30results about How to "Improve color distortion" patented technology

The invention discloses an image dehazing method and system based on a dark channel and a non-local prior, which belongs to the technical field of image information processing. The image dehazing method can reasonably recover a degraded image collected in the haze weather. The method comprises the following steps of (1) calculating a dark channel image of a hazed image; (2) estimating the atmospheric light intensity of the hazed image according to the dark channel image; (3) estimating the transmissivity of the image based on the non-local prior; (4) correcting a transmittance image; and (5) using an atmospheric scattering model to restore a dehazed image. The invention also discloses an image dehazing system based on the dark channel and the non-local prior. The invention can restore scene information in the image realistically and naturally, and the algorithm has the advantages of low complexity, fast running speed and wide application prospect.

The invention discloses an image defogging method based on a generative adversarial network. The method comprises the following steps: 1) obtaining sample data; 2) taking a real foggy image in the sample data as input data of a first generator, wherein the first generator generates a primary fogless image; wherein a real fog-free image in the sample data is used as input data of a second generator, and the second generator generates a primary foggy image; the first discriminator feeds back an error between the primary foggy image and the real foggy image to the second generator, the second discriminator feeds back an error between the primary foggy image and the real fogless image to the first generator, the second generator and the first generator reduce the error, and the truth of the generated image is improved; the generator and the discriminator perform repeated confrontation training to obtain an optimal defogging network model; and (3) performing image defogging. A generative adversarial network structure and a loss function are adopted, network training does not need a foggy-fog-free matching image of the same scene, and meanwhile it is guaranteed that the color of the image is not distorted before and after defogging.

Disclosed is a projection system. The projection system comprises a first light source, a second light source, a color gamut judgment module, a light source controller and a light modulation apparatus; the first light source is used for giving out primary light for modulating an image; the primary light can be used for modulating an image within a first color gamut range; the second light source is used for giving out supplementing light for expanding the color gamut of at least one kind of light from the primary light emitted from the first light source; the color gamut judgment module is used for receiving image data and judging a color gamut range of a to-be-displayed image according to the image data, and outputting a control signal according to the color gamut range; the light sourcecontroller is used for receiving the control signal and controlling the starting and closing of the first light source and the second light source according to the control signal to enable the color gamut range which can be modulated by the light emitted from the first light source and the second light source to satisfy the color gamut range of the to-be-displayed image; and the light modulation apparatus is used for performing image modulation on the primary light and the supplementing light to generate projection light needed by the to-be-displayed image.

The invention discloses a method for correcting a color domain in treating the video signals of an LED display screen, in particular to a method for expanding the color domain of a video source signal by using only one transition matrix, in order to overcome the disadvantages that the color domain of an LED display screen is reduced and the algorithm is complicated in the existing method. The method comprises the following steps: completing the mutual conversion of the video source system between a tri-chromatic system and a CIE1931XYZ color order system by a color/space conversion module; acquiring the chromaticity coordinate of the signal in the CIE1931Yxy chromatic diagram by an XYZ/Yxy normalizing module; expanding and correcting the chromaticity coordinate by one transition matrix in the Yxy colorimetric system; acquiring a new XYZ value from the corrected chromaticity coordinate by a Yxy/XYZ denormalizing module; and acquiring the expanded tri-chromatic value by the color/space conversion module. Accordingly, the invention can emphasize the high color expression of the LED display screen and improve the color distortion thereof by the simpler method.

The invention discloses a flexible defogging method based on dark channel improvement and image fusion. The method comprises the steps that 1, a dark channel graph of a foggy image I(x,y) is calculated; 2, first 0.1% of pixels with maximum brightness are selected in the dark channel graph, and then corresponding maximum brightness values of the pixels in I(x,y) are selected to serve as estimated values of atmosphere light A; 3, rough transmittance of I(x,y) is calculated; 4, box-oriented filtering is used to refine the rough transmittance; 5, the refined transmittance is corrected based on a quadratic function; 6, object light is restored, and a preliminary defogged image is obtained; 7, a pseudo-defogged image of I(x,y) is calculated; and 8, the preliminary defogged image and the pseudo-defogged image are fused to obtain a final defogged image. The method has the advantages that calculation speed is high, and the distortion phenomenon of the defogged image in an adjacent sky region isrelieved; and through weight-adaptive image fusion, the defogging effect and image colors are well balanced, and the phenomenon that the defogged image is dark in color is relieved.

