84 results about "Luminance channel" patented technology

The invention discloses an endoscope multi-region semantic perception time domain fusion adaptive white balance algorithm. The algorithm comprises the following steps: acquiring an endoscope image; performing tissue region division on the endoscope image through a lightweight semantic segmentation network to obtain a plurality of region images; converting each regional image from an RGB space to a YCbCr color space, separating a brightness channel Y from chrominance channels Cb and Cr, and calculating a channel mean value of the chrominance channels Cb and Cr; calculating the average offset of the chrominance channels Cb and Cr according to the calculated channel average of the chrominance channels Cb and Cr; performing white point detection on each regional image to obtain an RGB three-channel mean value; combining the calculated mean offset of the chromaticity channels Cb and Cr, the RGB three-channel mean obtained by white point detection of each regional image and a statistical index to form a multi-dimensional regional color feature vector; and fusing historical frame features with the regional color feature vector to obtain a feature vector based on space-time fusion.

A method comprising: receiving an image block unit of a frame, the image block unit comprising samples in color channels comprising at least one chrominance channel and one luminance channel; reconstructing samples of said luminance channel of the image block unit; determining a reference area for predicting target samples of at least one color channel of the image block unit, wherein said reference area comprises one or more reference samples in a neighboring block in current color channel / frame, in the neighboring of a co-located block in reference color channel / frame; and / or inside the co-located block in reference color channel / frame; determining weights for predicting said target samples based on a ratio between a normalized luminance histogram in said reference area and a normalized luminance histogram co-locating said target samples; determining filter coefficients of a filter for said predicting based on the weights, the reference samples and a shape of the filter; and predicting samples of at least one color channel of the image block unit based on the samples of said luminance channel and the filter coefficients.

The invention belongs to the technical field of image data processing, and particularly discloses a low-illumination image dynamic enhancement method and device, a medium and a program product, and the method comprises the steps: obtaining a to-be-processed low-illumination image, converting the to-be-processed low-illumination image into a YCbCr color space, and extracting a brightness channel of the to-be-processed low-illumination image; the brightness channel is input into an adaptive enhancement intensity parameter prediction module, the adaptive enhancement intensity parameter prediction module learns illumination features of the brightness channel through a residual block and a channel attention mechanism, and an adaptive enhancement intensity eta value is output; and inputting the original RGB image, the brightness channel and the eta value into the low-illumination image enhancement network, realizing refined enhancement through multi-scale feature fusion, and outputting an enhanced image. According to the method, the self-adaptive enhancement intensity parameter prediction module and the low-illumination image enhancement network are fused, a new low-illumination image enhancement network is formed, automatic regression estimation and de-interactive image enhancement of the self-adaptive enhancement intensity eta value are realized, and the intelligence and robustness of image brightness recovery are effectively improved.

The invention provides a high-fidelity anti-compression image watermarking method and system based on spectrum-airspace decoupling, and belongs to the field of information security. Firstly, the watermark information is mapped and remodeled; a watermark encoder based on multi-granularity spectrum-spatial domain feature decoupling is constructed, discrete cosine transform is introduced to filter out high-frequency components, Haar wavelet transform is adopted to realize lossless downsampling, a fast Fourier transform dynamic filter is combined to capture global semantic features, and local texture details are combined through multi-scale spatial domain volume accumulation; designing a physical perception and visual self-adaptive dual embedding strategy, and anchoring watermark energy to an anti-compression brightness channel; constructing an anti-attack layer containing differentiable JPEG compression simulation and mixed noise simulation, and participating in network training; and constructing a decoder and designing a loss function to carry out network optimization. According to the method, the robustness of the watermark under strong compression and complex black box attacks is improved, and extremely high visual imperceptibility is realized through physical and visual constraints.

The invention relates to an underwater image quality improvement method based on Retinex heuristic color correction and saturation driving. The method comprises the following steps: obtaining an underwater image after color correction; extracting a brightness channel, and decomposing the brightness channel into a base layer and three detail layers; estimating the transmissivity of the underwater image after color correction; and obtaining an underwater image with enhanced contrast and details, namely an enhanced image. According to the method, segmented channel compensation based on the maximum mean value is performed on the basis of channel characteristic difference observation of an underwater scene, the difference can be adapted in a targeted manner, and accurate channel compensation is realized; the color brightness is improved; the overall visual experience of the image is improved, and the color cast problem of the underwater image is effectively corrected; the accuracy and efficiency of underwater image transmissivity estimation can be obviously improved; according to the method, the fog effect removal of the image base layer and the enhancement of the gradient information of the multi-level detail layer are synchronously realized by using the estimated transmissivity, and finally the high-quality underwater image is generated.

