (EEG) automatic sleep staging method. The method comprises the following steps: (1) performing signal pre-processing; (2) extracting classification features; (3) carrying out sleep staging. The method provided by the invention has the advantages that 1, a pre-processing algorithm is designed to obtain single-lead EEG signals with better quality; 2, the method extracts multiple features from the time domain, the frequency domain and the nonlinear domain, and screens out the representative features; 3, a random forest model is adopted, so that over-fitting does not need to be worried about; the method has a good anti-noise ability, and the staging results of all decision trees can be obtained, so that the confidence probabilities of the random forest for all sleep stages are obtained; 4, a D-S evidence theory is combined, so that the accuracy rate of the sleep staging isfurther improved.

The invention discloses a brain health screening method based on portable EEG equipment. The method comprises an EEG signal collecting and judging step. The EEG signal collecting and judging step comprises the following steps of 1, performing signal sensing through a 1-4 lead high-sensitivity electrode plate; performing original EEG signal collection; and performing signal stability test on original signals through an impedance test module. After original EEG signals are collected through the portable EEG equipment, synchronous signal amplification is performed; the EEG signal transmission isperformed through wireless transmission; the EEG signal receiving at a mobile terminal is realized; the received signals are communicated with the cloud and are stored; signal recognition is performedthrough an EEG pre-processing algorithm, an EEG signal recognition algorithm, a corresponding EEG machine learning algorithm and a deep learning algorithm; and through the analysis and calculation oncollected data by the brain signals of people of different kinds in different states, the measurement and evaluation on various indexes in aspects such as brain functions and brain mental health areperformed.

The invention belongs to the technical field of unmanned ship navigation control, and specifically relates to anunmanned ship track planning method based on deep optimization. The unmanned ship trackplanning method based on deep optimization comprises the following steps that rasterized map information is read, starting and ending points are set, the obtained starting point and reachable neighbornodes in the eight directions of the starting pointare added to theopenlist; the point with the smallest F value in the openlistis searched for and set as the current node; whether the current node is the ending point or not is determined; if yes, then path searching is over; if not, then the current node is utilized to search for a next jump-point based on a jump-point search strategy; whether the jump-point is in the openlistor not is determined, and the point with the smallest F value is continuously searched for; and an optimal path is outputted. According to the unmanned ship track planning method based on deep optimization,the execution efficiency of grid method track planning algorithm is greatly improved based on the jump-point search optimization preprocessing algorithm,an path turning point is optimized, and finally a smooth navigation track is outputted.

The invention discloses an automatic large-size workpiece measurement system based on machine vision, and belongs to the technical field of machine vision measurement. The automatic large-size workpiece measurement system comprises an automatic large-size workpiece measurement hardware system and an automatic large-size workpiece measurement software system. The automatic large-size workpiece measurement hardware system comprises a light source, a camera, a lens and a high-accuracy moving device. The automatic large-size workpiece measurement software system comprises an image preprocessing algorithm, image data conversion modeling, a subpixel line/arc detection algorithm based on an improved RANSAC, and dimension calculation. The large-size workpiece can be measured by the system, and thesystem fills in the blank of application of machine vision in the field of large-size workpiece measurement. The software system can effectively eliminate noise and null points from an image and canrectify a non-uniform background. Production efficiency, stability and measurement accuracy of the system are improved.

The present invention provides an iris preprocessing algorithm based on space distance circle marking edge detection. The method comprises a first step of performing image acquisition on an iris of a human eye through a photographing device, thus to obtain an original gray level image; a second step of carrying out noise processing on the acquired image by using a median filtering algorithm; a third step of decomposing the iris image into four subband images by utilizing Haar wavelets; a fourth step of carrying out edge detection on an inner edge of the iris by using Canny operators; a fifth step of carrying out precision positioning of an inner circuit of the iris by using a sub pixel circle positioning algorithm; and a sixth step of carrying out accurate positioning on an outer circuit by using a method of increasing searching radius step length. According to the iris preprocessing algorithm based on the space distance circle marking edge detection, the Canny operators are utilized for filtering, enhancement and detection, the sub pixel circle positioning algorithm is utilized for carrying out accurate positioning of the inner circle of the iris, and the efficiency of circle detection operators is promoted by using the method of increasing the searching radius step length, thereby realizing accurate positioning of the outer circle of the iris, raising the detection precision, and promoting the detection speed.

