36results about How to "Full details" patented technology

The invention discloses an image enhancement method implemented through histogram equalization. The method comprises the following steps: a digital image required to be enhanced is input into the MATLAB software so as to obtain a matrix expression f (m, n); then, the average brightness value Y of the image f (m, n) is calculated, and the maximum value Kmax and minimum value Kmin of gray values K of pixels in all pixels of the image f (m, n) are calculated; according to the Kmax, the Kmin and the Y, an original image is divided into two subimages in gray intervals [Kmin, Y] and [Y, Kmax], and the average brightness values Y1 and Y2 of the two subimages in the gray intervals of [Kmin, Y] and [Y, Kmax] are calculated, and finally, the original image is divided into subimages in gray intervals [Kmin, Y1], [Y1, Y], [Y, Y2] and [Y2, Kmax]; and according to the gray value K of each pixel in the original image f (m, n), carrying out histogram equalization through a histogram equalization formula of a gray interval at which the pixel is located; and then a brightness preservation based enhanced image is output, wherein the output enhanced image is good in effect.

The invention discloses a Web GIS (geographical information system)-based comprehensive alarm display method. The method comprises the following steps: importing the tower and plant station data with geographic information to a GIS spatial database, and connecting the towers in the same circuit to form a circuit based on the sequence of tower numbers according to the circuit and the tower numbers of the towers; importing the information in the GIS spatial database; calling a display interface provided by a GIS service platform; performing layered drawing on power equipment on a Web browser according to equipment types and voltage grades to form a comprehensive display page; associating a service sub-system with the comprehensive display page to organize all comprehensive alarms according to the equipment, and organizing all comprehensive alarms associated with the same equipment together to form an comprehensive alarm array of the equipment. By adopting the Web GIS-based comprehensive alarm display method, the alarm information of sub-systems such as a power transmission and transformation monitoring system, a power grid scheduling automation system and a prudential system is integrated, and the alarms are classified, so that the comprehensive alarm information of the power grid can be learnt more visually, intuitively and thoroughly.

The invention provides a steel plate surface defect image extraction method. The method is characterized by including the following steps that steel plate surface images are subjected to ROI detection, and non-defect images are removed; defect images are sequentially read, the images are preprocessed, the influences of noise and non-uniform illumination on the defect segmentation effect are removed, and the foreground and background contrast ratio is increased; the preprocessed steel plate defect images are subjected to defect region segmentation extraction through Center-Surround Difference, and finally data is output. The efficiency of an image extraction algorithm is improved, it is not needed to occupy large memory space, real-time processing is convenient, the influence of the noise is effectively weakened, wrong extraction, caused by illumination and brightness unevenness, of the images is avoided, the contrast ratio is increased, the defect extraction effect is more excellent, and details are complete.

The invention relates to a pig face recognition method adopting a multi-channel convolutional neural network. The pig face recognition method is technically characterized by comprising the steps of collecting a pig face data image and constructing a pig face data set for multi-channel convolutional network training; constructing a multi-channel convolutional network model: extracting eye featuresby using two shallow networks, fusing the eye features, extracting the overall image features of the pig face by using a deep network, and inputting a fusion result of the last three networks into a standard support vector machine; training a multi-channel convolutional network model and performing parameter adjustment optimization; testing the recognition performance of the network model to obtain a trained network model; and shooting and numbering the pig individuals with the face images stored in the database, and inputting shot image data into the trained network model to obtain a pig facerecognition result. According to the pig face recognition method, the image features with large individual differences are added on the basis of end-to-end, so that the robustness is high, and non-contact pig face individual recognition is achieved, and the stress response of pigs is reduced, and the automatic management level of a pig farm is improved.

The invention provides a method for reconstructing and displaying a billion-pixel high dynamic range image. The method comprises the step of acquiring a plurality of million-pixel level sub-images, the step of splicing the acquired sub-images into a billion-pixel spherical surface image and adjusting the dynamic range of the spherical surface image, and the step of displaying the spliced image to a user in an interactive mode according to the demands of the user. According to the method, a panoramic image with integral details and different dynamic ranges can be acquired, and the user can integrally take out and display the concerned partial image conveniently.