The invention provides a method and a device for converting three-color data to four-color data. The conversion method comprises the steps of: determining a normalized stimulus value signal of a whitesub-pixel according to a minimum value of a first stimulus value signal after gain processing, a second stimulus value signal after gain processing and a third stimulus value signal after gain processing; and regarding a difference value between the first stimulus value signal after gain processing and a red stimulus value signal in a tristimulus value signal of the white sub-pixel as a normalized stimulus value signal of a red sub-pixel, regarding a difference value between the second stimulus value signal after gain processing and a green stimulus value signal in the tristimulus value signal of the white sub-pixel as a normalized stimulus value signal of a green sub-pixel, and regarding a difference value between the third stimulus value signal after gain processing and a blue stimulusvalue signal in the tristimulus value signal of the white sub-pixel as a normalized stimulus value signal of a green sub-pixel, so as to improve the penetration rate of light and screen brightness while solving the problems of large viewing angle color cast and color distortion.

The invention relates to a method for rebuilding color information, wherein it comprises that: via the position weight of pixels near each red/blue pixel, calculating out the color signal difference at horizontal and vertical directions; then via said difference, distributing weight values reversed; averaging the nearby two green pixels vertically and horizontally to obtain two average values; multiplying two average values with relative direction weight values, summing them into the green information of each blue/green pixel; then using dual-linear interpolation method to compensate the lost red and blue elements; using one middle-value selector to correct aberration. The invention has high accuracy, high resolution and uniform color.

The invention relates to the field of display and in particular relates to a composite protective layer and a flexible display unit. The composite protective layer comprises a polyimide layer, and a first hard coating and a first transparent optical adhesive layer which are respectively arranged on two sides of the polyimide layer. At least one of the first hard coating and the first transparent optical adhesive layer contains a nanoscale coloring agent. The invention further relates to a flexible display unit comprising a flexible display panel and the composite protective layer arranged on alight-exiting side of the flexible display panel. The nanoscale coloring agent has a spectrum adjusting effect in a visible light band. The nanoscale coloring agent is added into the first hard coating or the transparent optical adhesive layer, so that light yellow introduced by the polyimide layer can be compensated to produce a needed color, and particularly the polyimide layer is matched to produce white transmission light; and therefore, the condition of color distortion is improved.

The invention discloses an underwater image enhancement method combining multi-channel equalization and multi-scale fusion, and belongs to the field of underwater image enhancement, and the underwater image enhancement method combining multi-channel equalization and multi-scale fusion is realized by the following steps: step 1, performing multi-scale image enhancement; compensating the red channel by using the green channel and secondarily reinforcing the red channel through the mean value of the regional red channel; step 2, using a self-adaptive platform histogram to extend the gray scale range of the R, G and B three channels in a balanced manner and redistributing gray scale values; and step 3, carrying out multi-scale fusion on the brightness V (Value) components processed by the gamma algorithm, the GUM algorithm and the CLAHE algorithm. The method solves the problem of low definition of the underwater degraded image, improves color distortion, improves image contrast and brightness, has obvious enhancement effects on different scenes, and has good generalization adaptability.

The invention discloses a low-illuminance image enhancement method and system, and the method comprises the steps: carrying out the multi-scale feature extraction of a low-illuminance image based on a plurality of convolution kernels, and carrying out the splicing of the multi-scale features, and obtaining a multi-size feature map; performing feature screening on the feature map by using a spatial attention mechanism to obtain a spatial attention feature map; mapping the spatial attention feature map based on three residual blocks connected in series to obtain high-dimensional features; performing weight processing on the high-dimensional features to obtain a channel attention feature map; carrying out channel reduction and logarithm operation on the channel attention features to obtain input image environment illumination component estimation; and processing the image according to the Retinex theory to obtain an enhanced image. According to the method, rich feature information of a low-illumination image is obtained through multi-scale convolution, the depth of the network is effectively deepened by using a residual block, image features are mapped to a high dimension, and the extraction capability of the network on significant information is improved by using space and channel attention in the network.

The invention discloses an image defogging method based on an improved tolerance mechanism, and the method comprises the steps: adding the improved tolerance mechanism to an atmospheric scattering model, obtaining a final image restoration formula, processing a to-be-defogged image O, and obtaining a final restored image F; according to the method, the part of the region which does not meet the dark channel prior rule in the target picture can be compensated more accurately, the defogging capability is prevented from being reduced, and the visual effect of the image is improved.