A method comprising receiving an image block unit of a frame, the image block unit being predicted using a cross-component prediction mode and comprising samples in color channels comprising at least one chrominance channel and one luminance channel (900); determining intra prediction direction based on the samples of said luminance channels of the image block unit, samples in a neighborhood of the luminance channel of the block unit and / or samples in the neighborhood of the block unit (902); selecting a low-frequency nonseparable transform index for low-frequency non-separable transform using the determined intra prediction direction (904); and performing the low-frequency non-separable transform using the selected low-frequency non-separable transform index (906).

A method comprising receiving an image block unit of a frame, the image block unit comprising samples in a first chrominance channel, chrominance channel, a second chrominance channel and one luminance channel; defining co-located reference areas over luminance components of the luminance channel, chroma components of the first chrominance channel and chroma components of the second chrominance channel; performing motion-compensated prediction for the luminance component, the first chrominance component and the second chrominance component using reference frames and motion vectors; obtaining a first mapping function that maps the luminance component into the first chrominance component and a second mapping function that maps the luminance component into the second chrominance component using the co-located luminance prediction and the chrominance predictions; reconstructing a luminance residual; and obtaining a first chrominance prediction by using the first function and the luminance residual, and a second chrominance prediction by using the second function and the luminance residual; and obtaining a first chrominance prediction by using the first function and the luminance residual, a second chrominance prediction by using the second function and the luminance residual.

A method comprising: receiving an image block unit of a frame, the image block unit comprising samples in color channels comprising at least one chrominance channel and one luminance channel; reconstructing samples of said color channels to produce reconstructed chrominance samples and reconstructed luminance samples; determining that a picture-level model list re-ordering is used; means for determining a reference picture; determining a list of cross-component models for the reference picture; generating a re-ordered list where the cross-component models of the determined list have been re-ordered; determining an index for a cross-component model; means for deriving the cross-component model from the re-ordered list with the given index; applying a first adaptive in-loop filter for the reconstructed luminance samples; and the derived cross-component model for the reconstructed luminance samples to obtain an additional input for reconstructing the chrominance samples.

The present application relates to the technical field of image processing, and particularly relates to an infrared and visible light image fusion method, system, device and storage medium, comprising obtaining an infrared image and a visible light image, and converting the visible light image to a YUV color space by using a color space conversion method to obtain original luminance channel data and original chrominance channel data of the visible light image; performing feature extraction on the original luminance channel data of the infrared image and the visible light image respectively to obtain different modal image features; introducing a gradient attention mechanism to perform gradient-guided feature fusion on the different modal image features to obtain modal fusion feature information; and performing feature reconstruction according to the modal fusion feature information and the original chrominance channel data of the visible light image to obtain a color fusion image. The present application combines a feature extraction network and gradient weights of different modal image features to highlight and retain texture details, thereby improving the quality of infrared image and visible light image fusion.

The invention belongs to the technical field of image processing, and particularly relates to a dim light blurred image restoration method based on double-branch brightness-chrominance attention. The method comprises the following steps: acquiring a to-be-processed dark light blurred image, converting the to-be-processed dark light blurred image into a YUV color space, separating a Y brightness channel and a UV chromaticity channel, and obtaining a shallow brightness feature and a shallow chromaticity feature; inputting the shallow brightness features and the shallow chromaticity features into a pre-trained DB-LCANet network for processing to obtain deep brightness features and deep chromaticity features; obtaining a restored image according to the deep brightness feature and the deep chromaticity feature; the DB-LCANet network is composed of six DBSCAB modules which are connected in sequence; according to the method, the brightness information and the color information are processed separately, brightness enhancement in a new color space does not influence the color information any more, so that the problems of color distortion and excessive brightness improvement possibly caused in the dark light enhancement process are avoided, and the method has a good application prospect.

The invention provides an image display method and device, a storage medium and electronic equipment, and the method comprises the steps: converting a first image displayed on a screen of terminal equipment into a gray image, and then carrying out the Fourier transform operation of the gray image, and obtaining a first frequency spectrum image corresponding to the gray image. And enhancing the frequency intensity of each frequency in the first frequency spectrum image to obtain a second frequency spectrum image. And performing inverse Fourier transform operation on the second frequency spectrum image to obtain a gray level image corresponding to the second frequency spectrum image, and converting the gray level image corresponding to the second frequency spectrum image into a second image in an RGB color space. And updating the image displayed on the screen of the terminal device from the first image to the second image. According to the image display method provided by the embodiment of the invention, by enhancing the frequency intensity of each frequency in the frequency spectrum image corresponding to the brightness channel, the definition of image display can be improved, and the visual experience of a user is improved.

