35results about How to "Remove halo" patented technology

The invention belongs to the technical field of image enhancement and in particular relates to a method, a device and a system for image enhancement based on a YCbCr color space. The method comprises the steps of extracting the luminance component Y in an original image according to the input original image, performing median filtering on the obtained luminance component Y and then performing normalization processing to obtain a normalized image Ym, calculating the average value avgYm of the normalized image according to Ym and judging the measure of the fog concentration of the original image according to the range of avgYm, performing MSR processing and DCP processing on the original image to obtain corresponding processed images Y1 and Y2, putting Y1 and Y2 into a formula X=aY1+bY2 to calculate an image X after fusion processing, and performing automatic contrast control optimization on the image X after the fusion processing to obtain an optimized image, wherein a and b in the formula are fusion coefficients. The method for the image enhancement based on the YCbCr color space is capable of effectively eliminating the halo and over-enhancement phenomena, and therefore, the stability and quality of the output image can be improved.

The invention discloses an image demisting method based on sky segmentation and transmissivity adaptive correction, an iterative threshold segmentation algorithm is used to divide the fogged image into sky region and non-sky region, and the brightness of the segmented sky region is adjusted. A dark channel prior algorithm based on fast bilateral filtering and cubic logarithmic polynomial correctedtransmittance is used to de-fogging the non-sky region. At the same time, the average value of high luminance pixel set in dark channel image is used to ensure that the estimation result of atmospheric light value tends to reasonable value as far as possible. The output image is further enhanced by fast bilateral filter and cubic logarithmic polynomial transform of transmittance, so as to achievethe purpose of denoising, preserving edge and eliminating the edge halo of the scene. The experiment results show that the invention has the advantages of good demisting effect, high color fidelity of the sky region and strong edge retention ability.

Provided is a foreign matter inspection method for positively detecting a foreign matter in the neighborhood of the edge of a mirror-finished substrate without fail. Edge-emphasis and binarization are performed following the taking of an image of a substrate-under-inspection at a contour of its inspection area, to further detect a plurality of sampling points representative of a contour of the inspection area. An estimated inspection area is determined by determining the size, position and rotation angle of contour lines defined, size-reducibly, from the coordinates of the plurality of sampling points. After applying a mask to the binary image data in an area other than the estimated inspection area, a foreign-matter detection step is performed.

The invention relates to a motion compensation method and system based on occlusion detection. The motion compensation method comprises the following steps: carrying out motion estimation to obtain a frontward motion vector and a backward motion vector, and detecting a revealed/shielded region; calculating revealing/shielding probability according to an overlapped area of a position where the motion vector reaches an interpolation frame and a block to be processed and calculating an interpolation weight ; calculating to obtain the motion vector of the interpolation frame according to respective corresponding frontward and backward motion vectors of the former frame and the current frame and a detection result of the revealed/shielded region; detecting a crossed part of the revealed/shielded region and a background through the consistency of the motion vector of the interpolation frame and the interpolation weight and correcting the interpolation weight; carrying out interpolation to obtain pixel-by-pixel interpolation weight; interpolating according to the motion vector of the interpolation frame and the pixel interpolation weight to finally obtain a video with the improved frame rate. The accuracy of detecting the revealed/shielded region is improved and a halo phenomenon in a motion compensation image is remarkably alleviated.

An illumination-improving structure for LED or SMD LED lights is to mount a lamp base at a light head. The lamp base is funnel-shaped and has an interior annular cutout near its top edge. A substrate engages the annular cutout to carry one or multiple LED or SMD LED units at a center or other proper locations. Moreover, a rim is formed on the substrate to surround the LED or SMD LED units. The lamp base further has a light-adjusting lens mounted over the LED or SMD LED units. The light-adjusting lens has an outer convex arc performing a plane with edge surface and has an inner concave arc or an inner planar surface. The plane and the outer convex arc are connected in form of sharp angle attachment. The inner concave arc or the inner planar surface are treated with foggy treatment or coated with foggy paper.

The invention provides a video style conversion method based on a self-encoding structure and gradient order preserving, which is used for solving the technical problem that halo is generated at the edge of a foreground target in a stylized video in an existing video style conversion method. The method comprises the following steps: 1) constructing a training sample set and a test sample set; 2) constructing a video stylized network model; 3) training the video stylized network model; 4) testing the trained video stylization network model; and 5) obtaining a video style conversion result. According to the invention, through constructing a video stylization network model based on a self-encoding structure and a gradient order-preserving loss function, the time consistency constraint is redefined in a more reasonable mode, halo generated by the foreground target edge in the stylized video is effectively eliminated, texture detail information of the original video is reserved, the visualsense experience of people is improved, and the method can be used for completing later manufacturing and processing of photography and movie and television works.

The invention discloses a night face video image enhancement and noise reduction method. Information processing technology field, The method comprises the following steps: firstly, converting a face video image from an RGB space to an HSV space; carrying out BEMD decomposition on the V component of the image; adaptively decomposing into a plurality of IMF components according to a certain rule; filtering the low-frequency IMF component and removing the irradiation component in the low-frequency IMF component; the high-frequency IMF component is textured; The method comprises the following steps: firstly, enhancing information such as details and denoising, reconstructing the processed IMF components to obtain denoised and enhanced V components, performing self-adaptive contrast enhancementon the processed V components, and reconstructing the V components with H and S components subjected to wavelet denoising to obtain denoised and enhanced face video images. According to the method, detail information such as edges and textures can be sharpened while the contrast ratio of the image is effectively enhanced, the definition of the image is effectively improved, and the halo problem in night face image enhancement can be solved.