The invention discloses a paper base three-dimensional printing method based on NSDTF-DEM data. The method comprises the steps that firstly, the NSDTF-DEM data are converted into DEM data of an ArcInfo ASCII Grid format; secondly, three-dimensional surface constructing of the DEM data is conducted according to the grid calculation principle and the regular grid generating triangular mesh curved surface algorithm, and three-dimensional modeling of the DEM data is conducted according to the three-dimensional surface through the methods of shifting, stretching and cutting; and finally, the three-dimensional model of the DEM is layered according to the equal layer thickness layering principle, the three-dimensional model of the DEM is printed and output through the paper base three-dimensional printing method. According to the paper base three-dimensional printing method, the modeling process of the DEM data is rapid, stable and high in precision, the three-dimensional printing time is shortened, and environment protection is achieved; moreover, other backing materials are not needed in the printing process, the obtained three-dimensional printing model can completely present the three-dimensional morphology of digital elevation model data, and the printing precision of mountains and rivers is also high.

The invention discloses a salt and pepper noise filtering method based on a similar function, comprising the steps of setting an image filtering window in a 8-bit gray level image, determining noise pixels or suspected noise pixels through central pixel gray level values, and otherwise, judging the pixels to be signal pixels, establishing a marking matrix to mark the noise pixels, eliminating the pixel points in the filtering window, wherein the gray levels of the pixel points are identical to that of the central pixels, constituting a first signal point set by using the signal points which satisfy the marking matrix elements, processing the signals in the first signal point collection to obtain a first output image, setting the marking matrix element corresponding to the position of the output pixel in the output image to finish the filtering processing. The invention has better capability of denoising and maintaining details.

The invention relates to an intravascular image fusion method and system and an image acquisition device, and the method comprises the steps: collecting a first modal image and a second modal image ina blood vessel at the same time, and enabling the first modal image and the second modal image to belong to different types of modal images; fusing the first modal image and the second modal image byadopting an image fusion algorithm to obtain a corresponding fusion image. According to the method, the OCT image and the IVUS image are fused, the advantages of the OCT image and the IVUS image arebrought into full play, meanwhile, the complementary defects of the OCT image and the IVUS image are overcome, in other words, the advantages of the strong tissue penetrating power of the IVUS and thehigh resolution of the OCT image are brought into full play, and finally the high-quality fused image is obtained.

The invention discloses a face image synthesis method based on adaptive expression. By using the method, problems that synthesized image definition is low and details are not complete in an existing method are solved. The method comprises the following steps of firstly, processing a database, carrying out image filtering on all the images, then partitioning the images and extracting an image block characteristic so as to obtain one training image block dictionary and two photograph block dictionaries; secondly, testing whether a photograph block includes edge information or face characteristic information, according to that, selecting different dictionaries and searching a neighbor block; and finally, using a Markov network model to obtain image blocks to be synthesized, fusing all the image blocks to be synthesized and acquiring the synthesized image. Compared to the prior art, by using the method, a synthesis result possesses high definition and complete details and can be used for face retrieval and identification.

The invention discloses a face figure synthetic method based on coupling neighbor indexes, mainly solving the problem that a present method does not consider the training figure effect in neighbor selection. The method comprises the steps of: 1, diving a training figure sample set, a training photograph sample set and a test sample set; 2, diving all images into image blocks and forming block sets; 3, diving training photograph block sets and corresponding image blocks sets into a plurality of subsets; 4, establishing the indexes of each pair of photograph-image block in the training photograph block subsets and training image block subsets to K neighbor pairs thereof; 5, searching for a nearest neighbor of each test photograph block, and furthermore obtaining K neighbors thereof; 6, utilizing a Markov weight network to solve a reconstruction weight; 7, solving an image block to be synthesized; and 8, iteratively executing steps 5-7 for N times, and obtaining a finally synthesized image through fusion. Compared with the prior art, the synthesized image has higher definition and more complete details, and can be used for face retrieval and identification.

The invention discloses a three-dimensional model processing method and device, and a storage medium. The method comprises the steps of obtaining a target object three-dimensional model and a reference three-dimensional model; searching a target point which is closest to the vertex in the reference three-dimensional model in the target object three-dimensional model to obtain a first closest pointpair set; determining a normal direction corresponding to a target point in the nearest point pair and a nearest point pair direction between each nearest point pair in the first nearest point pair set, wherein the nearest point pair direction faces the target point; taking the nearest point pair corresponding to the condition that the angle between the nearest point pair direction and the normaldirection is less than or equal to a preset angle threshold as a second nearest point pair set; determining an updated reference three-dimensional model according to the second nearest point pair setand a point-to-surface constraint formula; performing iterative optimization based on the updated reference three-dimensional model until a preset convergence condition is reached; determining a target optimal solution of a point-to-surface constraint formula when a preset convergence condition is reached; and obtaining a target three-dimensional model matched with the target object three-dimensional model.

