Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

70 results about "Spin image" patented technology

Diffusion distance for histogram comparison

InactiveUS20070110306A1Time complexityCharacter and pattern recognitionDiffusionSpin image
A new measure to compare histogram-based descriptors, a diffusion distance, is disclosed. The difference between two histograms is defined to be a temperature field. The relationship between histogram similarity and diffusion process is discussed and it is shown how the diffusion handles deformation as well as quantization effects. As a result, the diffusion distance is derived as the sum of dissimilarities over scales. Being a cross-bin histogram distance, the diffusion distance is robust to deformation, lighting change and noise in histogram-based local descriptors. In addition, it enjoys linear computational complexity which significantly improves previously proposed cross-bin distances with quadratic complexity or higher The proposed approach is tested on both shape recognition and interest point matching tasks using several multi-dimensional histogram-based descriptors including shape context, SIFT and spin images. In all experiments, the diffusion distance performs excellently in both accuracy and efficiency in comparison with other state-of-the-art distance measures. In particular, it performs as accurate as the Earth Mover's Distance with a much greater efficiency.
Owner:SIEMENS MEDICAL SOLUTIONS USA INC

Image rotation correction method and system and electronic device

ActiveCN101639933AReduce the trouble of manual rotation correctionGeometric image transformationPictoral communicationImaging processingImage rotation
The invention discloses an image rotation correction method and a system and an electronic device. The image rotation correction method carries out the following steps before storing or browsing images: A: reading original image data; B. detecting the rotation angle of the image data: rotating images several times, calculating the reliability indices of the image before rotation and the images after each rotation, and marking the rotation angle whose reliability index is highest as the needed rotation angle, wherein, the rotation angle is the relative angle of the original image and image during normal checking; and C. according to detected rotation angle, carrying out rotation correction on the image. The invention utilizes the technologies in the fields of image processing, mode identification and the like to automatically detect the rotation angle and correct the rotation of the image data before storing or displaying the image data to a user to browse, thus ensuring that the user can see the image which is treated by rotation correction when browsing images and reduces the trouble for users to manually correct with an image browsing tool.
Owner:SHANGHAI HEHE INFORMATION TECH DEV

Contact developing method, image forming apparatus, and process cartridge

A contact developing method including supplying a two-component developer to an electrostatic latent image on a rotating image bearing member by rotating a developing sleeve and a rotatable magnet having multiple magnetic poles provided inside the developing sleeve, to develop the electrostatic latent image into a toner image. The developing sleeve and the image bearing member rotate in the same direction while facing each other. The two-component developer comprises a non-magnetic toner and a carrier. The carrier comprises a magnetic core particle and a resin layer covering the magnetic core particle. The resin layer comprises a conductive particle and a resin. The conductive particle comprises an alumina-based material and a conductive layer covering the alumina-based material. The resin is obtained by heating a copolymer comprising a monomer A unit and a monomer B unit.
Owner:RICOH KK

Method for detecting ampoule bottle appearance quality through medical visual inspection robot

The invention discloses a method for detecting ampoule bottle appearance quality through a medical visual inspection robot. The method comprises the steps of (1) acquiring an ampoule bottle image, and preprocessing the image through a median filter; (2) solving an ampoule bottle mimic symmetry line by employing a threading method to obtain a rotating angle alpha; (3) rotating the image by using a bilinear interpolation-summation method; (4) solving a symmetry center line, wherein the intersection of the symmetry center line and the head is a symmetry center point h0; (5) solving a head edge point; (6) enabling the outer curve at the head of the ampoule bottle to have the characteristic of a symmetrical variable trend in a lower parabola shape, and judging whether the ampoule bottle appearance wire-drawing quality is qualified; (7) positioning a black head detection rectangular area; (8) judging whether the black head ampoule bottle appearance is qualified by employing a difference method; and (9) integrating the appearance drawing and black head quality detection result. According to the method, the problems that the manual detection efficiency is low, the consistency is low and the leakage detection rate is high and the like are overcome, and the degree of automation and product quality of the ampoule bottle medicine production are improved.
Owner:HUNAN UNIV