A method of processing a mammogram image, including receiving a digital mammography image of a breast of a patient, and separating the digital mammography image into three channels. The method includes removing noise and uneven illumination to form a first set of three uniform background images, and separating a luminance channel and a chrominance channel from the first set with a transfer function to form a second set of three uniform background images. The method includes applying principal component analysis to the second set; and assembling a single grayscale image and applying a first subspace projection. The method includes removing at least a portion of a pectoral muscle from the grayscale image, and normalizing the muscle removed image using a second order Gaussian Laplacian and an oriented diffusion filter to form a processed image. The method includes identifying cancerous and / or noncancerous regions in the processed image.

The application discloses a multi-stage information interactive weak light image enhancement method based on a double-channel normalized flow, and specific steps are as follows: step 1, converting a weak light RGB image to a YUV color space to obtain a luminance channel image Y and color channel images U and V; step 2, constructing an overall network, inputting the luminance channel image Y and the color channel images U and V obtained into the overall network to obtain corrected luminance channel image Y'', color channel image U'' and color channel image V''; and step 3, converting the corrected luminance channel image Y'', the color channel image U'' and the color channel image V'' obtained into an RGB image to obtain an enhanced RGB image. The method improves the enhancement effect on a weak light image.

According to the face image processing method and device, the storage medium and the computer equipment provided by the invention, after the to-be-processed face image is acquired, the face region in the face image is firstly determined, and the key points of the five sense organs are marked, so that a space coordinate basis of the key region is provided for subsequent processing; and then, a brightness channel image is separated from the face region, and the scene category of the face image is judged by quantifying the illumination distribution characteristics of the face region, so that a decision basis is provided for subsequent processing. For example, in a dark scene, five-sense-organ brightness hierarchical correction is performed to maintain skin pore-level textures while brightening; performing dynamic range compression in a strong backlight scene to balance light and shade transitions; limited histogram equalization is performed in a normal illumination scene to prevent over-sharpening or noisy explicit of the image. In addition, noise reduction processing, detail restoration and feature enhancement are sequentially carried out on the image after enhancement processing, and the finally generated image can greatly improve the recognition accuracy and the living body detection passing rate.

A method comprising: receiving an image block unit of a frame, the image block unit comprising samples in color channels comprising at least one chrominance channel and one luminance channel (1200); reconstructing samples of said luminance channels of the image block unit (1202); determining a reference area for predicting target samples of at least one color channel of the image block unit, wherein said reference area comprises one or more of reference samples in a neighboring block in current color channel / frame, in the neighboring of a co-located block in reference color channel / frame; and / or inside the co-located block in reference color channel / frame (1204); determining at least one fixed value to be subtracted from sample values of samples in said reference area prior to determining parameters of a cross-component prediction model (1206); predicting said target samples of at least one color channel of the image block unit using the determined parameters of the cross-component prediction model (1208); and adding said at least one fixed value to values of the predicted target samples of at least one color channel of the image block (1210).

A method comprising: receiving one or more image block units of a picture, the image block units comprising samples in color channels comprising at least one chrominance channel and one luminance channel; reconstructing samples of said colors channels to produce reconstructed chrominance samples and reconstructed luminance samples; deriving an indication that picture-level cross-component model inheritance is used for adaptive in-loop filter chrominance update for the current picture; determining a reference picture from a set of candidate reference pictures; and applying, for said one or more image block units of the picture, the adaptive in-loop filter chrominance update parameters as used in co-located image block units of the reference picture.

A method comprising: receiving an image block unit of a frame, the image block unit comprising samples in color channels comprising at least one chrominance channel and one luminance channel; reconstructing samples of said colors channels to produce reconstructed chrominance samples and reconstructed luminance samples; determining a list of cross-component models; determining an index in the list of cross-component models; deriving a cross-component model from the list with the given index; applying a first adaptive in-loop filter for the reconstructed luminance samples; applying the derived cross-component model for the reconstructed luminance samples to obtain an additional input for reconstruction of samples of at least one chrominance channel.