The present invention provides a resolution improvement based film and TV works renovation method for film and TV works with low resolution and low definition. The method includes the specific steps of firstly, acquiring a resolution of an original video and a target resolution, and calculating a zoom ratio; then, segmenting an input video into an image frame set according to a certain segmentation manner; then, performing conversion according to a prestored mapping relation, so as to obtain high resolution video frames; and finally, combing the high resolution video frames to obtain a high resolution video. The prestored mapping relation is obtained by learning a hybrid expert model, and the process is finished offline in a computer. The method has the advantages of good adaptability, fast speed, good effect, expandability and so on.

The invention provides a combined optimizing and training method for the multi-dictionary learning of image sparse representation, which belongs to the multi-media communication and image data processing field, and is characterized by: regarding the non-zero element in the singular value matrix after the singular value decomposition of the gradient matrix of the training image unit as the energy value of the gradient direction; according to set the energy value parameter threshold, dividing the image unit into various isotropic images and various anisotropic images; learning successively a shared dictionary and a specialized dictionary; optimizing the factors to minimize the objective function such as the residuals of the isotropic and anisotropic images after the sparse representation, the autocorrelation and the degree of cross-correlation of each dictionary, and the regularization of nonzero element; in the optimization process, using the orthogonal matching and tracking algorithm to optimize A0 and Ak, and then optimizing D0 and Dk by the gradient descent algorithm; and in keeping the parameters to be optimized, regarding the items not involving the parameters as constants. When the method is used for image compression, the details could be well preserved, a low distortion rate is achieved and a good image quality could also be achieved.

The invention discloses a multi-sensory-mode continuous attention monitoring system and method. The multi-sensory-mode continuous attention monitoring system comprises front-end monitoring equipment, a server and a display terminal, the front-end monitoring equipment is connected with the server and is used for setting and presenting visual stimulation pictures or auditory stimulation sounds, receiving key responses and collecting state video information of a testee in the monitoring process; the server performs data analysis according to the collected user response signal and video information, and the server is connected with the display terminal; the display terminal is provided with a graphical display interface for playing back a video of a state in a user monitoring process; the system is simple in structure and convenient to use and comprises a visual mode and an auditory mode, the tested state is monitored through a video method while monitoring is conducted, and testing effectiveness is ensured; and the periodic signal percentage is put forward as an index for monitoring continuous attention, the hyperactivity condition of a subject in different periods is described, more comprehensive and detailed information can be provided for continuous attention monitoring, and simultaneous monitoring of multiple persons is achieved.

The invention discloses a gas ash microscopic image segmentation method and system based on a full convolution residual network, and belongs to the technical field of image processing. The method comprises the following steps: S1, constructing a data set; S2, constructing a full convolutional neural network model; S3, constructing a full convolution residual error network model; and S4, carrying out segmentation test on the gas ash microscopic image. According to the invention, the gas ash microscopic image can be segmented accurately; an image segmentation effect comparison experiment is carried out; the FCRN network shows a good segmentation effect, the MIoU index reaches 90.15%, the contour of the segmented image is clear, details are complete, semantic segmentation of the gas ash microscopic image is realized, a foundation is laid for subsequent accurate identification of gas ash components, and the method is worthy of popularization and application.

The invention discloses a face portrait compositing method based on Bayesian inference, which mainly solves a problem that an existing method does not consider similarity constraints between adjacent image blocks in a neighbor finding or weight solving stage. The scheme of the face portrait composting method comprises the steps of 1, dividing a training portrait sample set, a training photo sample set and a test sample set; 2, dividing all images into image blocks and forming block sets; 3, dividing the training photo block set and the corresponding portrait block set into a plurality of subsets; 4, selecting nearest neighbor blocks from a training photo-portrait block set; 5, carrying out neighbor block reselection on the nearest neighbor blocks according to an Euclidean distance in the training photo-portrait block set, and solving a linear combination weight of the reselected neighbor blocks; 6, solving portrait blocks to be composited according to the neighbor blocks and the combination weight; and 7, iteratively executing the steps 5-6 for N times, and fusing to acquire a final composite portrait. The face portrait composting method has the advantages of high resolution of a composite result and more complete details, and can be applied to face retrieval and recognition.

