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

257results about How to "Reduce image noise" patented technology

System and method for image noise reduction using a minimal error spatiotemporal recursive filter

Certain embodiments of the present invention provide a system and method for reducing image noise with the use of a minimal error spatiotemporal recursive filter. An input image is filtered both temporally and spatially, producing a temporal output and a spatial output. Both the temporal output and the spatial output are correlated with the input image to produce a temporal correlation output and a spatial correlation output. The temporal correlation output and the spatial correlation output are mixed to generate a selecting signal. The selecting signal directly or indirectly determines the composition. of an output image. The selecting signal may select a portion of the temporal output and a portion of the spatial output to compose an output image. Alternatively, the selecting signal may select either the temporal output or the spatial output to compose an output image.
Owner:GE MEDICAL SYST GLOBAL TECH CO LLC

CT (Computed Tomography) value correcting method for cone-beam CT

The invention discloses a CT (Computed Tomography) value correcting method for cone-beam CT. The CT value correcting method comprises the following steps: scanning air, a water phantom and a bone tissue body phantom under different scanning conditions to respectively obtain projection data; reestablishing an image; removing noise and artifacts by adopting a polynomial fitting method based on a template image; selecting a plurality of interested regions and calculating a mean value of an attenuation coefficient and a standard deviation of the attenuation coefficient; obtaining the value range of the attenuation coefficient and taking the attenuation coefficient of maximum occurrence probability; fitting the attenuation coefficients of the air, the water phantom and the bone tissue body phantom under the different scanning conditions with corresponding ideal CT values to obtain respective fitting curves; performing CT scanning and image reestablishment on a scanned material; obtaining a CT value image according to a material attenuation coefficient image and a fitting curve and finishing the CT value correction. According to the CT value correcting method disclosed by the invention, image noise and artifact can be effectively reduced, the reestablished image of single material reaches the uniformity to the great degree, the precision of the attenuation coefficient of the material becomes higher and further high accuracy for the fitting of the curve of the CT value and the material attenuation coefficient is realized.
Owner:NORTHEASTERN UNIV

Image lens assembly

An image lens assembly includes, in order from an object side to an image side, a first lens element, a second lens element, a third lens element, a fourth lens element and a fifth lens element. The first lens element with positive refractive power has a convex object-side surface. The second lens element has negative refractive power. The third lens element with refractive power is made of plastic material, and has at least one surface being aspheric. The fourth lens element with refractive power is made of plastic material, and has a concave object-side surface and a convex image-side surface, wherein at least one surface of the fourth lens element is aspheric. The fifth lens element with positive refractive power is made of plastic material, and has a convex object-side surface and a convex image-side surface, wherein at least one surface of the fifth lens element is aspheric.
Owner:LARGAN PRECISION

System and Method for Denoising Medical Images Adaptive to Local Noise

A system and method is provided for estimating the local noise of CT images and denoising the images using a modified non-local means (NLM) algorithm that is adaptive to local variations of noise levels. A strategy for efficiently estimating the local noise of CT images is also described.
Owner:MAYO FOUND FOR MEDICAL EDUCATION & RES

Color image segmentation method based on Gaussian mixture model and support vector machine

InactiveCN102637298AProcessing speed will not be greatly affected byReduce configuration requirementsImage analysisColor imageSupport vector machine
The invention discloses a method for segmenting color images by means of combining a Gaussian mixture model and a support vector machine. The method mainly includes extracting characteristics of an image; building the Gaussian mixture model; and classifying by the aid of the support vector machine. A particular process mainly includes firstly, extracting color characteristics and texture characteristics of the image; then building the Gaussian mixture model and obtaining new characteristics of the extracted original characteristics by the aid of the Gaussian mixture model; secondly, obtaining an initial segmentation result by the new characteristics; and finally selecting training samples according to the initial segmentation result, classifying the training samples by the aid of the support vector machine and obtaining a final segmentation result. When the characteristics are described, the image is initially segmented according to the new characteristics obtained via the Gaussian mixture model (GMM) without being based on the original characteristics, and the final segmentation result is obtained by the aid of the support vector machine (SVM). Time-space domain information of the image is sufficiently utilized, shortcomings of the Gaussian mixture model (GMM) which builds a module with a complicated background only by the aid of time domain information are overcome, and segmentation accuracy is effectively improved.
Owner:LIAONING NORMAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products