136results about How to "Avoid color distortion" patented technology

The invention provides a multi-scale gradient domain image fusion algorithm which is used for fusing infrared thermal images with visible light images. The multi-scale gradient domain image fusion algorithm is characterized by comprising the following steps: a step of constructing gradient fields; a step of correcting gradient fusion weight; a step of reconstructing gradient fields; and a step of fusing images through a transparency method. The multi-scale gradient domain image fusion algorithm provided by the invention can be used for simultaneously reserving temperature rise areas and detail information of infrared thermal images and visible light images, removing a halation background-effect phenomenon and redundant information due to interaction among images and avoiding color inconsistency of an infrared thermal image temperature rise area.

An OLED display including a display panel having a plurality of R, G, and B pixels formed and at least one of a high-potential and low-potential driving voltage supply line disposed; a data driving circuit; a gamma reference voltage generating circuit for generating gamma reference voltages for R, G, and B by dividing voltages of high-potential gamma power sources; a current estimating circuit for generating digital estimated current values for R, G, and B; a current sensing circuit for generating digital sensing current values for R, G, and B; and a gamma power source control circuit for controlling the high-potential gamma power sources by comparing the digital estimated current values for R, G, and B with the digital sensing current values for R, G, and B so that driving currents corresponding to the respective digital estimated current values flow in the respective R, G, and B pixels.

The invention discloses a color image enhancement method based on improved multi-scale Retinex. Firstly an unprocessed color image is read, a conventional multi-scale Retinex algorithm is improved, and the average brightness component of a current pixel is calculated by adopting bilateral filtering so that brightness component estimation based on the bilateral filtering method is obtained; secondly local contrast enhancement is performed according to the size relation of brightness of each pixel point and domain average brightness thereof; and finally the brightness image after enhancement is compared with the brightness component of the original image, RGB information of the recovered and enhanced image is linearly adjusted, and color image enhancement is obtained finally. The color image enhancement method has advantages of image detail recovery, elimination of the "halo" phenomenon, meeting the human eye visual effect and short operation time.

The invention discloses a colored planar display panel and a corresponding colored planar display device. The colored planar display panel comprises a plurality of pixels, a plurality of scanning lines and a plurality of data wires, wherein each pixel comprises a first color sub-pixel, a second color sub-pixel and a third color sub-pixel; each scanning line is electrically connected with a corresponding line of sub-pixels along the line direction respectively; each data wire is electrically connected with a corresponding row of sub-pixels along the row direction respectively; and first-color sub-pixels, second-color sub-pixels and third-color sub-pixels in each pixel are arranged along the row direction, so that the corresponding line of sub-pixels electrically connected with each scanning line are sub-pixels of the same color. The sub-pixels in each line are sub-pixels of the same color, so that gamma reference voltages of corresponding colors can be received correspondingly, and cross-color is avoided.

The invention provides a single image defogging method based on a convolutional neural network. The method comprises the steps that firstly, a training set is constructed to serve as input of a deep convolutional neural network model, the network model comprises a shallow neural network model and a deep neural network model, and the shallow neural network model is used for extracting and fusing features of RGB color space of a foggy image and outputting a scene depth map of the foggy image; and the deep network model performs multi-scale mapping, pooling, convolution and other operations on the scene depth map on the basis of the shallow network model, and outputs a transmissivity map of the foggy image. And finally, recovering the fog-free image through the transmissivity, the atmosphericlight value and the atmospheric scattering model. According to the method, the characteristics of the RGB color space of the atomized image are extracted and fused to construct the shallow convolutional neural network model, and the shallow convolutional neural network model is connected with the multi-scale deep neural network model to establish the end-to-end neural network model, so that defogging clearness can be realized in various scenes, and particularly, color distortion of the image can be avoided in a dark environment.

The invention relates to a Retinex-theory-based low-illumination low-altitude remote sensing image enhancing method, mainly comprising the following steps of: transforming a low-illumination low-altitude remote sensing image from a red, green, blue (RGB) color space into a hue, saturation, intensity (HSI) color space; adjusting a luminance component I and a saturation component S on the premise of guaranteeing that a hue component H is not changed, so that the processed image accords with visual characteristics of eyes of a human body and a color distortion phenomenon is avoided; transforming the enhanced image from the HIS color space into the RGB color space; and performing convolution operation by using a laplace operator and an original image to obtain an edge image; and superposing the enhanced image and the edge image to obtain the finally enhanced image. By virtue of the method, the luminance and the contrast of the low-illumination low-altitude remote sensing image are improved, the color distortion phenomenon is avoided, and the low-illumination low-altitude remote sensing image has rich edge information and accords with the visual characteristics of the eyes of the human body.