Parallax image pickup apparatus and image pickup method

A parallax image pickup apparatus for forming a parallax image train by photographing an object from a plurality of directions includes an image pickup unit in which an image pickup device and an image forming optical system are integrated in order to photograph the parallax images of the object; a rotating unit on which the image pickup unit is mounted and which rotates the image pickup unit in a parallax direction; an image pickup unit moving unit for rectilinearly moving the image pickup unit and the rotating unit synchronously with the rotation of the rotating unit; a control unit for controlling so that a virtual image pickup center portion is always located at the center of a photographed image; and a focal distance control unit for continuously changing a focal distance of the image pickup unit.
Owner:SONY CORP

Inline image rotation

Methods and apparatus for performing an inline rotation of an image. The apparatus includes a rotation unit for reading pixels from a source image in an order based on a specified rotation to be performed. The source image is partitioned into multiple tiles, the tiles are processed based on where they will be located within the rotated image, and each tile is stored in a tile buffer. The target pixel addresses within a tile buffer are calculated and stored in a lookup table, and when the pixels are retrieved from the source image by the rotation unit, the lookup table is read to determine where to write the pixels within a corresponding tile buffer.
Owner:ALLLE INC

Method for eliminating image rotation caused by 45 degree scanning lens

The method of eliminating image rotation caused by 45 deg scanning lens is suitable for eliminating image rotatino in case of faulted K lens and no K lens. The method includes at least the folloiwng steps: rotating computer input image; calculating imaging relationship in computer; deducing the imaging process of the optical instrument from the basic reflection law; obtaining the mapping relationship between the image rotating coordinate and rotation elimianting image coordinate; eliminating rotation of the whole image frame; and output rotation eliminated image; circular execution. For faulted K lens, there include also the steps of obtaining K lens angle and inputting to computer. The present invention can eliminate rotation of image, simplify optical path of remote sensing instrument, raise the reliability of instrument in satellite.
Owner:SHANGHAI INST OF TECHNICAL PHYSICS - CHINESE ACAD OF SCI

Image rotation realization method and apparatus

The invention discloses an image rotation realization method and apparatus. The method comprises the steps of determining a reading sequence of image data according to a source storage format and a source data format of a to-be-rotated image, and a rotating angle of the image; reading rotating units in the image data according to the determined reading sequence, and transmitting the rotating units to a rotator; and performing pixel rotation on pixels in the read rotating units according to the rotating angle by the rotator, and recombining the rotating units subjected to the pixel rotation, thereby obtaining an image of the corresponding rotating angle. The image rotation is realized in a form of changing the reading sequence through hardware, so that the hardware cost input is reduced and the processing speed and efficiency are improved.
Owner:新岸线(北京)科技集团有限公司

Process Cartridge and Image Forming Apparatus

A process cartridge detachably mountable to a main assembly of the image forming apparatus, the process cartridge includes an image bearing member; a developing device for developing an electrostatic image formed on the image bearing member with a developer; an image bearing member driving force input portion for receiving a driving force for rotating the image bearing member from an image bearing member driving force output portion from the main assembly; a developing device driving force input portion for receiving a driving force for driving the developing device from a developing device driving force output portion of the main assembly, wherein the image bearing member driving force output portion and the image bearing member driving force input portion are engaged with each other with a play in a mounting and demounting direction of the process cartridge, when the driving force is inputted from the image bearing member driving force output portion to the image bearing member driving force input portion, and wherein when the driving force is inputted from the developing device driving force output portion to the developing device driving force input portion, a part of the process cartridge is urged toward a positioning portion for positioning of the process cartridge relative to the main assembly.
Owner:CANON KK

Dual-mode image automatic fusion method

The invention provides a dual-mode image automatic fusion method which comprises the following steps: respectively obtaining distance sequences from IVUS and OCT (Optical Coherence Tomography) inner membrane points to the center of an image on the basis of a sinake model; Calculating scaling coefficients of the OCT image and the IVUS image blood vessel lumen through the average inner membrane radius of the IVUS image and the average inner membrane radius of the OCT image blood vessel lumen; Rotating the IVUS image according to a preset angle range and a preset step length; calculating mutual information of the rotated IVUS image and the OCT image; when the mutual information is the maximum value, the corresponding angle serves as a reference, adopting a circumferential correlation algorithm for estimating the actual rotation angle, and after IVUS and OCT images are registered, adoptinga Poisson fusion algorithm for fusing the converted IVUS image and the converted OCT original image. According to the technical scheme, the advantages of IVUS imaging and OCT imaging are brought into full play, and the speed of the fusion process is increased.
Owner:INNERMEDICAL CO LTD

Template matching method, system and device based on normalized cross-correlation and medium

