68results about How to "Resolve clarity" patented technology

The invention discloses a system and a method for processing a high-definition picture for intelligent monitoring and belongs to a picture transmission system of an intelligent monitoring system. The processing system at least comprises a picture source end and a picture receiving end. The picture source end comprises a picture sensing module, a picture collecting and separating module and a picture processing and coding module. The picture receiving end comprises a picture decoding module, a picture synthesis module and a picture displaying module. A background and a foreground in the high-definition picture are separated, compressed and transmitted at the picture source end. Foreground data are transmitted in real time and a background layer which is not changed for a long time is transmitted once for a long time. Background picture data and the foreground picture data are synthesized to restore the picture at the picture receiving end so that more details of the picture can be reserved and contradiction of picture definition and data volume is solved. The system and the method for processing the high-definition picture for the intelligent monitoring are particularly suitable for monitoring and the intelligent monitoring system based on facial recognition, anti-fake recognition and other advanced picture processing application of the next generation and an applied range is wide.

Embodiments of the present invention disclose a microphone audio capture effect adjustment method and apparatus. The method comprises the steps of controlling a microphone configured on a terminal to boot audio capture; adjusting, according to a motion state of the terminal, a volume of an original audio collected by the microphone; and outputting the audio with the volume adjusted. Through adoption of the technical solution, when a user is in a motion state, the volume of the audio collected by the microphone is not affected by swinging of an arm, and is stable and clear, so that the audio collected by the microphone can be output stably.

The invention discloses a high-resolution remote collaborative vehicle loss assessment system and a high-resolution remote collaborative vehicle loss assessment method. The system comprises a high-resolution camera, a central server and at least one expert loss assessment computer; the high-resolution camera is arranged in a loss assessment field and used for taking high-resolution videos or pictures; the central server is used for receiving the videos or the pictures periodically and automatically uploaded by the high-resolution camera and putting the videos or the pictures on record; the expert loss assessment computer is used for calling the videos or the pictures which are put on record in the central server for loss assessment, or receiving the videos or the pictures which are automatically returned by the central server for loss assessment so as to determine a loss assessment result. The system and the method bypass the bottleneck of network bandwidth, solve the problems of untimely loss assessment, low resolution, poor cooperativity, low transparence and the like in the vehicle loss assessment industry, and have the advantages of timely loss assessment, high-resolution pictures, collaborative loss assessment by a plurality of loss assessment experts, accurate loss assessment results and the like.

The application discloses a PET image reconstruction method and a PET imaging device. The method comprises steps of: performing image reconstruction on a target object to generate a PET initial image and an MRI anatomical image; fusing the PET initial image with the MRI anatomical image to generate a fusion image that retains only a target object edge, wherein the sharpness of the target object edge in the fusion image is higher than that of the PET initial image; fusing the PET initial image and the fusion image to generate a PET reconstruction image of the target object, wherein the sharpness of the target object edge in the PET reconstruction image is higher than that of the PET initial image. The PET image reconstruction method can improve the sharpness of the edge of the target object in the PET reconstruction image and ensure the uniformity of the metabolic region of the target object in the PET reconstruction image.

The invention relates to a method for manufacturing printing dots of a lenticular grating stereoscopic printing map, which effectively solves the problems of improving the definition and stereoscopic impression of the lenticular grating printing map; the method thereof is as follows: according to the number of lines of used grating plates, the resolution of an output device, and the number of rows of laser points which are generated by each view, the number of images in accordance with the subdivision by visual angle and a printing dot manufacture model are determined; the computer is used for programming so as to obtain a printing dot generating program 3D-RIP which is implemented by the computer for obtaining the printing dot binary image of each color version; a film manuscript of the image is sent to a compositor by a laser typesetter or the printing version is output by a direct computer plate-making machine; the printing dot is output onto the film or the printing version; and by using a stereoscopic map printing method, a printing product of high definition and super-strong stereoscopic sense is obtained. The method is simple and easy for operation, greatly improves the expressive ability of the grating stereoscopic printing products, enhances the quality and competitiveness of the products, saves the production consumables, has broad application prospects, and enormous economic and social benefits.

