49 results about "YCbCr" patented technology

Disclosed in the present invention is a soft tissue photoacoustic / ultrasonic multi-modal image fusion method based on deep learning. The method comprises the following steps: an ultrasonic-photoacoustic imaging device collecting a human body soft tissue photoacoustic image and ultrasonic image, and performing size normalization processing; inputting the images into a spatial conversion module to convert same into a YCbCr space; inputting the images into a pre-convolutional module to change the number of data channels; inputting the images into a multi-scale feature extraction module to extract salient features of the source images; inputting the features into a filter prediction module to obtain a multi-scale filter; and inputting the filter into a filtering fusion and adaptive enhancement module and combining same with the input source images, so as to obtain a final fusion result. Compared with several traditional fusion methods and deep-learning-based fusion methods, the method provided in the present invention has a greater fusion effect, and more importantly, has an excellent real-time performance. Moreover, multiple modes of photoacoustic / ultrasonic fusion extension experiments are performed on a photoacoustic / ultrasonic multi-modal imaging system, verifying the effectiveness of the method in the present invention.

The invention discloses a low-illumination image enhancement method based on a YCbCr space and a Fourier frequency domain, and the method comprises the steps: extracting a brightness component of a low-illumination image in the YCbCr space, and constructing a training set together with a normal-illumination image and the low-illumination image; constructing a low-illumination image enhancement network model, and inputting the training set into the model for training; constructing a loss function between the amplitude enhancement network branch and the normal illumination image as well as between the phase enhancement network branch and the normal illumination image, and adjusting model parameters by minimizing the loss function to obtain an optimization model; and inputting a to-be-enhanced low-illumination image into the optimization model for image enhancement. According to the method, the YCbCr brightness component and the amplitude information of the Fourier frequency domain are combined, and the Transform is utilized to enhance the phase information, so that the visual quality of the low-illumination image is remarkably improved, the visibility and definition of the image are improved, and the method has wide application prospects in tasks of image enhancement, denoising, super-resolution recovery and the like.

The invention discloses a deep learning-based multimodal image fusion method for soft tissue photoacoustic / ultrasound imaging. Steps: an ultrasound-photoacoustic imaging device acquires photoacoustic and ultrasound images of human soft tissue and performs size normalization processing; an input spatial transformation module converts the images to the YCbCr space; an input pre-convolution module modifies the number of data channels; an input multi-scale feature extraction module extracts salient features from the source images; an input filter prediction module derives multi-scale filters; and an input filter fusion and adaptive enhancement module combines the input source images to obtain the final fused result. The invention has superior fusion performance compared to several traditional fusion methods and deep learning-based fusion methods, and more importantly, it exhibits excellent real-time performance. Furthermore, various modes of photoacoustic / ultrasound fusion extension experiments have verified the effectiveness of the method proposed in the invention.

The invention provides a multi-source image fusion method based on a three-discriminator generative adversarial network, and the method comprises the steps: carrying out the color space conversion of a visible light RGB image, obtaining YCbCr, and cascading a Y-channel infrared image with a single-channel infrared image to form a dual-channel combined image; inputting the combined image into a generator to obtain a single-channel fusion brightness image with the same spatial size as the input image; taking the fused brightness image as a Y channel, and converting the Y channel and a CbCr channel to obtain a fused color image in an RGB format; the generator is trained based on three discriminators before image fusion, the first discriminator discriminates the authenticity of the fusion color image and the visible light color image, the second discriminator discriminates the authenticity of the fusion brightness image and the infrared image, and the third discriminator discriminates the authenticity of the fusion brightness image and the Y channel; the problem that visible light is insufficient in information expression when illumination is poor can be solved, and the challenges that the fused image is insufficient in definition and not high in correlation with the source image are solved.

The present invention relates to a semantically aware visible light and infrared image fusion method, comprising the following steps: acquiring a paired visible light image and infrared image; converting the infrared image into a single-channel grayscale image; converting the visible light image into a YCbCr format and using only the Y channel to obtain a Y-channel image; and inputting the grayscale image and the Y-channel image into a fusion network model to obtain a single-channel fused image. The present invention can effectively aggregate local and global information, giving the fusion network semantic awareness capabilities.