The invention discloses an R wave detection algorithm based on extremum field mean mode decomposition and improved Hilbert enveloping and belongs to the technical field of weak biological signal processing. An electrocardio signal pre-processing algorithm based on the extremum field mean mode decomposition and the improved Hilbert enveloping and an R wave detection algorithm based on slope threshold are provided. Detection criteria are set according to wave form characteristics and time domain distribution characters of electrocardio signals, and positions of R waves with most obvious characters and highest information amount in the electrocardio signals are detected. An extremum field mean mode decomposition algorithm improves empirical mode decomposition speed and can effectively restrain mode superimposition and boundary effect. The improved Hilbert enveloping can effectively restrain interference of noise and other characteristic waves an can also enhance energy of the R waves. The R wave detection algorithm based on the extremum field mean mode decomposition and the improved Hilbert enveloping can also detect positions of R points accurately even if interference of strong noise and large P/T waves exists. A Massachusetts institute of technology-Beth Israel hospital (MIT-BIH) data base is used for detecting the R wave detection algorithm. Sensitivity of the R wave detection algorithm is 99.94%, and positive predictive rate is 99.87%.

The invention discloses a running chart line addition optimization method based on a multi-target mixed-integer programming model in the high-speed railway operation management field. According to themethod, station line allocation, a departure time window of a departure station, a train stop scheme, acceleration/deceleration consumed time and other actual factors are comprehensively considered,simultaneous minimization of running time of newly added lines and adjustment amplitudes of existing lines is used as an optimization target, and running demands of the newly added lines and running demands of the existing lines are both considered. Through decomposition of an original large-scale problem in combination with a preprocessing algorithm, high-speed railway running chart line additioncan be efficiently realized.

The invention discloses a Raman spectrum preprocessing method. The method comprises a wavelet denoising stage, an asymmetrical least square method denoising stage, a standard normalization processing stage and a cubic smoothing spline fitting processing stage, wherein in the asymmetrical least square method denoising stage, by designing a special gate circuit to replace a software processing method of an asymmetrical least square method baseline correction algorithm in a preprocessing system, the processing capacity and the preprocessing effect of a Raman spectrum signal preprocessing system are improved, and in the same processing time condition, the effect of a Raman spectrum preprocessing algorithm can tend to be restrained to better effect through multiple iterative processing. The idea can be widely applied to other spectrum signal preprocessing systems.

The invention discloses a ship waterline extraction method. The ship waterline extraction method is combined with an image processing technology, extracts an effective area by the combination of frame-to-frame differences and the preprocessing algorithm of morphological close operation, enhances the intensity of a target area and reduces noise intensity through a threshold value algorithm based on a triangular membership function relationship, and carries out image binarization through a Otsu algorithm. Then, according to the width of an image, a reasonable sampling proportion is selected, the edge points of a water gauge are scanned and extracted from top to bottom, and the sampled edge points are subjected to interpolation processing so as to obtain a real waterline. The ship waterline extraction method has the advantages of wide applicable range, high measurement efficiency and the like, lowers the interference of human factors and reduces manpower, material resources and transaction cost.

The invention provides a face and voiceprint authentication system and method based on deep transfer learning. The face and voiceprint authentication system comprises: a user side module used for collecting and constructing a human face and voiceprint image data set and returning a verification result; a training module whichcomprises a data preprocessing algorithm, a user living body detection algorithm, construction of a deep convolutional neural network model, fusion of a transfer learning algorithm, training of the convolutional neural network model and a model integration algorithm of theconvolutional neural network; and the data and model storage module comprises storage of a face data set and a voiceprint data set and storage of a face recognition model and a voiceprint recognitionmodel which are trained by the network model. According to the invention, face recognition and voiceprint recognition are applied to the system verification process, a user does not need to input a user name and a password and other operations, so that the system login process is simpler and more convenient, the user does not need to worry about the problem that the user name and the password arestolen and forgotten, and the login experience of the user is improved.