The invention provides a face recognition monitoring camera. The camera comprises a cradle and a camera body; the camera body is movably connected with the cradle, and comprises an optical lens, an image sensor, a high-definition digital video controller, a face image preprocessing and capturing module, a picture caching module, and a network interface; the image sensor converts an optical signalof the optical lens into a digital signal, and transmits the converted digital signal to the high-definition digital video controller; the high-definition video controller is connected with the face image preprocessing and capturing module; and the face image preprocessing and capturing module is connected with the network interface through the picture caching module. The face recognition monitoring camera provided by the invention can effectively reduce the monitoring cost, greatly reduce the data size required to transmit, and improve the transmission efficiency; the camera cradle and the optical lens can be controlled to track and amplify the valuable face to perform the optimal state capturing, thereby providing high-valuable face image for a distant background face recognition serveror portable equipment.

The present invention belongs to the field of biological characteristic distinction, and is especially the method of extracting geometric characteristic of iris based on characteristic edge distribution. The method includes first defining geometric characteristic of iris and describing its reliability and stability; subsequent extracting geometric characteristic edge of iris in antisymmetric double orthogonal wavelet process and constituting overall edge distribution characteristic in unequal interval grading according to the inhomogeneous distribution of geometric characteristic of iris; and finally introducing characteristic distance expression and proposing legal user judging method. The method has high distinction precision and less outer factor influence.

The invention discloses an image processing method used for intelligent monitoring and a high-resolution camera applied in the image processing method, and belongs to high-definition image collecting equipment in an intelligent monitoring system. An image sensing module is connected to an image collecting and foreground and background separation module to be used for converting environment conditions in a functioning range into original image data and transmitting the original image data to the image collecting and foreground and background separation module. The image collecting and foreground and background separation module is connected with an image processing encoding module to be used for performing a step A and a step B. The image processing encoding module is connected with a communication port to be used for performing from a step C to a step F, and transmitting the separated image data to an image receiving end through a communication port. The image processing method used for intelligent monitoring is simple in procedure, suitable for safe monitoring and a next-generation intelligent monitoring system based on facial recognition, anti-fake recognition and other advanced image recognition and wide in application range.

The invention belongs to the technical field of computer image processing, and discloses an image definition evaluation method and system, a storage medium, equipment and application. The method comprises the following steps: obtaining a gray matrix of a to-be-evaluated image; calculating the average value of the gray value of a certain pixel point and the gray difference of the adjacent eight pixels, and representing the local definition index of the point by using the product of the average value and the maximum value in the eight gray differences; and calculating the quadratic sum of the definition index of each matrix block to obtain the definition score of the whole picture. According to the method, the problem that the definition evaluation result is inconsistent with the subjectivefeeling of people when a traditional algorithm is used for dealing with certain highly fuzzy pictures can be solved. And compared with a traditional algorithm, the definition of a general picture canbe evaluated more efficiently.

The invention discloses a wireless triggering image collection device, and the device comprises image collection equipment and wireless equipment. The wireless equipment comprises a wireless control device and a client signal transit module. The client signal transit module receives an induction signal transmitted by the wireless control device, converts the induction signal into a triggering signal and transmits the triggering signal to the image collection equipment. The method comprises the following steps: operating the wireless control device, transmitting the induction signal to the client signal transit module, and transmitting the triggering signal; receiving the triggering signal through the image collection equipment, shooting a vehicle which breaks a rule, judging whether a vehicle breaks a rule or not, carrying out the next step if the vehicle breaks the rule, and returning to the last step if the vehicle does not break the rule; carrying out information matching, and outputting the information of the vehicle which breaks the rule. The device can achieve image collection through wireless triggering, can timely shoot the vehicle which breaks the rule, prevents delayed operation from causing the reduction of image collection accuracy, and is visual and quick in actual operation.