The invention provides a method and device for processing a signal lamp image. The method includes the steps that S1, signal lamp marginal information in one frame of image collected through a camera is detected; S2, according to the signal lamp marginal information, a signal lamp area is segmented from the image; S3, color strengthening is performed on the signal lamp area in the image. The device comprises a marginal detecting module, an area segmenting module and a color strengthening module, wherein the marginal detecting module is used for detecting the signal lamp marginal information in one frame of image collected through the camera, the area segmenting module is used for segmenting the signal lamp area according to the signal lamp marginal information, and the color strengthening module is used for performing color strengthening on the signal lamp area in the image. The method and device for processing the signal lamp image can solve the problem that the color of a signal lamp in the collected image is distorted when illumination intensity of the environment where the camera is located is too high or too low.

A black/white stretching system using R, G, B information and a method thereof. The black/white stretching system includes a first transformer to transform a luminance value and a color difference value of an input image to R, G, B values of each pixel, a histogram estimator to estimate a histogram distribution by accumulating each of the transformed R, G, B values of each pixel of the input image with a same weight, a mapper to generate mapped R′, G′, B′ values by mapping the transformed R, G, B values according to a mapping function generated based on the estimated histogram distribution, and a second transformer to generate an output image by reverse-transforming the mapped R′, G′, B′ values from the mapper to an updated luminance signal and an updated color difference signal. Therefore, the black/white stretching system prevents color distortion generated in a primary color image using only luminance information.

The invention discloses a colour camera automatic white balance processing method and device under low illumination. The method comprises the following steps: the mapping relationship table of exposure parameters of images, the environment infrared light intensity and infrared light image intensity estimated values is obtained through training; an image to be processed is acquired and the exposure parameters corresponding to the image are acquired, the current environment infrared light intensity information is detected on a real-time basis, and the current infrared light image intensity estimated value is acquired according to the exposure parameters, the environment infrared light intensity information and the mapping relationship table; the infrared influence removing process is performed on the image to be processed according to the current infrared light image intensity estimated value; and white balance correction is performed on the processed image obtained through the infrared influence removing process. By adopting the method and device of the invention, the chromatic aberration problem caused by the reason that correction cannot be performed effectively due to the influences of infrared light in the automatic white balance process under the low illumination condition can be avoided to make a color image having the advantage of high quality still can be obtained under low illumination.

The invention discloses a method used for Bayer Data interpolation which includes steps as follows: calculating gradient value on three directions through R or B component contained by a present pixel point, selecting a pixel point containing G component on one side with minitype edge difference value of two edge direction sides for restoring G component of the present pixel point. The method solves problem of rough edge transition caused by bilinear interpolation. The method can restore lack B or R component in the present pixel point for avoiding color distortion of gradient color bilinear interpolation caused by mistake judgement.

The invention is suitable for the technical field of image processing, and provides an image dehazing method and device and a mobile terminal. The method includes the steps that an atmospheric light value of an input image is estimated; transmittance of the input image is estimated according to a foggy weather imaging module and a dark channel prior rule; the transmittance is optimized to obtain optimized transmittance; the optimized transmittance is modified through a guide filter to obtain a transmission propagation graph; the input image is restored to be a fogless image according to the foggy weather imaging module, the atmospheric light value and the transmission propagation graph. According to the method, when dehazing is carried out on the input image, a transmittance optimization mechanism is introduced, and accordingly the estimated transmittance can be optimized to obtain the optimized transmittance. The dehazing method in which the optimized transmittance is introduced can be suitable for images with a large number of grey areas; when the images are processed, color distortion of the grey areas can be avoided, and the requirement of outdoor photographing of users can be completely met.

The invention relates to a convolutional neural network defogging algorithm based on regional division and heavy fog preprocessing. The algorithm comprises the following steps that: dividing a foggy image into non-overlapped image blocks; for each image block, calculating the dark channel value Di of each image block; distinguishing a heavy fog image block and a mist image block; independently estimating transmissivity; and defogging Pi to obtain a fogless image block.