The application provides a target recognition method based on a morphological recognition template matching, comprising the following steps: S1, acquiring an original image; S2, converting the original image from an RGB format to a YCBCR format, and performing a binaryzation processing on the original image in the YCBCR format to obtain a binaryzation image, and sequentially screening out pixel points greater than a first threshold value corresponding to YCBCR of various colors from the binaryzation image; S3, judging whether the distance between two pixel points is greater than a second threshold value, if yes, the two pixel points correspond to different targets, if not, the two pixel points are the same target, and a new second threshold value is generated; and S4, matching the binaryzation image with binaryzation template images of various targets, so as to determine the types of various targets existing in the binaryzation image. The application integrates the color, quantity and type of the target into one, and has small resource usage, and is suitable for simple use scenarios.

In a method to improve backwards compatibility when decoding high-dynamic range images coded in a wide color gamut (WCG) space which may not be compatible with legacy color spaces, hue and / or saturation values of images in an image database are computed for both a legacy color space (say, YCbCr-gamma) and a preferred WCG color space (say, IPT-PQ). Based on a cost function, a reshaped color space is computed so that the distance between the hue values in the legacy color space and rotated hue values in the preferred color space is minimized. HDR images are coded in the reshaped color space. Legacy devices can still decode standard dynamic range images assuming they are coded in the legacy color space, while updated devices can use color reshaping information to decode HDR images in the preferred color space at full dynamic range.

To provide a "composite image generation system and rear image display system" for performing natural composition of a YCbCr image using a small amount of processing.SOLUTION: From first / second images of a YCbCr system, portions of overlapped imaging areas are extracted as first / second comparison images. A Y gain calculation section 4114 calculates a ratio of representative values of Y signals of the first comparison image and the second comparison image, as a correction gain d. An RGB gain calculation section 4118 calculates a ratio of representative values of R / G / B signals of the first comparison image and the second comparison image converted in an RGB system, as a correction gain a / b / c. A CbCr correction section 4119 corrects Cb, Cr signals of the second image so that gain correction of R, G, B components using correction gains a, b, c is reflected. A Y correction section 4120 corrects a Y signal of the second image using the correction gain d. A composition section 4121 composes the first image and the corrected second image.SELECTED DRAWING: Figure 3

The application provides an image processing method, which comprises the following steps: removing the object shadow area in an RGB image; calculating the pixel value of an (i, j) position I ij in a YCbCr image, and then respectively calculating the average pixel values of the object shadow area and the non-object shadow area in the YCbCr image; adding the average pixel value of the object shadow area and the average pixel value of the non-object shadow area in the obtained YCbCr image to the pixel value of the Y channel image, so as to obtain the ratio r of the average object shadow pixel and the average non-object shadow pixel; then, according to the obtained r value and I ij , a new image pixel value of the non-object shadow area is calculated again, and the YCbCr image is converted into an RGB image according to the new image pixel value of the non-object shadow area, so as to obtain the RGB image of the non-object shadow area; in this way, only the liquid leakage area in the RGB image is reserved, and the accuracy of liquid leakage detection based on the YOLOv5 target detection algorithm is ensured.

The present invention discloses a lipstick recognition method for ID photos based on a convolutional neural network, comprising: obtaining an image training set, preprocessing the image training set to obtain an RGB space image of the lip area; converting the RGB space image of the lip area into a YCbCr space image, and forming a training sample pair with the RGB space image and the YCbCr space image; constructing a convolutional neural network, using the training sample pair to train the convolutional neural network to obtain a lipstick recognition model; obtaining an image to be recognized, preprocessing it, and performing lipstick recognition on the preprocessed image to be recognized by the trained lipstick recognition model to obtain the category probability corresponding to the image to be recognized, and selecting the category label with the largest probability as the lipstick recognition result of the image to be recognized. The present invention solves the problem that the prior art cannot effectively and stably recognize lipstick in ID photos when the light changes, the environment is complex, and the lips have partial lesions.

