160 results about "Image post processing" patented technology

In an image post-processing method and apparatus for 3D visualization of 2D / 3D fused image data for use in catheter angiography in an endovascular interventional procedure, upon forward movement of a micro-catheter through blood vessel in the interventional procedure, x-ray images are acquired from different projection directions and are subjected to a pattern recognition algorithm for edge-based segmentation of the image regions filled by the micro-catheter, with all remaining image regions being masked out. The segmented projection exposures are prepared by a 3D reconstruction algorithm to obtain an image data set for (pseudo-) three-dimensional representation of the micro-catheter. This image data set are intraoperatively registered and fused with an image data set acquired from an angiographic pre-examination for three-dimensional visualization of the vessel topography. The reconstructed 3D representation of the catheter is mixed into the three-dimensionally prepared representation of endovascular blood vessel sections to be treated.

A marker-coordinate detecting unit detects coordinates of a stent marker on a new image when the new image is stored in an image-data storage unit; and then a correction-image creating unit creates a correction image from the new image through, for example, image transformation processing, so as to match up the detected coordinates with reference coordinates that are coordinates of the stent marker already detected by the marker-coordinate detecting unit in a first frame. An image post-processing unit then creates an image for display by performing post-processing on the correction image created by the correction-image creating unit, the post-processing including high-frequency noise reduction filtering-processing, low-frequency component removal filtering-processing, and logarithmic-image creating processing; and then a system control unit performs control of displaying a moving image of an enlarged image of a set region that is set in the image for display, together with an original image.

The invention relates to a videography processing method and a videography processing system supporting face detection. One frame image that is obtained by videography is processed through face detection, and whether a face exists in the frame image is determined according to a detecting result; if the face exists in the frame image, image characteristic information of a face area is acquired, and one or more image control parameters are adjusted by taking the image characteristic information of the face area as a basis or one of the bases; correspondingly, the videography processing system comprises an imaging device and a camera processing chip connected with the imaging device; and the camera processing chip comprises an image processing module, an image post-processing module, a face detecting module and a memory module which saves a training model library used for face detection. The videography processing method and the videography processing system can support the videography processing for face detection, so as to achieve better videography effect.

The invention relates to a 3D composite material prefabrication piece robot sewing system, which comprises a robot, a single-face sewing machine, a structured light vision sensor and an image processing unit; the single-face sewing machine is connected with a shell of the structure light vision sensor and fixed at the tail end of an arm of the robot; the structured light vision sensor comprises a laser and a CCD video camera which are respectively fixed inside an shell of the structured light vision sensor, the included angle of a light axis centerline of the CCD video camera and a laser structure light surface of the laser is 30 to 60 degrees, which is perpendicular with the work-piece surface of a sewing material; the image processing unit comprises an image acquisition card, a PC machine and an image processing program library, the image processing program library comprises a sewing material type identification module, an image pre-processing module, an image post-processing module and a control capacity output module; the CCD video camera is connected with the image acquisition card through an video data line, the image acquisition card is arranged inside a main board slot of the PC machine, the PC machine is connected with the robot through a serial port.

An image processing accuracy estimation unit estimates an image processing accuracy by calculating a size of an object by which the accuracy of measurement of the distance of the object photographed by an on-vehicle camera becomes a permissible value or less. An image post-processing area determination unit determines, in accordance with the estimated image processing accuracy, a partial area inside a detection area of the object as an image post-processing area for which an image post-processing is carried out and lattices the determined image post-processing area to cells. An image processing unit processes the image photographed by the on-vehicle camera to detect a candidate for object and calculates a three-dimensional position of the detected object candidate. An image post-processing unit calculates, in each the individual cell inside the determined area the probability as to whether the detected object is present and determines the presence / absence of the object.

The invention discloses a CMR image segmentation and classification system comprising an image preprocessing module and an image segmentation and classification module. The image preprocessing moduleis used for obtaining and cutting an original CMR image and obtaining a target area image; the image segmentation and classification module is a trained convolutional neural network and comprises an encoder, a decoder and an image post-processing module; wherein the encoder comprises a convolutional layer, a spatial pyramid pooling layer and a first softmax classifier which are connected in sequence; a shallow feature map of the target area image is output by the convolutional layer; the first softmax classifier outputs a deep feature map and a classification result of the target area image; the decoder is used for fusing the shallow feature map and the deep feature map to obtain a segmentation probability response map; and the image post-processing module is used for obtaining a segmentation mask of the target area image according to the segmentation probability response map. According to the technical scheme provided by the invention, automatic and accurate target region segmentationand image classification can be carried out on the CMR image, and doctors are assisted to carry out disease diagnosis.