The invention discloses a single image defogging method, which mainly solves the problems of constrained nonlinear fitting ability, cumbersome training and single applicable scene in the prior art. The scheme comprises: constructing a convolutional neural network consisting of a feature sharing part, a haze atmospheric light value estimation branch and a transmittance estimation branch under the Caffe framework; acquiring a group of fog-free image set J, artificially fogging J to obtain a fog image set I; averagely dividing I and J into multiple paired image groups by batch size, and sequentially inputting in order for 200000 times to the neural network for training; inputting the image I that needs to be defogged into the trained neural network, and outputting the atmosphere light value Aand transmittance T; and calculating according to the atmosphere light value A and transmittance T to obtain a fog-free image J. The invention may well maintain the contrast and color saturation of the restored image, with the peak signal to noise ratio and the structural similarity both superior to the prior art, and may be used for the clear processing of the foggy image.

The invention provides a traffic image defogging method based on an improved generative adversarial network. The method comprises the following steps: establishing a traffic image defogging data set; establishing a generator network and a multi-scale discriminator network based on mixed attention, and optimizing a loss function; training a mixed attention-based generator network and a multi-scale discriminator network by using the established traffic image defogging data set; and inputting an image needing to be defogged into the trained generator network to obtain a defogged image. According to the method, the problems of color distortion, detail loss and non-ideal defogging effect of a dense fog area during defogging of the traffic image can be solved.

The invention relates to an intelligent terminal-based virtualized fitting method which is applied to a virtualized fitting system formed by an intelligent terminal, a third party fitting platform and at least one apparel design terminal; an apparel factory sends apparel parameters of all apparel samples to the third party fitting platform, the third party fitting platform builds apparel sample virtual fitting models, a client sends own actual posture parameters to the third party fitting platform, and the third party fitting platform builds a human body virtual fitting model of the client after building a human body three dimensional sample model in advance; recommended apparel samples matching with the actual posture parameters of the client, corresponding recommended apparel sample virtual fitting models, all stored apparel sample parameters and the apparel sample virtual fitting models are obtained after screening operation and then sent to the intelligent terminal of the client; the client puts favorite apparel sample virtual fitting models on the human body virtual fitting model of the client on the intelligent terminal, and whether dressing effects are satisfying can be observed.

The invention discloses a dark channel sky area defogging method based on threshold segmentation optimization, and mainly solves the situation of poor processing effect of the sky area of an image of a foggy day in the prior art. The realization steps of the dark channel sky area defogging method based on threshold segmentation optimization are that (1) a randomly selected foggy image including the sky area is inputted, and the dark channel value and the atmospheric light value of the image are calculated in turn; (2) the transmission graph of the foggy image is solved; (3) orienting filtering is performed on the transmission graph so that the optimized transmission graph is obtained; (4) the sky area is marked; and (5) transmittance of the sky area is amplified so that the defogged image is restored. Fog information of non-sky areas of the image of the foggy day can be effectively eliminated, and the sky area processing effect can be optimized so that the phenomenon of color distortion and halation of the sky area can be avoided, and thus the dark channel sky area defogging method based on threshold segmentation optimization can be used for image enhancement and video monitoring.

The invention discloses an image gray-world white balance adjustment method and device based on a color temperature curve. The method comprises the following steps: selecting a target image block in a target image, a first color component ratio and a second color component ratio of the target image block meeting function relationship of a preset color temperature curve; calculating gain coefficients of R, G, B three color channels of the target image through a gray world algorithm according to RGB values of all pixel points in the target image block; and adjusting color values of the target image through the gain coefficients. The gain coefficients of the R, G, B three color channels of the target image are calculated based on color information of the target image block instead of color information of the whole target image; and then, the color values of the target image are adjusted based on the gain coefficients, so that the color information of the adjusted image is basically same with the original color information, color distortion does not occur, and the method is better in applicability.