The invention discloses a template matching method, system and device based on normalized cross-correlation and a medium. The method comprises the following steps: constructing a template image pyramid and a target image pyramid with the same layer number according to a template image and a target image; performing rotation processing on each layer of image of the template image pyramid according to a preset angle step length to obtain a plurality of rotation images, and further determining key pixel points; screening out a first matching area with the highest correlation coefficient with the rotation image from a top image of the target image pyramid according to the key pixel points, and determining a first upper left corner coordinate and a first rotation angle; and performing layer-by-layer search on each layer of image of the target image pyramid according to the first upper left corner coordinate and the first rotation angle until a second matching area with the highest correlation coefficient with the rotation image in the bottom layer image is determined. According to the method, the calculation amount of template matching is reduced, the template matching efficiency is improved, the template matching accuracy is also improved, and the method can be widely applied to the technical field of image processing.
Owner:GUANGZHOU UNIVERSITY

Image acquiring device and method or rotating images

An image acquiring device and method of rotating images includes a scanning module, a driving mechanism, a selecting module, a control-processing unit and a memory. The scanning module scans a plurality of originals in sequence in conjunction with the driving mechanism. The selecting module selects a specific mark of a first original as a basis for judging an orientation state of a second original. The control-processing unit generates a digital mark signal stored in the memory according to the signals output from the scanning module and the selecting module. The control-processing unit judges a position of the digital mark signal in a digital signal obtained after the second original is scanned, and thus generates a rotating signal and rotates the digital signal into a normal image signal according to the rotating signal. Thus, the document image may be automatically rotated into a normal state.
Owner:AVISION

Image re-sampling detection based on Markov process and Gabor filtering

An Image re-sampling tampering detection algorithm is one of the important methods for image tampering evidence collection. According to the invention, an image is detected mainly based on condition state transition probability matrixes in a Markov process and the texture features in a Gabor filter. After an image is re-sampled, the correlation between adjacent DCT coefficients changes. However, the transition probability matrixes can well describe the change in DCT coefficients and surrounding coefficients. Thus, transition probability matrixes in four directions are extracted as Markov features. The detection rate of the algorithm fluctuates greatly when comes to texture images of different complexity. Thus, a Gabor filter group is adopted to extract the texture features of the image and perform two-dimensional discrete Fourier transform to get the final texture features of the image, and then, an SVM is adopted to train and classify the two types of features. With the algorithm of the invention, scalable images and rotary images can be well detected, and detection of rotary images is of high robustness.
Owner:JIANGNAN UNIV

Aneurysm detection method and system based on MRA, terminal and medium

The invention discloses an intracranial aneurysm detection method based on MRA, and the method comprises the following steps: obtaining to-be-processed original image data, carrying out the correction and normalization processing of the original image data, and obtaining the processed image data; performing mIP reconstruction on the processed image data to obtain MIP images, and generating three kinds of rotating images after the external carotid artery is deleted, wherein each rotating image is composed of projections evenly distributed around a single rotating shaft; automatically segmenting intracranial artery blood vessel voxels; manufacturing a plurality of patches for each voxel in the blood vessel area, calculating the probability that all patches contain the aneurysm, classifying the calculated probabilities according to a preset probability threshold value, wherein the voxels larger than the preset probability threshold value generate a volume shape index image and a curvature image based on a curvature algorithm to display the aneurysm; measuring the maximum diameter of the aneurysm; and outputting an aneurysm detection result. According to the method, the intracranial artery blood vessel can be accurately identified, and the size of the aneurysm can be accurately measured.
Owner:TONGXIN YILIAN TECH BEIJING

Offsetting rotated tables in images

A method for image processing, including: obtaining an image including a table; identifying a first line corresponding to the table in the image, a first confidence value for the first line, and a first angle for the first line; initiating a plurality of angle bins corresponding to multiple angles; calculating, based on the first confidence value, a first plurality of bin values for a first subset of the plurality of angle bins within a window surrounding the first angle; adding the first plurality of bin values to the first subset of the plurality of angle bins; identifying an angle bin of the plurality of angle bins having a maximum bin value; and rotating the image based on the angle bin having the maximum bin value.
Owner:KONICA MINOLTA LAB U S A INC