In accordance with various embodiments, an electronic device for colorizing a black and white image using a Generative Adversarial Network (GAN)-based model comprising a transformer block includes a processor, wherein the processor is set to: obtain a black and white image including only first information about a luminance channel; and generate a pseudo color image including only second information about a chrominance channel by applying the black and white image to the GAN-based model, the GAN-based model includes a generator network including a plurality of transformer blocks for color conversion, a plurality of convolution layers, and a plurality of transpose convolution layers, the plurality of transformer blocks each include a Depth Wise Convolution (DWC) layer, a first Layer Normalization (LN) layer, a Window-based Multi-head Self Attention (W-MSA) layer, a second LN layer, and a Colorization Feed Forward (CFF) block. Other various embodiments are possible.

The invention relates to the field of electric data processing, in particular to a data set distillation-oriented hidden backdoor attack method and device. The method comprises the following steps: acquiring an original clean training image sample S and a corresponding real label L, generating an implicit trigger t based on Gaussian distribution, and constructing a binary mask m; based on the binary mask m, the generated implicit trigger t is embedded into a brightness channel of a YCbCr color space of the original clean training image sample S in a linear superposition mode, and a poisoning sample Spoisoned is obtained; keeping the label of the poisoning sample Spoisoned consistent with the real label L of the original clean training image sample S; mixing the poisoning sample with the original clean training image sample to form a poisoning training data set Dpoison, and using the poisoning training data set Dpoison for data set distillation to obtain a synthetic data set Ssynth; according to the scheme, the filtering effect of data set distillation can be resisted, and high hiding is kept before and after distillation.

Methods and apparatus for image compression / decompression using tensor product B-spline (TPB) representations. According to an example embodiment, an image compression method includes generating a plurality of TPB models representing an image, the plurality of TPB models including a TPB model for approximating a spatial remodeling function and a plurality of block-by-block TPB models for estimating an image signal. In some examples, the plurality of tile-by-tile TPB models includes a plurality of luma channel TPB models and a plurality of chroma channel TPB models. The spatial remodeling function is configured to transform a non-uniform local content complexity distribution in the image towards a more uniform transition. The method also includes generating a metadata stream carrying metadata representing a set of coefficients for the various TPB models. At least a portion of the metadata is generated by quantizing corresponding coefficients to a smaller number of bits and applying arithmetic coding to the quantized coefficients.

A method comprising: receiving (1500) an image block unit of a frame, the image block unit comprising samples in color channels, wherein the color channels comprise at least one chrominance channel and one luminance channel; reconstructing (1502) samples of said luminance channels of the image block unit; determining (1504) a reference area for predicting target samples of at least one color channel of the image block unit, wherein said reference area comprises one or more of reference samples in a current or a co-located block in a current color channel / frame or in a reference color channel / frame encoded using an intra block copy (IBC) method; determining (1506) a block vector indicating a spatial distance of an area of target samples to the reference area; and predicting (1508) said target samples of at least one color channel of the image block unit using the cross-component prediction model based on the reference samples in said reference area indicated by said block vector.

Grain pattern quality assessment (GraPQA) is performed. Mean filtering is performed on a luminance channel of an input frame to generate a mean frame. The mean frame is subtracted from the input frame to create a mean-subtracted frame. Local similarity correlation measurements are performed between the mean-subtracted frame and a film grain template. Results of the local similarity correlation measurements are scored to generate a grain pattern quality score for the input frame.

The present embodiment provides a method for compressing an additional channel other than a YUV channel. In the present embodiment, an image decoding device acquires a bitstream including a luma channel and a chroma channel of an image. The image decoding device reconstructs the luma channel and the chroma channel from the bitstream. The image decoding device identifies whether an additional channel is included in the bitstream. When the additional channel is included in the bitstream, the image decoding device reconstructs the additional channel from the bitstream.

The invention discloses an infrared multi-mode composite imaging system based on an APD detector, and the system achieves the quick conversion of three modes through a switchable optical assembly: in a passive imaging mode, the detector receives a thermal radiation signal emitted by a target; in the active gating mode, a laser is utilized to irradiate a target, and set target depth-of-field imaging is realized by controlling a time window of a detector; in the active 3D imaging mode, a time flight method is used, and distance information of a target is obtained by emitting laser and receiving reflection echoes of the laser. Meanwhile, a double-layer fusion framework based on adaptive weight is designed, spatial distance information in an active 3D imaging mode is coded to a chrominance channel in a YCbCr color space, heat radiation information and object contour details in a passive infrared mode are coded to a brightness channel, and an image fusing two-dimensional heat information and three-dimensional space information is output.