The invention relates to a full-color layered slicing algorithm based on a three-dimensional model of texture mapping. The full-color layered slicing algorithm based on the three-dimensional model oftexture mapping includes the steps that a three-dimensional model file of texture mapping is analyzed, a triangular mesh adjacent topological relation based on color information is established, and fast query of triangular mesh adjacent information of the color information is realized; the fast intersection operation of color information triangular meshes and a tangent plane is realized, positioncoordinates and texture coordinates of all vertexes in each layer are obtained, the vertexes are connected in sequence to form a full-color two-dimensional contour, and the full-color two-dimensionalcontour is filled; and a full-color bitmap is generated, the position of the full-color contour in the bitmap is precisely located according to the position of a colourless model in a printing platform, the thickness of the contour is increased appropriately, and the function of layer-upon-layer printing and layer-upon-layer coloring is achieved. The full-color layered slicing algorithm based on the three-dimensional model of texture mapping has high slicing efficiency, the surface colors of the model are realistic, the reduction degree is high, the aftertreatment process of coloring the modelis omitted, the requirement for proficiency of operators is greatly reduced, the forming quality of parts is improved, and a real sense of color three-dimensional printing is realized.

The invention relates to a low illumination image enhancement method based on a foggy day degradation model. Firstly, the low illumination image is inverted to get the pseudo-fog image. Then the transmittance is calculated by convolution neural network and the local atmospheric light value is used instead of the global atmospheric light value. Finally, the non-fog image is restored based on the atmospheric scattering model, and the enhancement result of low illumination image is obtained by reversing the non-fog image. The method of the invention not only effectively improves the brightness ofthe low-illumination image, but also avoids obvious color distortion, over-exposure and other phenomena, and has good image visual effect after enhancement.

The invention discloses a frog day image rapid restoration method based on feedback mean value filtering, for restoration processing of a frog day image. The method takes an atmosphere scattering model as a basis, comprises specific steps shown in an attached drawing 1 of the abstract of the descriptions, and mainly involves restoration of the frog day image through four steps including image preprocessing 2, atmosphere light value estimation 7, transmission graph estimation 12 and tone adjustment 14. The main technical features of the invention comprise weight graph establishing 4, mean value filtering 9, parameter repairing fuzzy edge feedback 10 and high-light area transmissivity self-adaptive correction 11. The advantages are as follows: atmosphere light values can be accurately estimated, influences exerted by a non-sky high-light area are avoided, at the same time, the complexity of the algorithm for estimating a transmission graph is low, and quite good restoration effect can be achieved within a short period. The method provided by the invention is applied to restoration processing of a degraded image under the condition of foggy weather, dusty weather and the like.

The invention discloses a method and device for adjusting the color temperature of a screen. The method comprises the steps: detecting an RGB value of a pixel in a user interface of a terminal; acquiring tone information of the user interface according to the RGB value; acquiring a color temperature value corresponding to the tone information of the user interface according to the preset correspondence of the color tone and the color temperature; and adjusting the color temperature of the screen according to the acquired color temperature value. By adopting the method and device, the color temperature of the screen can be dynamically adjusted by the terminal along with the variation of the user interface, so that the color temperature of the screen is matched with the user interface. When the color tone of the user interface is relatively cool, the color temperature of the screen is correspondently lowered, and the color is enabled to be warmer; when the color tone of the user interface is relatively warm, the color temperature of the screen is correspondently increased, so that the color is cooled, the final display effect of the user interface is more natural and more real by virtue of mutual integration and mutual counteraction, the distortion of the picture color is avoided, the display effect of the terminal is improved, and the user experience is enhanced.

The invention provides an OLED pixel and a display panel using the same. The OLED pixel comprises three sub-pixel groups. Each sub-pixel group comprises a first sub-pixel and a second sub-pixel, wherein the first sub-pixel and the second sub-pixel share one driving circuit, and the light emitting waveband of the first sub-pixel and the light emitting waveband of the second sub-pixel are complementary. The sum of the light emitting wavebands of the first sub-pixels of the sub-pixel groups is a white light waveband. According to the OLED pixel and the display panel using the same, the sub-pixels are formed by means of the principle of diffraction of light and the combination of white light OLED light emitting bodies, beam splitting pieces and light barriers. Due to the fact that the six kinds of sub-pixels all adopt the white light OLED light emitting bodies, the problem of chromatic aberration caused by different aging degrees of different materials is avoided. Due to the fact that three kinds of sub-pixels are additionally arranged to assist imaging processing, luminous efficiency of the OLED pixel is improved and power consumption is reduced. Due to the fact that the two sub-pixels of each sub-pixel group share one driving circuit, the distinguishability of the OLED display panel is improved.