The invention discloses an electrocardiosignal characteristic detection algorithm, and provides an electrocardiosignal preprocessing algorithm combining an improved lifting wavelet threshold and an improved approximate enveloping algorithm. Compared with wavelet denoising, improved lifting wavelet threshold denoising has the advantages that the signal processing time is shortened, the signal-to-noise ratio is increased, the design of an envelope function is improved, and other characteristic waves except R waves and the energy of noise are suppressed while the R-wave energy is enhanced. The characteristic detection algorithm based on a slope threshold is designed, and detection of R waves, P waves and T waves is performed respectively. The detection algorithm is simple and quick, and is suitable for parallel processing. The occupied memory space is small, and the R-wave detection rate can be up to 99.8 percent.

The invention discloses a multi-sensor based smart automobile environment perception method. The technical scheme aims to solve the technical problems of single perception measure and difficulty in accurately, comprehensively and fully extracting information of an environment surrounding an automobile in an existing automobile environment perception system. According to the technical scheme, detection of objects surrounding the automobile by 360 degrees and a front lane line recognition function are realized by a multi-perception environment sensor consisting of an ultrasonic radar sensor, a millimeter radar sensor and a camera sensor through a sensor data preprocessing algorithm, a multi-sensor data fusing algorithm and a target tracking algorithm, and 360-degree perception for the automobile can be realized truly.

The invention provides a low-power-consumption real-time noise-reduction and sharpening merged preprocessing algorithm for a CMOS image sensor. The low-power-consumption real-time noise-reduction and sharpening merged preprocessing algorithm aims to solve the problems that in the prior art, according to a CMOS image sensor image preprocessing method, a denoising algorithm and a sharpening algorithm are executed separately, the algorithm is high in complexity, and saving hardware resources and reducing the total power consumption are not facilitated. By means of the low-power-consumption real-time noise-reduction and sharpening merged preprocessing algorithm, input light signals are divided into three primary colors of red, green and blue (RGB), namely three kinds of pixels RGB through a color filter array (CFA), data cache is conducted in the mode that data are stored in a on-chip blocked and classified mode, the noise of the pixels RGB is reduced through a space self-adaptive noise reduction algorithm, an laplace operator and a smoothness operator are combined to generate a new operator model, and sharpening processing is conducted on the G pixel through the new operator model. The low-power-consumption real-time noise-reduction and sharpening merged preprocessing algorithm has the advantages that noise reduction and sharpening are merged together, complexity is lowered greatly, hardware overhead and total power consumption are reduced greatly, the hardware design difficulty is lowered, the processing speed is increased, performance is better, and the algorithm is easy to implement.

The invention discloses an image registration method based on feature points, and relates to the technical field of image registration. The method comprises the following steps: a, preprocessing a reference image and an image to be registered by adopting a wavelet transform threshold denoising method; b, extracting feature points by an SIFT algorithm; c, describing the feature points by adopting adeformation dimension reduction method; d, performing rough matching on the feature points according to cosine similarity; and e, eliminating part of mismatching by adopting an improved RANSAC algorithm to obtain a matching point pair with relatively high matching precision. Images are preprocessed by using a wavelet transform threshold denoising method before feature points are extracted, part of noise in the image is eliminated, so that the purity of the feature points is improved, a deformation dimension reduction method is provided for describing the extracted feature points when the feature points are described, SIFT descriptor dimensions are reduced, the algorithm operation time is shortened. The matched feature point pairs are optimized by adopting a method of combining rough matching and fine matching, so that the matching accuracy of the algorithm is improved.