The invention discloses an image blurring method, an image blurring device, equipment and a storage device. The image blurring method comprises the steps: determining weights and pixel values of pixelpoints contained in a to-be-blurred image, wherein the weights of foreground pixel points in the to-be-blurred image are lower than the weights of background pixel points; performing blurring processing on the background pixel points by utilizing the weights and the pixel values to obtain a blurred background image; and obtaining a blurred image according to the blurred background image and the foreground pixel points. According to the scheme, the image blurring can be realized, and the halo problem is eliminated.

The invention discloses an anti-blooming implementation method for an image sensor. Hardware consists of a microprocessor or programmable logic circuit, a CCD (Charge Coupled Device) front-end signal processor AD9923 and a CCD image sensor ICX274, wherein the microprocessor or programmable logic circuit is used for transmitting data to the CCD front-end signal processor through a serial communication interface; the CCD front-end signal processor is used for transmitting a driving signal to the CCD image sensor under dual control of an original normal light-sensitive driving time sequence and a newly-added blooming-removing driving time sequence; and the CCD image sensor is used for outputting a blooming-removed image signal. The blooming-removing driving time sequence is arranged between original two frames of normal light-sensitive driving time sequences. The method has the advantages of easiness, wide application range, high operability and remarkable effect.

The invention relates to a gray level image compression method and device, computer equipment and a computer readable storage medium. The method comprises the following steps that: calculating the histogram cumulative distribution function of an initial gray level image to be compressed; extracting the basic layer of the initial gray level image, and obtaining the luminance average value of the basic layer; and according to the histogram cumulative distribution function, the basic layer of the initial gray level image and the luminance average value of the basic layer, obtaining the target compression image of the initial gray level image. By use of the method, image complexity is subjected to simplified processing, and meanwhile, an imported halo is eliminated.

The invention discloses an image blurring method, an image blurring device, equipment and a storage device. The image blurring method comprises the steps: acquiring an original background image of a to-be-blurred image, wherein the original background image comprises an invalid area corresponding to a foreground part of the to-be-blurred image; performing pixel value filling on the invalid area byutilizing an effective pixel value, located outside the invalid region, of the original background image to obtain a filling background image; performing blurring processing on the filling backgroundimage to obtain a blurred background image; and fusing the blurred background image and the foreground part of the to-be-blurred image to obtain a blurred image. According to the scheme, image blurring can be realized, and the halo problem is eliminated.

The invention provides an anti-background difference-based cell image segmentation method. The method comprises the steps: (A1) carrying out the noise reduction of an obtained original cell image, and obtaining a first image; (A2) performing anti-background difference processing on the first image to obtain a second image; (A3) carrying out global threshold segmentation processing on the second image to obtain a third image; and (A4) carrying out hole filling and image filtering on the cell region in the third image to obtain a fourth image. The method has the advantages of high segmentation precision, high efficiency and the like.

Luminescent glass comprises a glass substrate, a glass cover plate, an interlayer, and a light-emitting diode, wherein the interlayer and the light-emitting diode are arranged between the glass substrate and the glass cover plate, a conducting circuit is formed on the surface of the glass substrate, the light-emitting diode is fixed on the conducting circuit, an opening which contains the light-emitting diode is formed inside the outer contour of the interlayer, light emitted by the light-emitting diode passes through the opening and is emitted from the glass cover plate, and the interlayer, the glass substrate, and the glass cover plate are fixed at the position near the outer contour of the inter layer. The luminescent glass can prevent halo from being generated, and achieves good light-out effect. The invention further provides a manufacturing method of the luminescent glass.

A screen composite provided on a face plate of a flat panel display device, said screen composite containing an aluminum layer and a metal layer formed on said aluminum layer for substantially reducing a halation phenomenon.

The invention discloses a total reflection type halation-eliminating and light-beam-homogenizing optical system. The total reflection type halation-eliminating and light-beam-homogenizing optical system comprises a first hyperboloid reflecting mirror, a first off-axis parabolic mirror, a first curved-surface reflecting mirror array, a second curved-surface reflecting mirror array, a second off-axis parabolic mirror and a second hyperboloid reflecting mirror and is characterized in that the light beam deflection angles of all the mirrors are 90 degrees, and the central symmetry faces of all the mirrors are located on the same plane. The total reflection type halation-eliminating and light-beam-homogenizing optical system novel in structural design is based on the combining features of the hyperboloid reflecting mirrors and the off-axis parabolic mirrors, the light beam homogenizing and shaping and halation eliminating features of the two reflecting mirror arrays and the direct water cooling performance and good thermal conductivity of the metal mirrors, is applicable to the homogenizing and shaping of optical output type laser, especially has advantages in the light beam homogenizing of myriawatt, high-power and large-optical-fiber-diameter optical fiber output type laser devices, can greatly increase the application performance of laser machining such as laser cladding and quenching.

The invention discloses a dedicated magnifier for a digital camera. The magnifier is characterized in that the magnifier comprises a magnifying lens, a light source, sight glass and a shell; the magnifying lens, the light source and the sight glass are fixed to the shell; the magnifying lens is a combined lens formed by two flat convex lens with different curves; when the planes of the two flat convex lenses are opposite, the amplifying times of the combined lens are more than or equal to 5; the light guide part of the light source is a foggy LED; the diameter of the LED is more than or equal to 5mm. The dedicated magnifier belongs to the apparatus cleaning field, is suitable for observing the dust on the lens surface of an apparatus and especially suitable for observing the dust on a surface of an image sensor of a digital single lens reflex camera and in a cavity. The dedicated magnifier aims at eliminating halos generated on a CCD/CMOS surface of the digital camera and clearly observing the dust and a cleaning degree of the surface of the image sensor of the digital single lens reflex camera. The magnifier is simple in structure and the halos generated on the surface of the digital camera are effectively eliminated.