The invention discloses a microexamination method for the forms of fishes laying drifting eggs at different developmental stages of the early phase. The microexamination method is characterized by being composed of a development form observation method from fertilization of the drifting eggs to the tail bud stage, a development form observation method from the muscle effect stage to the early hatching stage and a development form observation method of hatched fry. According to the method, the problems that due to the fact that from fertilization to the tail bud stage of the drifting eggs, theembryos are small, and the egg envelopes are large, the germ cells suspend in water, the embryos suspend in the egg envelopes and flow in pairs, and the best shooting angle is hard to find can be solved. Then the problems that from the muscle effect stage to the early hatching stage, the embryos crouch in the egg envelopes and turn over, and a complete embryo image is hard to obtain are solved. Finally, the problem that due to the fact that the fry is hyperactive easily after being hatched, the shooting picture cannot be fixed is solved. Practice proves that the method is used for microexamination of the drifting eggs or the fry, the shooting angle is adjustable, the embryo development picture is easy to capture, the fry rarely fades or dehydrates, the shooting effect is alive, and the details are complete.

The invention discloses a microexamination method for the forms of fishes laying drifting eggs at different developmental stages of the early phase. The microexamination method is characterized by being composed of a development form observation method from fertilization of the drifting eggs to the tail bud stage, a development form observation method from the muscle effect stage to the early hatching stage and a development form observation method of hatched fry. According to the method, the problems that due to the fact that from fertilization to the tail bud stage of the drifting eggs, theembryos are small, and the egg envelopes are large, the germ cells suspend in water, the embryos suspend in the egg envelopes and flow in pairs, and the best shooting angle is hard to find can be solved. Then the problems that from the muscle effect stage to the early hatching stage, the embryos crouch in the egg envelopes and turn over, and a complete embryo image is hard to obtain are solved. Finally, the problem that due to the fact that the fry is hyperactive easily after being hatched, the shooting picture cannot be fixed is solved. Practice proves that the method is used for microexamination of the drifting eggs or the fry, the shooting angle is adjustable, the embryo development picture is easy to capture, the fry rarely fades or dehydrates, the shooting effect is alive, and the details are complete.

The invention discloses a real-scene three-dimensional model and three-dimensional simulation model hybrid loading method and relates to the field of graphic images. The method is characterized by, to begin with, optimizing a three-dimensional simulation model by utilizing a real-scene three-dimensional model; then, carrying out block division on the real-scene three-dimensional model and the three-dimensional simulation model; thirdly, designing hybrid loading parameters; and finally, carrying out real-scene three-dimensional model and three-dimensional simulation model hybrid loading when camera parameters change in a three-dimensional scene according to the hybrid loading parameters. The method comprehensively utilizes different advantages of two data resources of the real-scene three-dimensional model and the three-dimensional simulation model; and at the macro level, advantages of real color and rich details of an oblique photography model are utilized, and at the micro level, the advantages of complete details and clear textures of three-dimensional simulation are utilized, so that a purpose of carrying out real presentation of a city is achieved, the problem that it is difficult to express city macro and micro forms and colors at the same time by merely utilizing the real-scene three-dimensional model or the three-dimensional simulation model separately is solved, and an application effect of a three-dimensional digital city is improved.

The present invention provides a high -pressure cable porcelain sleeve end infrared image filtering method.An infrared image filtering method of high -voltage cable porcelain set, including the following steps: S1. Enter the infrared image of the high -pressure cable porcelain set terminal to be treated; set the threshold to divide the pixels of infrared images into useful signal points andSuspicious noise points; s3. Do not process the useful signal point, and the noise point of suspicious noise points is further exfoliated based on its neighborhood; S4.The filtering method of the present invention first divides the pixels of infrared images into useful signal points and suspicious noise points, and further processing the suspicious noise point can achieve better noise effects.

The invention discloses a face image synthesis method based on adaptive expression. By using the method, problems that synthesized image definition is low and details are not complete in an existing method are solved. The method comprises the following steps of firstly, processing a database, carrying out image filtering on all the images, then partitioning the images and extracting an image block characteristic so as to obtain one training image block dictionary and two photograph block dictionaries; secondly, testing whether a photograph block includes edge information or face characteristic information, according to that, selecting different dictionaries and searching a neighbor block; and finally, using a Markov network model to obtain image blocks to be synthesized, fusing all the image blocks to be synthesized and acquiring the synthesized image. Compared to the prior art, by using the method, a synthesis result possesses high definition and complete details and can be used for face retrieval and identification.