A digital imaging device detects or tracks a user's direction of gaze. The detected direction of gaze may be used to set one or more functions in the digital imaging device, and the history of the user's direction of gaze may be stored with a captured digital image for later use by an automatic image post-processing apparatus.

The invention discloses a multi-vehicle-license-plate dynamic identification method of a real-time traffic scene. The method is mainly divided into the multiple main steps of image pre-processing, vehicle-license-plate locating network training, image post-processing, identification network training and the like. Multiple pieces of vehicle-license-plate information in a single picture can be highly efficient identified in real time by using a vehicle-license-plate locating network and a character identification network in a case of not dividing character information; and compared with traditional character segmentation and identification methods, the method of the invention has innovative advantages, and can be widely applied to parking lot charging and peccancy behavior monitoring of expressways and the like.

In a client / server-based image archiving, image retrieval and image rendering system and method for storage, retrieval and graphical visualization of multi-dimensional digital image data such as assessment of medical image data, the detail depth level of volume data received via a data transfer network, to be shown in graphical form, is adjustable by the compressed volume data of subjects to be presented being stored with a highest-possible resolution (predetermined by an imaging system) in a databank administered by a server and directly accessibly only by this server. Although the client / server-based image archiving, image retrieval and image rendering system is able to offer volume data with this highest possible resolution to any point of the system at the request of a screen client, volume data are transferred to a screen client in a compressed form only up to a specific, spatially-variable, region-specific, or subject-specific detail depth level and are presented at the requesting screen client in graphical form. Complicated image rendering and image post-processing algorithms are implemented by the server.

The invention relates to a motion detection method based on edge detection and frame difference. The method comprises the following steps of: 1, acquiring an image sequence and determining images of a reference frame and a current frame; 2, performing Gaussian filtering on the images of the reference frame and the current frame; 3, extracting the edge information of the reference frame and the current frame after the filtering; 4, acquiring converted images of the reference frame and the current frame; 5, performing the frame difference on the converted images of the reference frame and the current frame, and determining a motion region by using a double threshold value method; and 6, performing image post-processing on the motion region, and determining a motion object. The method has the advantages that: due to the adoption of the thinking of frame difference, the method is simple and practical, the complex computations of an optical flow method and hybrid Gaussian are avoided, computing time is only 1 / 3 of that of classical hybrid Gaussian, and requirements on the real-time performance of intelligent monitoring are met; incomplete frame difference detection results are improvedto a certain extent by the combination of the edge detection and the frame difference and a series of additional processing; and compared with the hybrid Gaussian serving as a mainstream method, the method is difficult to influence by illumination and external interference.

An in-line monitoring method for the end vibration of stator windings of large electric generator is based on the resonance characteristics of optical quartz fibre. An optical fibre probe for detecting resonance is arranged at the end of said stator winding. In said probe ,the vibrating fibre is coupled to external light source and the imaging fibre cluster is coupled to external CCD cameral head. The vibration image is received by said CCD camera head and then processed by computer to obtain the amplitude and direction of vibration.

The invention relates to the retinal blood vessel segmentation technology and especially relates to a multi-characteristic fusion monitored retinal blood vessel extraction method. The method comprises steps of step 1, retinal blood vessel image pre-processing; step 2, retinal blood vessel image characteristic extraction; step 3, random forest classifier training; and step 4, retina retinal blood vessel image post-processing. The method is advantaged in that through experiment verification of a DRIVE and STARE eyeground image database, susceptibilities are respectively 0.8354 and 0.8452, accuracies are respectively 94.82% and 95.34%, compared with existing retinal blood vessel segmentation methods in the prior art, the multi-characteristic fusion monitored retinal blood vessel extraction method is integrally better, moreover, disadvantages of the other methods at adjacent blood vessel portions, blood vessel cross sections and capillaries are solved, and segmented blood vessel structures are relatively closer to gold standards and actual blood vessel dimension values.