The invention discloses a document image watermark adding and tampering detection method based on Chebyshev and Arnold. The watermark adding method comprises the following steps: converting a digital paper file into an image file; performing Arnold transformation on the image to obtain a scrambled image xi; converting the image xi into a Ycbcr color space, and extracting a Y channel; two-dimensional Chebyshev transformation is carried out on the Y channel; keeping coefficients greater than a set threshold value mu, and setting the rest coefficients to be zero; performing Chebyshev inverse transformation on the processed Y channel, replacing the processed Y channel into a Y channel in a Ycbcr space, converting the Y channel back to an image, and performing Arnold inverse transformation; and performing Chebyshev inverse transformation on the part of which the coefficient is smaller than a set threshold value mu, and forming encrypted global summary information by extracting noise level features. According to the method, the image storage overhead is hardly increased after the watermark is embedded, and the storage smaller than the original file in size can be obtained under partial conditions, so that the storage and transmission cost is effectively reduced.

This invention discloses a non-contact heart rate measurement method, system, device, and storage medium, applicable to the field of heart rate monitoring technology. The invention extracts RGB and YCbCr spatial sample data from video data within a dataset, thereby obtaining the overall RGB and YCbCr spatial feature maps. Based on these maps, corresponding rPPG feature information is extracted, and the target rPPG feature information is obtained. This leverages the characteristics of RGB space to ensure temporal and spatial information extraction redundancy, reducing interference from significant redundancy in video images. Simultaneously, the characteristics of YCbCr space effectively suppress noise, thus improving the accuracy of non-contact heart rate measurement and enhancing the overall accuracy of the results.

Using a standard-based RGB to YCbCr color transform, a new RGB to YCC 3×3 transformation matrix and a 3×1 offset vector are derived under a set of coding-efficiency constraints. The new RGB to YCC 3×3 transform comprises a luminance scaling factor and a 2×2 chroma sub-matrix that preserves the energy of the standard-based RGB to YCbCr transform while maintaining or improving coding efficiency. It also adds support for an authorization or watermarking mechanism in streaming video applications. Examples of using the new color transform using image reshaping are also provided.

The application provides an image fusion method and system based on a cascade attention mechanism and a neural network, and the method comprises the following steps: converting a color visible light image located in an RGB space into a YCbCr space; extracting features of the color image and an infrared image respectively and calculating attention maps of the color image and the infrared image; constructing a color fusion result through a fusion module; and converting the YCbCr space into the RGB space, so that the fused image is displayed in the RGB space. The application solves the technical problems of excessive dependence on artificial design, poor applicability and decreased visual effect.

The invention discloses a reflection removal method, device and equipment for an ultra-high-definition image, a medium and a product, and relates to the technical field of image processing, and the method comprises the steps: converting an input ultra-high-definition image in an RGB format into a Lab color space, a YCbCr color space and an HLS color space; carrying out cross validation on an initial skin area determined based on the YCbCr color space and a YCbCr initial correction result and an HLS color space to obtain a target skin color area, a YCbCr target correction result and an HLS correction result; correcting the ultra-high-definition image and the green reflection pollution points determined in the Lab color space to obtain a Lab correction result; and combining the first correction image, the second correction image and the third correction image which are converted from the Lab correction result, the YCbCr target correction result and the HLS correction result to obtain a reflection-removed image, thereby improving the reflection removal effect of the ultra-high-definition image.

This invention relates to the field of high-performance computing in deep learning computer vision, specifically to a CPU-based fast and accurate JPEG image decoding method. It includes the following steps: S1, loading JPEG image data using AVX2 instructions and decoding the data, including inverse quantization and color space conversion; S2, performing parallel computation on inverse quantization and inverse Fourier transform using the AVX2 instruction set; S3, converting the decoded YCbCr data to RGB format, performing parallel computation using the AVX2 instruction set, and quickly completing the color space conversion using a conversion formula; S4, outputting and storing the converted RGB data in CHW format for subsequent face recognition processing.