The invention brings forward a picture renewing method based on resolution improvement, and is applied to pictures with quite low resolution and quite low sharpness. First of all, pictures are preprocessed and trained, secondly, a mapping relation model based on a hybrid expert model is obtained, next, low-resolution pictures to be processed are segmented to blocks, and finally, according to the mapping relation model, the low-resolution pictures are improved to high-resolution pictures. The method provided by the invention has the advantages of good adaptability, fast speed, good effect, high expansibility and the like.

The invention brings forward a picture renewing method based on resolution improvement, and is applied to pictures with quite low resolution and quite low sharpness. First of all, pictures are preprocessed and trained, secondly, a mapping relation model based on a hybrid expert model is obtained, next, low-resolution pictures to be processed are segmented to blocks, and finally, according to the mapping relation model, the low-resolution pictures are improved to high-resolution pictures. The method provided by the invention has the advantages of good adaptability, fast speed, good effect, high expansibility and the like.

The invention discloses a small-sample high-resolution remote sensing image scene classification method. The method mainly comprises the following three parts: firstly, preparing source domain and target domain training sample sets, respectively selecting a proper amount of images from different remote sensing scene data sets to respectively construct a source training sample set with a large number of samples and a target domain training sample set with a small number of samples, and simulating the condition of small sample classification; secondly, AlexNet is selected as a DCNN main network, and deep convolution feature extraction is carried out on the sample image in combination with an FPN network layer fusion strategy; and finally, realizing feature distribution migration from a source domain to a target domain by using an improved distribution adaptation algorithm WS-BDA based on single sample weighting, and training a target classifier by using migrated feature data to finish classification of remote sensing scene images.

The invention provides a digital radiographic inspection integrated control system. The digital radiographic inspection integrated control system comprises a process control module, a visual monitoring module, a process setting module, an image processing module and a quality management module; the process control module communicates with a PLC to obtain equipment operation state data, and the visual monitoring module has two functions of detection process monitoring and detection result visualization; the process setting module sets parameters in the detection process, and the image processing module performs preprocessing of image correction and contrast adjustment on the obtained digital image and uploads the processed result to the film evaluation platform; and the quality management module completes statistics of detection results and performs prediction maintenance according to equipment state data. According to the invention, processes of process setting, process control, visual monitoring, image processing, quality management and the like involved in the digital radiographic inspection process are integrated on a software platform, the inspection process is managed and controlled in a centralized manner, and the digital radiographic inspection efficiency is improved.

The invention provides a method for reconstructing and displaying a billion-pixel high dynamic range image. The method comprises the step of acquiring a plurality of million-pixel level sub-images, the step of splicing the acquired sub-images into a billion-pixel spherical surface image and adjusting the dynamic range of the spherical surface image, and the step of displaying the spliced image to a user in an interactive mode according to the demands of the user. According to the method, a panoramic image with integral details and different dynamic ranges can be acquired, and the user can integrally take out and display the concerned partial image conveniently.

The invention discloses a procedure for emergency room cardiopulmonary resuscitation (ERCPR), and relates to the technical field of cardiopulmonary resuscitation operation processes. When cardiac arrest is diagnosed, four teams (divided into four roles A, B, C and D) are immediately formed, cardiopulmonary resuscitation is immediately carried out by the group members according to a C-A-B principle, A / C pressing is conducted till the Lucas cardiopulmonary resuscitation machine is installed, then A assists B in preparing tracheal intubation articles, B carries out airway management, firstly, a balloon mask is used for ventilation, trachea intubation is conducted after Lucas are installed, the A and C are matched with the B at a ratio of 30: 2 for pressing and ventilation, C connects a defibrillation monitor to the patient, immediately holds the carotid artery pulsation by a hand to judge the pressing quality for 5 seconds after defibrillation preparation is made, then immediately defibrillates if a defibrillable heart rate exists, places Lucas together with A after defibrillation (or not defibrillated), C establishes a vein channel, draws blood and applies medicines, D prepares Lucasand starts the machine, A installs the machine after self-inspection is completed, and D is responsible for recording time and controlling cardiopulmonary resuscitation quality.