The invention discloses a video Optical Character Recognition (OCR) image-text separation method and a system thereof to solve the problem that the current recognition method by using a bilateral model can not extract intact strokes in the case of uneven thickness of strokes. The methods comprises: the bilateral model is improved, so that text strokes with the width within the preset range is extracted; the improved bilateral model is used for extracting stroke images from an original text image; the extracted stroke images are converted into binary images; and the binary images are treated by de-noising processing. The invention can extract all the strokes with the stroke width within the preset range, and during the image post-processing stage, a new method combining of two-level overall threshold and edge detection is provided, which can be effective in eliminating background noise while maintaining the integrity of strokes.

The invention provides a mammary gland auxiliary diagnosis system and method based on fusion depth characteristics, and relates to the technical field of medical image post-processing. The system comprises a preprocessing unit, a lump detection unit, a fusion depth feature extraction unit and a lump diagnosis unit, and is characterized in that an original mammary gland image is preprocessed, and amammary gland region is divided into a plurality of non-overlapped sub-regions; Mammary gland sub-region depth features are extracted by using a convolutional neural network CNN, and US- ELM is usedto cluster the depth characteristics of each sub-region to obtain mammary gland lumps and non-lump regions; a convolutional neural network CNN is used to extract lump depth features, lump morphology and texture features are extracted, and the lump depth, morphology and texture features are fused into a fused depth feature; And the fusion depth features are learned by using an extreme learning machine (ELM) to finally obtain benign and malignant diagnosis results of the lumps. The method is applied to breast auxiliary diagnosis, and accurate diagnosis of breast diseases can be effectively assisted.

The invention provides a remote surgical planning and navigating system. The remote surgical planning and navigating system comprises a medical image post-processing subsystem, a multi-mode image fusion subsystem, a medical image management subsystem, a surgical planning subsystem, a surgical navigation subsystem and a remote consultation subsystem, wherein the medical image post-processing subsystem is used for post-processing medical images; the multi-mode image fusion subsystem is used for fusing multi-mode images of a patient and carrying out three-dimensional reconstruction and visualization processing; the medical image management subsystem is used for storing and managing the medical images of the patient and establishing a personal file for the patient; the surgical planning subsystem is used for providing preoperative surgical simulations and plans; the surgical navigation subsystem is used for navigating a surgery; the remote consultation subsystem enables a surgical doctor and an imaging doctor to remotely cooperate and consult. According to the remote surgical planning and navigating system, data can be shared among different departments effectively, doctors in different departments can remotely communicate and cooperate, the problem of requirements for re-acquisition of scanned images which do not meet diagnosis requirements of the doctors is further effectively solved, and the efficiency and the success rate of the surgery are effectively improved.

A novel high resolution large visual field optical imaging system is composed of a share primary mirror, a microlens array and a detector array. The share primary mirror is in a holocentric spherical mirror structure, and the center of the share primary mirror is a spherical mirror. Two meniscus lenses are wrapped on two sides of the share primary mirror, and incident rays respectively pass through the share primary mirror and the microlens array, and finally reach the detector array for imaging. Through the computed imaging technology, image restoration is carried out on every sub-image (eliminating impact of spherical difference on image quality), and all sub-images are subjected to registration recombination to obtain a complete clear image. The novel high resolution large visual field optical imaging system is simple in structural type, and the visual field can reach 180 degrees in theory. The full visual field has a uniform resolution ratio, and combines with the computed image post processing technology, the systematic resolution ratio can be close to a diffraction limit in theory. The novel high resolution large visual field optical imaging system has the advantages of having an extra large visual field, a high resolution ratio, and the like, and particularly suitable for researching and finding of space targets in a wide range, air monitoring for a stratosphere, and the like.

A marker-coordinate detecting unit detects coordinates of a stent marker on a new image when the new image is stored in an image-data storage unit; and then a correction-image creating unit creates a correction image from the new image through, for example, image transformation processing, so as to match up the detected coordinates with reference coordinates that are coordinates of the stent marker already detected by the marker-coordinate detecting unit in a first frame. An image post-processing unit then creates an image for display by performing post-processing on the correction image created by the correction-image creating unit, the post-processing including high-frequency noise reduction filtering-processing, low-frequency component removal filtering-processing, and logarithmic-image creating processing; and then a system control unit performs control of displaying a moving image of an enlarged image of a set region that is set in the image for display, together with an original image.

A user interface for a CT imaging system is disclosed. The user interface includes a first display configured to enable an operator to perform set-up and scanning tasks associated with performing a CT exam on one or more patients, with the set-up and scanning tasks including acquiring and verifying scan image data. The user interface also includes a second display configured to enable the operator to perform image post-processing tasks associated with the CT exams on the one or more patients, with the image post-processing tasks including performing image reconstructions and reformats. Each of the first display and the second display are operable independent from one another to provide for parallel workflows between the first display and second display and between the patient set-up and scanning tasks and the post-processing tasks.