Image processing device and image processing program

An image processing device that rotates an image according to the inclination of a line segment included in the image, includes an evaluation unit 106 that evaluates a plurality of line segments whose inclinations are different, on the basis of each of a plurality of different decision standards, and a selection unit 106 that selects, on the basis of the results of the plurality of evaluations, from among the plurality of line segments, a line segment on the basis of which the image is to be rotated
Owner:NIKON CORP

Scanning type printing apparatus

The scanning type printing apparatus prints an image and / or a text on a recording medium in accordance with image data and / or text data while moving on the recording medium. The apparatus includes a moving unit, an image processing unit that, prior to printing, rotates the image and / or the text to be printed based on the image data and / or the text data and / or reverses front and back thereof; and an ejection head that includes at least one nozzle and at least one ink ejection unit that eject ink.
Owner:FUJIFILM HLDG CORP +1

Generating photorealistic viewable images using augmented reality techniques

Methods, systems, computer-readable media, and apparatuses are presented for generating a photorealistic viewable model using augmented reality (AR). An AR scene is generated by overlaying a virtual object onto a view of a physical environment. When placed into the AR scene, the virtual object can interact with the physical environment by, for example, reflecting or taking on colors, shadows, brightness, and other attributes of the physical environment. To generate the viewable model, the virtual object is manipulated (e.g., moved or rotated) within the AR scene and a plurality of images are generated by capturing the virtual object as the virtual object is being manipulated. The viewable model can be generated based on one or more of the images and can be output in the form of an interactive presentation, for example, a spin image.
Owner:CDS VISUAL INC

Image processing method and device, electronic equipment and storage medium

The invention discloses an image processing method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a to-be-processed image, performing iterative downsampling processing of a preset rule on the to-be-processed image to obtain an image set of a pyramid structure, thereby obtaining a multi-scale image set, and performing rotation processing on the image of any layer in the image set of the pyramid structure based on at least one rotation strategy to obtain at least one rotating image of any layer of image, thereby obtaining a multi-angle image, wherein the rotation strategy comprises a size-invariant rotation strategy, a size-variable rotation strategy and an inscribed circle rotation strategy; and forming a target image set of the to-be-processed image based on each layer of image and the at least one rotation image corresponding to each layer of image. According to the method and device, multi-scale and multi-angle image set construction is achieved, rich image selection is provided for image registration, the image registration precision is improved, and the method and device can also be used for objectively evaluating an image registration algorithm with a rotation angle.
Owner:GUANGDONG TOPSTAR TECH

Typhoon positioning method, device and system, electronic equipment and storage medium

The invention discloses a typhoon positioning method, device and system, electronic equipment and a storage medium. The typhoon positioning method comprises the following steps of: acquiring previous moment geographic position information and a previous moment satellite image of a typhoon; determining first pixel coordinates of the previous moment geographic position information in the previous moment satellite image; taking the first pixel coordinates as a center, taking a target image area with a set window size from the previous moment satellite image data, and rotating the target image area to obtain a plurality of rotating image areas; respectively matching each rotating image area with a current moment satellite image, and determining the central point of the rotating image area with the highest matching degree as a current moment first typhoon position; and converting the current moment first typhoon position into current moment geographical position information. According to the typhoon positioning method, multiple data sources are adopted, the problem that errors are large when typhoon positioning is conducted only through satellite images is avoided through adopting a multi-source weighted fusion algorithm and a distance attenuation algorithm, and the calculated typhoon path is smoother and more stable.
Owner:象辑科技股份有限公司

Light spot detection method and device, electronic equipment and readable storage medium

ActiveCN112686842AAccurate and stable extractionSolve the problem of large memory consumptionImage analysisGeometric image transformationSpin imageLight spot
The invention provides a light spot detection method and device, electronic equipment and a readable storage medium, and the method comprises the steps: carrying out the scanning of an original image and a rotating image obtained after the original image rotates 90 degrees in a first direction in a horizontal direction, obtaining the pixel points of each row of images in the original image and the rotating image, determining candidate light spot pixel points from the pixel points, forming a row light spot array by all candidate light spot pixel points meeting a preset requirement in each row image, and respectively clustering all the row light spot arrays to obtain target light spot arrays of the original image and the rotating image, and performing union set on the spot area corresponding to the target light spot array of the rotating image after rotating for 90 degrees along the second direction and the spot area corresponding to the target light spot array of the original image to obtain a target light spot of the original image. According to the invention, light spot detection can be carried out on the detection image simultaneously through one set of algorithm, the problem of high memory consumption is solved, and the effects of simple algorithm, small storage space, low time consumption and accurate and stable light spot center point extraction are achieved.
Owner:轻威科技(绍兴)有限公司