This invention discloses a real-time video clarity restoration system based on depth artifact recognition, belonging to the field of computer vision technology. Specifically, it includes: a decoding extraction module, a feature extraction module, a mask generation module, a dynamic allocation module, and an image reconstruction module. The system decodes the original video stream, extracting the luminance and chrominance channel data of each video frame. By comparing the transform coefficient information obtained from the decoding side with cross-frame chrominance data, a dual-channel fused chrominance residual feature map is calculated, constructing a multi-channel input feature tensor. Based on a lightweight shallow convolutional neural network, a pixel-wise artifact probability mask is output through cross-channel feature fusion and nonlinear mapping. The video frame is divided into high-probability artifact regions and low-probability smooth regions, and these regions are processed separately. Using spatial fusion weights, the restored region features are weighted and linearly combined with the original video frame data, and a high-definition video frame is output after processing.

The invention relates to the technical field of image enhancement, in particular to a film and television production system based on ai intelligence and audio-video simulation restoration technology, which comprises a pixel sequence extraction module, an illumination path generation module, a dynamic filling and sorting module, a structure track integration module and a direction restoration calculation module. According to the method, the brightness channel value of the target area in the continuous frames is extracted, the inter-frame gradient map is constructed, the brightness change trend is accurately described, the path set with direction coherence is established by combining the angle difference comparison between the edge gray level direction and the adjacent frame brightness direction, the recovery accuracy of the shielded area is improved, and the method has the advantages of being simple in structure and convenient to operate. Establishing a scoring mechanism according to the brightness amplitude and the change rate, optimizing a pixel filling sequence, avoiding brightness information dislocation, screening and combining the difference value of the included angle between the brightness trend and the direction of a grid area, enhancing the structural continuity and the naturalness of brightness transition, and reconstructing a brightness change sequence based on track guidance. And the restoration effect of the shielding area is more realistic and has structural harmony.

A method, apparatus and program for encoding an image unit that includes image data represented by a luminance channel and a chrominance channel are provided. The method includes obtaining a luma coding tree by dividing a luminance unit representing a luminance channel of an image unit, and obtaining a chrominance tree by dividing a chrominance unit representing at least one chrominance channel of the image unit, wherein obtaining the chroma coding tree includes determining whether the chroma coding tree and the luma coding tree are identical, and signaling information data indicating whether the chroma coding tree and the luma coding tree are identical.

A method for detecting color moiré in an image, including: obtaining image data corresponding to an input image, wherein the image data comprises chrominance channel data and luminance channel data; applying a frequency transform to the image data to obtain transformed image data; based on the transformed image data, selecting at least one lowest frequency component in the chrominance channel data, and at least one lowest frequency component in the luminance channel data; determining a first magnitude corresponding to the at least one lowest frequency component in the chrominance channel data, and a second magnitude corresponding to the at least one lowest frequency component in the luminance channel data; determining a moiré grade by calculating a ratio of the first magnitude and the second magnitude; and detecting a color moiré artifact in the input image based on the moiré grade

The present principles relate to a method for encoding a picture unit comprising image data represented by a luminance channel and at least one chrominance channel, the method comprising obtaining a luminance coding tree by splitting luminance units representative of the luminance channel of the picture unit, and obtaining a chrominance coding tree by splitting chrominance units representative of the at least one chrominance channel of the picture unit. The method is characterized in that, when a size of a sub-unit of the chrominance coding tree at a given level of decomposition is greater than a maximum size, information data indicative that the sub-unit of the chrominance coding tree at the given level of decomposition is not split is signaled when a sub-unit of the luminance coding tree at the given level of decomposition co-located with the sub-unit of the chrominance coding tree is split.

The present application belongs to the field of computer vision and image recognition technology, and relates to a ship navigation obstacle visual detection method and system. The method comprises: converting the initial image of the water area in front of the ship to the LAB color space to separate the brightness and chrominance channels; performing CLAHE processing on the brightness channel, calculating the absolute difference value feature, and combining the pixel value to extract the local brightness distortion degree; extracting the color Euclidean distance and the local brightness distortion degree for fusion to obtain the scene chrominance response feature; based on the theoretical maximum normalization constant, combining the local brightness distortion degree to generate a dynamic gain compensation term to construct a color shift compensation coefficient; and using the compensation coefficient to compensate the chrominance channel, and converting the enhanced brightness image back to RGB to generate a global enhanced image. The present application can effectively separate the brightness and chrominance to avoid mutual influence, scientifically analyze the color protection demand, effectively correct the color shift to maintain the original characteristics, and improve the accuracy and safety of ship navigation obstacle visual detection.