The invention discloses a method for robustly positioning a tampered region by utilizing GLCM characteristic, and belongs to the technical field of signal and information processing. The method is characterized in that: by utilizing the image blocking thought, a quantitative DCT coefficient matrix of each image block is extracted, and a Gray Level Co-occurrence Matrix (GLCM for short) of the coefficient matrix is calculated and serves as the characteristic, the classes of the subimage blocks are judged by data trained in advance and the subimage blocks are marked by corresponding colors. Each image block is subjected to the operation repeatedly so as to obtain a detection result image; and if the result image has a marked color different from most regions, the region marked by the color may be the temperate region. The method has the advantages of positioning the temperate region of the tempered image, having robustness for the common image postprocessing operation, such as rotating, zooming and feather, and providing an effective tool for detecting the authenticity and completion of the images for judicial offices and criminal investigation departments. The method is suitable for the field of information security.

The invention discloses a dry-method lump coal sorting device. The dry-method lump coal sorting device comprises a vibration queuing and feeding device, a lump raw coal slide way, CMOS image acquisition devices, lens dust removers, an image post-processing device, a signal transmission and control system, baffles, a controller, a clean coal channel, a middling coal channel and a gangue channel, wherein lump raw coals with granularities of 50-150mm are queued through the vibration queuing and feeding device, and then fed to the corresponding lump raw coal slide way, each CMOS image acquisition system acquires lump raw coal images at a speed of 3-8fps, the images are transmitted to a background image processing system, the system carries out feature extraction and grey-level calculation on the images, divides ashes into three threshold value ranges, converts signals with grey-level differences to electric signals, and then controls the angles of the baffles to guide clean coal, middling coal and gangue in the corresponding collection channels. The dry-method lump coal sorting device has the following advantages: dry-method sorting can be realized, dependence on water can be reduced, and sorting of lump coals in arid regions can be achieved; and the equipment is small in size, low in energy consumption, and capable of improving raw coal sorting accuracy and automation degree.

Method for determining organ-dependent parameters for image post-processing and image processing device The invention relates to a method for the automatic determination of one or more organ-dependent parameters for image post-processing, having the following steps: recording of a raw image and the execution of image preprocessing on the raw image data in order to generate a preprocessed image, determination of an organ-specific comparison image, stored in a database, which has been optimized by postprocessing using organ-specific postprocessing parameters, and acquisition of the postprocessing parameters for the comparison image, and postprocessing of the preprocessed raw image, using the postprocessing parameters of the comparison image.

The invention provides a multi-nuclide multi-frequency resonance synchronous imaging system which is used for detecting the tumor ion dynamic balance, the energy metabolism, the molecular target change and the tumor microenvironment change. The system can simultaneously transmit radio frequency pulse signals corresponding to four nuclides of 1H, 23Na, 31P and 19F and synchronously receive the nuclear magnetic resonance load signals of the four nuclides. The multi-nuclide multi-frequency resonance synchronous imaging system comprises a signal excitation system, a multi-nuclide multi-frequency signal excitation and acquisition system, a magnetization system and an imaging system. The multi-nuclide multi-frequency signal excitation and acquisition system comprises four nuclide channel modules of 1H, 23Na, 31P and 19F, and each nuclide channel module comprises a signal excitation power amplifier submodule and a signal acquisition submodule. The magnetization system comprises magnets and radio frequency transmitting coils. The imaging system comprises a signal preamplifier, a signal acquisition command module, an image reconstruction module, an image post-processing and display module and an image database.

The invention discloses a method for measuring a leaf area by manually shooting. Aiming at the defects that the conditions required by shooting the leaf images are hardly met in the open air and the effect on image post-processing is poor, and the like in the prior art, the invention provides the method for measuring the leaf area by manually shooting. When a leaf plane image is acquired, the leaf is placed on a standard template with standard control points; image inversion is performed on the shot image on the basis of correspondence of the standard control points between coordinate positions on different images and spatial relationships, and orthographic images of the shot images are acquired; and each leaf image area in the acquired orthographic images is calculated by using the image processing software. Compared with the prior art, the method has the advantage that: the needed equipment is particularly simple and convenient to carry when the method is implemented, manual shooting is performed by only using a common digital camera during the leaf shooting, the image post-processing only needs conventional software, the measured result is accurate and credible, and the error can be controlled. The complete set of the method for measuring the leaf area by manually shooting is particularly suitable for the requirement on field survey.