The invention provides a deep counterfeiting identification method and device and electronic equipment, and relates to the technical field of image processing. The method comprises the following steps: acquiring video data to be recognized, and performing face screenshot on the video data to obtain a target face image; the target face image is converted to a YCbCr color space, and YCbCr features are obtained; fusing the RGB feature and the YCbCr feature of the target face image to obtain a fused feature; and inputting the fused features into a counterfeit identification model, extracting local features and global features by the counterfeit identification model, and obtaining an identification result output by the counterfeit identification model according to the local features and the global features. According to the scheme, the original image is converted into the YCbCr color space, thereby facilitating the amplification of a counterfeit clue, fusing the RGB color features with the YCbCr color features, and improving the detection precision. Meanwhile, in consideration of artifacts generated after the video is subjected to high compression, global features are concerned while local features are considered, and the recognition precision of the network is improved.

The application discloses a video stream compression and decompression method and system based on OpenMP thread nesting, adopts parallel pipeline to process video frame data, simplifies original JPEG coding, compresses RGB data into YCbCr data for transmission, adopts OpenMP thread nesting to process the compression and decompression of the video frame data in a multithreading mode under the condition that the outer thread processes the video frame data by using the parallel pipeline, effectively improves the support resolution and fluency of remote playing video, saves the engineering cost of client computing, and improves user experience.

The application belongs to the technical field of medical image fusion, and discloses a network model and method for glioma SPECT-MRI image fusion. The network model is referred to as DEFSD, which promotes image fusion by decomposing exclusive features and saliency masks. Specifically, first, the source SPECT image in the RGB space is converted into the YCbCr space, then the SPECT image and the MRI image in the Y channel are input into the DEFSD, the DEFSD combines the attribute vector and the object feature map, respectively reconstructs the two source images, and determines the exclusive features of the source images, meanwhile, the features of the highlighted regions are utilized by using the saliency mask; then the image output by the trained DEFSD is converted into the RGB space together with the SPECT images in the Cb and Cr channels, and finally, the output fusion image is obtained. The training is carried out on the medical image data set disclosed by Harvard Medical School, and the experimental results show that the DEFSD can produce a fusion image containing a large amount of information unique to each modality, and has obvious groove features in the lesion area, which is beneficial to early diagnosis of glioma.

This application discloses a method, apparatus, device, medium, and product for removing reflections from ultra-high-definition images, relating to the field of image processing technology. The method includes converting an input ultra-high-definition image in RGB format into Lab color space, YCbCr color space, and HLS color space; cross-validating an initial skin region determined based on the YCbCr color space and the initial YCbCr correction result with the HLS color space to obtain a target skin region, a YCbCr target correction result, and an HLS correction result; correcting green reflective pollution points determined by the ultra-high-definition image and the Lab color space to obtain a Lab correction result; and merging a first corrected image, a second corrected image, and a third corrected image converted from the Lab correction result, the YCbCr target correction result, and the HLS correction result to obtain a reflection-removed image. This application improves the reflection removal effect of ultra-high-definition images.

The application discloses an underwater image enhancement method and device based on adaptive color-brightness embedding and content perception. The method first converts the input image to YCbCr space for feature decoupling using a color-brightness embedding learning module, and extracts the brightness prior feature and the color prior feature respectively; then the original image features are input into the content perception backbone network composed of a shallow detail branch and a deep content branch, and the local texture and global contrast of the image are recovered through dynamic filtering and Fourier domain modulation; finally, through an explicit multi-prior fusion module, the learned physical prior is injected into the enhanced features for collaborative refinement, and the color deviation is corrected and a clear image is reconstructed. The PSNR and SSIM indicators of the application on multiple data sets are better than those of the existing advanced algorithms, which can effectively solve the color deviation, low contrast and detail blur problems of underwater images, and have very high fidelity and robustness.