The invention discloses a frame-lowering photographing method, a mobile terminal and a storage medium. The method includes: using a camera to preview so as to obtain the preview frame rate of a current environment, and collecting the exposure information of each frame of data in real time; judging whether the current photographing environment is a preset-value low-light environment or not according to the exposure information and the preview frame rate; if so, modifying exposure parameters according to a preset algorithm, and outputting corresponding frame data according to the exposure parameters; selecting the frame data with the exposure time satisfying a preset value, and outputting an image according to the selected frame data. The method has the advantages that the original camera isused to output high-quality pictures by lowering frame rate, the problem that pictures are poor in sharpness and have many noise points under a low-light environment is solved from the source, the quality of the pictures is increased, and use convenience is brought to users.

The invention relates to a digital image halftone method based on small-wavelet-domain multi-scale information fusion and belongs to the technical field of digital image processing before printing. The digital image halftone method based on small-wavelet-domain multi-scale information fusion comprises the steps that a continuous-tone image is converted into a grayscale image, and whether the grayscale image is a standard 2n*2n grayscale image is judged; small-wavelet-domain four-scale information of the standard grayscale image is obtained through two-dimension discrete wavelet transformation, and an edge error measure function is obtained by means of wavelet detail coefficient relation between autocorrelation fusion layers of inter-scale wavelet coefficients; the standard grayscale image is divided into k areas with the K-means cluster method, and an area error measure function is established with the reciprocals of variances of the areas serving as weights; a mixed error measure function is established according to the additivity of the edge error measure function and the area error measure function, and then errors of the standard grayscale image and a rough halftone image are minimized with the direct binary searching method. The digital image halftone method based on small-wavelet-domain multi-scale information fusion solves the problem that according to an existing method, the smoothness and the definition of images can not be guaranteed at the same time.

The invention discloses a near-infrared zoom lens with an embedded liquid lens assembly. The lens includes a lens barrel, lens bodies, a diaphragm, the liquid lens assembly and an optical filter; thelens bodies comprise the first lens body, the second lens body, the third lens body and the fourth lens body, wherein the first lens body, the second lens body, the third lens body, the diaphragm, theliquid lens assembly, the fourth lens and the optical filter are arrayed sequentially from an object side to an image side in the lens barrel; a double-convex glass spherical-surface lens body with positive focal power is adopted as the first lens body, a falcate glass spherical-surface lens with positive focal power is adopted as the second lens body, a double-concave glass spherical-surface lens with negative focal power is adopted as the third lens body, and a double-convex glass spherical-surface lens body with positive optical power is adopted as the fourth lens body. According to the lens, the four glass spherical-surface lens bodies and the liquid lens assembly are added, so that the problems are solved that the working distance range of traditional fixed-focus lenses is narrow, the number of existing zoom lenses in which liquid lens assemblies are embedded is large, and the definition is low.

The invention relates to high-resolution human figure automatic recording and comparing system and method in a key region. The system comprises a video detecting module, an image acquisition module, a suspected face comparing module and an alarming module. The method comprises the following steps of: scanning and comparing a detection region by the video detecting module in real time; sending a triggering signal to the image acquisition module if a number of pixel information of a detection stripe band exceeds the preset threshold; acquiring the current image information by the image acquisition module through a network camera to form member face records and sending the records to the suspected face comparing module; comparing and matching suspected face information hierarchically one by one by the suspected face comparing module; if the suspected face information is matched successfully, sending alarming information to the alarming module; and carrying out alarming processing by the alarming module according to the alarming information. By adopting the high-resolution human figure automatic recording and comparing system and method in the key region, the system power consumption is reduced, the energy is save, no pollution is caused to the environment, the comparing times of the system is reduced, and the comparing efficiency is improved. The high-resolution human figure automatic recording and comparing system and method in the key region are suitable for large-scale suspected face comparison.