Image forming apparatus

An image forming apparatus forms an image on a recording medium and includes a rotatable image bearing member, and a rotatable developer carrying member that carries a developer, forms a developing portion by contacting the image bearing member, and forms a developer image on a surface of the image bearing member by supplying the developer to an electrostatic latent image formed on the surface of the image bearing member in the developing portion. After performing an image forming operation, a controller controls driving of the image bearing member and the developer carrying member to perform a rotation operation for rotating the image bearing member with rotation of the developer carrying member stopped in a state where an amount of carried developer in the developing portion during the rotation operation is smaller than the amount of carried developer in the developing portion during the image forming operation.
Owner:CANON KK

Video call processing method and device

The invention relates to the field of multimedia communication, in particular to a video call processing method and device, and the method comprises the steps: obtaining the angle information of a current transmitting end in a video call process; rotating a currently acquired image according to the angle information and a preset image acquisition angle; displaying rotated images, the rotated imageis sent to a receiving end; and the receiving end displays the rotated image. Therefore, according to the change of the receiving end angle information; the image is rotated, the rotated image is displayed locally and sent to the receiving end, and therefore it can be guaranteed that the locally-displayed video image and the video image displayed by the receiving end are both upright normal images, image rotation is conducted through the receiving end, the processing efficiency is high, real-time synchronism can also be guaranteed, and the accuracy is improved.
Owner:CHINA MOBILEHANGZHOUINFORMATION TECH CO LTD +1

Rotating palm image detection method

The invention discloses a rotating palm image detection method, which comprises the following steps of: 1, rotating an image to be detected at an interval of 5 degrees to form a 72-original image, andstoring the 72-original image into an image rotating star disk from a rotating image within a range of 0-360 degrees; 2, inputting all the pictures in the image rotation star disk into a pre-trainedforward palm detector in batches according to a sequence; 3, screening all detection results to the maximum extent, and obtaining a unique candidate detection result; 4, calculating a reverse rotationmatrix corresponding to the rotation angle in the candidate detection result; and finally, performing rotation processing on the candidate detection result through the rotation matrix to obtain a final palm image detection result with an angle. The invention provides an image rotation star disc and a maximum possibility screening method, and combines the most efficient detection network Yolov3 inthe target detection field in the current deep learning to realize palm image detection with an attached angle.
Owner:XI AN JIAOTONG UNIV

System and method for image re-orientation

Systems and methods are provided for image re-orientation. A computing system for image re-orientation may comprise one or more processors and a memory for storing instruction that, when executed by the processors, cause the system to perform: obtaining positive samples including text of a predetermined type in a predetermined orientation range and negative samples not including text of the predetermined type in the predetermined orientation range; training a model with the obtained positive and negative samples; receiving an image in an original orientation; applying the trained model to thereceived image; in response to determining that the received image does not comprise any text of the predetermined type in the predetermined orientation range, rotating the image by a predetermined angle and re-applying the trained model to the rotated image to determine if the rotated image comprises at least some text of the predetermined type in the predetermined orientation range.
Owner:BEIJING DIDI INFINITY TECH & DEV

A Dual Energy Subtraction Method Based on DR Machine

ActiveCN106296613BLower requirementRadiation exposure interval extensionImage enhancementImage analysisDual energy subtractionComputation complexity
The invention discloses a dual-energy subtraction method based on a DR machine, which includes the following steps: S1: acquire X-ray high-energy images and low-energy images with an exposure interval of 2 seconds; S2: use the high-energy image as a template, The energy images are registered to obtain a low-energy image that is not shifted relative to the high-energy image; S3: Logarithmic transformation is performed on the high-energy image and the registered low-energy image, subtracted and displayed. The ray exposure interval of the present invention can be extended to 2 seconds; the present invention adopts an improved registration method to effectively correct motion artifacts caused by patient displacement, rotation, inconsistent image brightness, noise, etc.; the present invention reduces energy consumption at high and low energy levels. In terms of shadow calculation, the high-energy image and the registered low-energy image are logarithmically transformed, and the low-energy image is multiplied by an elimination factor to eliminate soft tissue or bone tissue, which greatly improves the calculation speed and effectively reduces the computational complexity and Requirements for computer memory.
Owner:NANJING PERLOVE RADIAL VIDEO EQUIP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products