The invention discloses an image processing system for the surface detection of an coiled material, which comprises a light source, a linear array camera group and a control cabinet, wherein the light source is used for providing light for the linear array camera group; the linear array camera group is used for capturing the original image information of the surface of the coiled material, performing early image processing of the original image information to obtain the result of the early image processing; and the control cabinet is used for performing post image processing according to the result of the early image processing to obtain the result of the post image processing. The image processing system for the surface detection of the coiled material can overcome the defects of high labor intensity, high cost, high loss rate, low detection precision and the like in the prior art and has the advantages of small labor intensity, low, cost, low loss rate and high detection precision.

Certain embodiments of the present invention provide a system and method for automatic image post processing in a healthcare environment. In an embodiment, an automatic post processing image generation system includes at least one user interface, which is adapted to display at least one image on an image viewer and perform image post processing using at least one image post processing application. The system also includes at least one storage server capable of storing user data, wherein the user data includes at least one image and / or at least one post processing parameter. In addition, the system includes a post processing engine for automatically generating and displaying a current post processed image based on at least one image registration technique to correlate the at least one post processing parameter of a related previous post processed image with a current image.

The invention discloses a medical photography system and a photography method implemented by the same. The medical photography system comprises a data acquiring module, a parameter calculating module and an executing and processing module. The data acquiring module is used for acquiring information of patients; the parameter calculating module determines framework location parameters, photography parameters and image post-processing parameters according to the information of the patients; the executing and processing module controls framework locations according to the framework location parameters, controls photography devices to carry out photography on the positions of the patients according to the photography parameters and processes acquired photography images according to the image post-processing parameters. The medical photography system and the photography method have the advantages that working processes can be simplified, skill requirements on operators can be lowered, the clinical training efficiency can be improved, and the operators can effectively concentrate on medical image diagnosis.

The invention provides a CT liver-perfusion image post-processing method and a CT liver-perfusion method. The CT liver-perfusion image post-processing method includes: obtaining a CT liver-perfusion image sequence and identifying an abdominal aorta from the CT liver-perfusion image sequence so as to obtain a time curve of a hepatic-artery contrast-agent concentration; and based on the time curve of the hepatic-artery contrast-agent concentration, calculating a contrast-agent concentration time curve of each pixel point and obtaining liver-perfusion parameters. The invention also provides a CT liver-perfusion method which uses the CT liver-perfusion image post-processing method. The CT liver-perfusion image post-processing method and the CT liver-perfusion method are higher in accuracy.

The invention discloses a deep image post-processing method, which comprises the following steps of: (1) based on to-be-processed left and right view point three-dimensional images and corresponding left and right view point deep images, taking one view point image as a main view point and the other view point image as an auxiliary view point, and detecting reliable points and unreliable points of the main view point deep image; (2) determining filtering size range for processing the main view point deep image according to the basic size of a filtering window; and (3) carrying out multi-size filtering on the main view point deep image by utilizing the main view point image and the reliability of each pixel in the main view point deep image, retaining reliable points, and gradually correcting the unreliable points. According to the invention, aiming at the deep image generated by a three-dimensional matching algorithm, the unreliable points in the shielding region and low-texture region in the deep image can be quickly and effectively corrected, the object edges can be effectively retained, and the accurate and smooth deep image is obtained.

The invention belongs to the technical field of scientific research on petroleum and relates to a CO2-brine contact angle measuring method based on micro-focus X-ray CT. The measuring method comprises a rock core displacement process and a micro-focus X-ray CT shooting and image post-processing process. Pore-level in-situ measurement of CO2-brine contact angles is realized with the method. The CO2-brine contact angles in different positions and in different pores of rock cores can be measured after one-time shooting, and compared with traditional methods, the method consumes less time and is smaller in measurement result error. The method is applied to actual rock cores instead of smooth and ideal materials, and effects caused by surface roughness, mineral composition, heterogeneity of pore structures and the like on the CO2-brine contact angles are considered. The method is applicable to measurement of CO2-brine balance contact angles, retreat contact angles and advance contact angles and wide in measurement range. Measurement results are directly used as input parameters for numerical simulation and can be popularized to contact angle measurement of any gas-liquid-solid or liquid-liquid-solid three-phase systems.