The invention discloses an OCR bill problem identification method and system based on feature detection. The method comprises the steps of performing background elimination and denoising processing ona bill image to obtain a first image; performing projection transformation on the first image, removing a separator, and identifying characters to obtain a bill text; extracting a keyword combinationof the bill text; matching the keyword combinations in a knowledge base to obtain a rule set with the highest matching degree as a reference rule set; and if the audit content information of the billtext is greater than a preset risk threshold of the reference rule set, sending alarm information. According to the method, the problem that original file handwriting definition, cleanliness and thelike are difficult to recognize is effectively solved, bills can be imported on a large scale, similarity recognition can be rapidly carried out on the bills, OCR recognition error correction is achieved through intelligent verification of intelligent recognition based on text character features, and the accuracy is further improved. According to the positioned risk points, the auditing workload is rapidly reduced, and the user experience of the informatization system is improved.

The invention belongs to the technical field of thermoprint materials, particularly relates to a heat sublimation washing label printing thermal transfer ribbon. The heat sublimation washing label printing thermal transfer ribbon comprises a ribbon base, a back coating layer coated to one face of the ribbon base and a heat transfer printing layer coated to the other face of the ribbon base; and the heat transfer printing layer is divided into two layers, the lower layer is a pigment layer with the thickness being 1.0 micrometer to 1.5 micrometers, is formed by vinyl chloride-vinyl acetate resin and carbon black, and comprises, by mass percentage, 80%-90% of the vinyl chloride-vinyl acetate resin and 10%-20% of the carbon black, and the upper layer is a heat sublimation dye layer with the thickness being 0.6 micrometer to 0.8 micrometers, is made of waterborne polyurethane resin and heat sublimation dye, and comprises, by mass percentage, 70%-80% of the waterborne polyurethane resin and 10%-30% of the heat sublimation dye. The heat sublimation washing label printing thermal transfer ribbon has the beneficial effects of washing resistance, dry washing resistance, friction resistance and the like; and meanwhile, the preparing method of the heat sublimation washing label printing thermal transfer ribbon is easy and convenient, and the better application and popularization values are achieved.

The invention discloses a narrow bandwidth lower than 4 K / S video transmission method and system. The narrow bandwidth lower than 4 K / S video transmission method comprises the steps that a video is captured; a USDC coding technology is adopted to perform high power compression on video streaming media files with low damage; the sending of video frames is adjusted according to the network environment; a video server receives and distributes video streaming; a video receiving end receives, decodes and plays the video. By the adoption of the technical scheme of the narrow bandwidth lower than 4 K / S video transmission method and system, the bandwidth occupied by transferring high-definition images is minimal, the image quality is clear and smooth, the image delay is small, the operating cost is reduced, and therefore, the bottleneck problem between the high definition high code streaming and lack of bandwidth is solved.

The invention discloses a polarization splitting prism gluing process, wherein the glued polarization splitting prism is subjected to milling, grinding, polishing, coating, and gluing processing in sequence; and the gluing processing relates to machine shaping a triangular prism which is qualified in size, angle, and appearance qualities and has matched PBS film characteristics and optical constants respectively according to the following steps: dispensing, glue discharging, adjusting of size-position of the glue, and ultraviolet curing. The glued prism prepared in the methodnot only has a small degree of separation of pixels at an edge of gluing regression passing through a light path, regarding to a 3D projection image, but also can greatly reduce the width and brightness of a dark zone generated at the edge of gluing regression on a white screen, so that overall color and luminosity of an image on the white screen cannot be obviously distinguished visually.

The invention relates to the technical field of face recognition, in particular to a face snapshot gunlock load balancing method, which comprises the steps that two paths of original images are acquired, and an acquisition module of a snapshot gunlock transmits the original images to an image encoding and decoding module; an image encoding and decoding module outputs one path to a CPU encoding module for encoding, and outputs the other path to the GPU module for face detection; after receiving the image, a CPU image application module stores the image to a local storage card and uploads the image to a far-end server through a network; a CPU image analysis module analyzes the locally stored images, counts the number N of face snapshots in a set time and transmits a code rate value X needingto be adjusted, and the CPU encoding module acquires and configures an initial code rate value as the adjusted code rate value X; the coding code rate is dynamically adjusted in real time, the code rate is reduced when the snapshot amount is large, and the effects of giving way to CPU resources, locally storing pictures and uploading the pictures to a remote server are achieved; on the contrary,the code rate can be recovered and even improved in the time period with small snapshot amount, and a load balancing strategy is achieved.

The invention provides a migrant crowd video surveillance method based on face recognition. Through a face recognition surveillance camera, a real-time digital video is collected, an original image inthe real-time digital video is preprocessed to screen face images which can be used for comparison and recognition, and the obtained face images which can be used for comparison and recognition are transmitted to a control platform through a telecommunication network; and a control platform is connected to a face server to recognize the face images. By use of the method, in the digital video image with an ultrahigh resolution, the face image can be found in time, a camera optical lens and a head can be controlled to track and amplify the valuable face to be subjected to optimal state capture,the valuable face image is provided for a remote background face recognition server or portable equipment, a data size which needs to be transmitted is greatly lowered, and the face recognition accuracy and speed of a surveillance system is improved.

The invention discloses a non-perception face image acquisition method and system, and the method comprises the steps: S1, photographing a panoramic image of a to-be-detected region, detecting the position of a human body in the panoramic image through a human body detection method, and obtaining a human body bounding box vector bi; s2, transmitting the human body bounding box vector bi to a pre-trained PTZ camera motion model, wherein the PTZ camera motion model is used for outputting a PTZ camera motion parameter vector which corresponds to the input human body bounding box vector bi and canshoot a human front face image; and S3, the PTZ camera moves the direction of the camera and changes the focal length of the camera according to the PTZ camera motion parameter vector, aligns at a person at a corresponding position for shooting, realizes face angle screening through face detection and head posture recognition algorithms, and acquires a front face image of the person. A two-stagedetection method combining human body detection and face angle screening is adopted, the face detection efficiency is high, and the practicability is high.

The invention discloses an image encoding method and device, an image decoding method and device and a processor. The method comprises the following steps: determining a target macro block including atext in a to-be-coded image; determining the basic color of the text of the target macro block; setting indexes for the basic color and the non-basic color of the target macro block, and generating acolor index map of the target macro block; generating a background image of the to-be-coded image according to the color index map; and respectively encoding the mapping table of the basic colors, the color index map and the background image. The technical problem of poor text definition or large image coding code stream when the images fused by the text and the image is coded in the prior art issolved.

The invention discloses a Retinex enhancement method of a color image based on a guiding filter, and belongs to the technical field of image processing. The method comprises the steps of reading an RGB color image and extracting a component; performing R component logarithmic transformation to obtain the filtered image LR; calculating a DR image; calculating a histogram of the gray image DR; calculating h0 corresponding to p >= p 0; recording a gray value of H (i) > h0, and setting a stretching range; Finding out the position of the gray value on the image DR in turn, and recording the corresponding value from the image DR; Recording the gray value of H (i) <= h0, taking out the gray value, and searching for the position and value of the gray value in the image DR; Outputting an R component output image; The original color image RGB is changed into a new variable to output the color image. The invention relates to a histogram-limited color image enhancement method which combines guidefiltering and Retinex theory, which is mainly used for solving contrast and clarity difference caused by narrow dynamic range of image, improving image contrast and clarity, and improving image visualrange and visual effect.

The invention provides an image preprocessing method for a face recognition surveillance video. The image preprocessing method comprises acquiring a real-time digital video; preprocessing an originalimage in the real-time digital video; screening out face images available for comparison recognition; separating the foreground from the background of the original image by using differential technology; separating the foreground image from the background image in the original image to obtain the foreground image; convoluting the foreground image and a high-pass filter template to find the boundary contour of an object; according to the continuity and the closure of the contour, separating independent objects; normalizing the image of each object; and convoluting the normalized image and a face feature template to obtain an object image. The method can extract face images from the ultrahigh-resolution digital video image in real time, provides high-valued face images for a remote background face recognition server or a portable device, greatly reduces the amount of data to be transmitted, and improves face recognition accuracy and speed of a surveillance system.

The invention discloses a high light-transmitting fiber glass surface paper, which comprises sulfuric acid paper, and the two sides of the sulfuric acid paper are coated with an undercoat layer, a secondary coat layer and a protective layer in sequence, and the undercoat layer is copolymerized by carbon dioxide 80 parts of polyols, 18 parts of diisocyanates, 22 parts of chain-extending cross-linking agents and 14 parts of hydrophilic chain-extending agents; 7 parts of sustained-release microcapsules, 16 parts of ethyl acetate, 0.3 parts of white mineral oil and 10 parts of dye; the protective layer is made of 27 parts of hydroxyethyl cellulose ether, 2 parts of sodium lauryl sulfate, polypropylene Made from 4 parts of amide and 6 parts of triethanolamine; this kind of high-transmittance fiber glass paper can significantly improve the light transmission and surface smoothness of the fiber, and the surface smoothness of the paper after double-sided treatment is greater than 210 seconds, and at the same time The preparation method of the process is simple and the application range is wide.

An outdoor weather-proof engineering material based on fast-growing grass is disclosed. The engineering material has an alternant layered structure. The layered structure includes 3 layers or above, and includes odd-number layers and even-number layers. The odd-number layers are pennisetum alopecuroides (L.) Spreng. The even-number layers include polylactic acid wood wool and wood composite particles. The polylactic acid wood wool includes 20-30% by weight of wheat straw powder and 70-80% by weight of polylactic acid. The wood composite particles include 50-55% of high density polyethylene (PE), 35-40% of wheat straw powder, 3-10% of stearic acid and 2-5% of an ethylene-vinylacetate copolymer (EVA). The invention also discloses a preparing method of the outdoor weather-proof engineering material based on fast-growing grass. The objective of the invention is to provide the outdoor wood engineering material having high weatherability, high apparent hardness, good static bending intensity and good processing / etching properties and the preparing method thereof, aiming at defects of present artificial panels and preparing processes thereof.

The invention provides an image processing method. The image processing method comprises the steps of preprocessing a to-be-processed picture; optimizing the pre-processed picture; converting the resolution of the optimized picture from a first resolution to a second resolution, wherein the second resolution is greater than the first resolution; and cutting or / and zooming the picture with the second resolution according to the template image. Through image processing and other technologies of the invention, the picture background, the face size and the picture layout of the face picture are unified; and moreover, the picture definition and the face illumination have better quality, the problem that the picture coding format, the picture size, the picture definition, the picture background,the face illumination, the face size and the like in the traditional face picture are different is solved, and the manual viewing during application is facilitated.

The invention discloses a 3-DOF (degree of freedom) mobile loading platform for a vertical optical microscope. An optical source is disposed on a horizontal position adjustment platform. One end of a lifting rod is fixed with the horizontal position adjustment platform, and the other end extends into a bottom seat. A displacement adjustment handle driving the lifting rod to move upward along a vertical direction in the bottom seat is disposed on the bottom seat. The horizontal position adjustment platform comprises two horizontal displacement guide blocks, two horizontal displacement adjustment handles, and a base seat. The two horizontal displacement guide blocks are disposed along the vertical direction on the bottom seat. The sides of the horizontal position adjustment platform are respectively provided with the horizontal displacement adjustment handle driving the horizontal displacement guide block at an upper layer to move along a horizontal direction on the horizontal displacement guide block at a lower layer, and the horizontal displacement adjustment handle driving the horizontal displacement guide block at the lower layer to move along the horizontal direction on the bottom seat. The moving directions of the two horizontal displacement guide blocks are perpendicular to each other. According to the invention, an observed object can be quantitatively moved in the horizontal direction, and the focusing accuracy of a lens barrel can also be improved.