The present invention discloses a video dynamic frame extraction method for experimental operation specification evaluation, which extracts key frames of different experimental videos and extracts a binary image containing only the hand through a YCbCr Gaussian skin color algorithm; constructs a single-input and single-output neural network for training; in the first stage, learns the color and edge information of images without a specific environment through an open-source image classification training set, then replaces the class prediction layer with a 512-dimensional fully connected layer as the feature output layer and concatenates a hand feature restoration module and a feature similarity classification module, and restores the hand area of the experimental picture to assist in enhancing the algorithm's attention to the hand part and reducing the influence of other light or irrelevant object changes. The beneficial effects of the present invention: Based on a deep neural network to judge the similarity of video frames, when processing experimental operation specification evaluation videos, operation videos containing key interactions do not skip frames, and video frames of irrelevant operations are directly skipped, intelligently fast-forwarding to compress the video duration.

The invention discloses a weak light image enhancement method based on YCbCr brightness guidance, and the method specifically comprises the steps: converting a normal light image and a weak light image from an RGB color space to a YCbCr color space, obtaining a brightness component, a blue component and a red component, inputting all the brightness components into a brightness component diffusion enhancement branch, obtaining an enhanced component, enabling the enhanced brightness component to be subjected to the YCbCr brightness guidance, and enabling the enhanced brightness component to be subjected to the YCbCr brightness guidance to be subjected to the YCbCr brightness guidance. The blue component, the red component and the enhanced component of the weak light image are spliced and then input into a chrominance component recovery branch to obtain an enhanced blue component and an enhanced red component, the enhanced brightness component, the enhanced blue component and the enhanced red component are converted into an RGB color space to obtain an enhanced image, and loss constraint is carried out to obtain an enhanced image; and a final enhanced image is obtained. According to the method, the problems of poor color and brightness recovery effect and unclear enhancement result texture of the existing method are solved.

The invention provides a frequency domain visual processing method, system and device based on RAW images and a medium. The method comprises the following steps: acquiring Bayer array RAW image data; according to the pixel arrangement mode of the Bayer array RAW image data, channel rearrangement processing is carried out on the RAW image data, and an RGB image is generated; segmenting the RGB image into a plurality of non-overlapped RGB image blocks; for each RGB image block, based on a preset frequency domain coefficient set, performing frequency domain transformation processing on the RGB image block to obtain a compressed RGB frequency domain feature of the RGB image block; wherein the frequency domain coefficient set is used for indicating frequency domain coordinates needing to be generated in the frequency domain transformation result; performing frequency domain color space transformation processing on the compressed RGB domain frequency domain features to generate YCbCr domain frequency domain features; performing channel splicing on the YCbCr domain frequency domain features of the RGB image blocks to form frequency domain features; and inputting the frequency domain features into a visual task processing model to generate a corresponding visual task result. According to the method, the image processing rate is improved while the task precision is ensured.

The invention discloses a single-frame video non-blind watermark embedding and detecting method based on DWT-SVD (Discrete Wavelet Transform-Singular Value Decomposition). The watermark embedding method comprises the following steps: S1, converting an original video frame into a YCbCr color format, and performing secondary discrete wavelet decomposition on a Y component to obtain a low-frequency component LL; s2, dividing the LL into a plurality of isometric matrixes LLi, performing singular value decomposition on each matrix LLi, and arranging singular values in a descending order to obtain a singular value diagonal matrix S; s3, modifying S to obtain S * according to watermark information to be embedded, performing inverse SVD decomposition to obtain LLi *, and merging to obtain LLi *; and S4, replacing the original low-frequency component LL with the watermark-embedded low-frequency component LL *, performing secondary discrete wavelet inverse transformation to obtain Y *, replacing the original Y component, converting into an original color format, and outputting the watermark-embedded video frame. According to the method, the defects of poor watermark robustness and concealment of the existing single-frame video are overcome, and the detection accuracy is further improved.

The invention relates to a low-complexity video data compression method and device, and the method comprises the steps: determining to-be-transmitted video data in a YcbCr format or a YCoCg-R format, or converting to-be-transmitted video data in an RGB format into the YcbCr format or the YCoCg-R format; each row of pixels of the to-be-transmitted video data are segmented into a plurality of data sets, each data set comprises N pixels, and each data set is composed of head coded data with a preset data length and pixel coded data comprising N pixels; and carrying out compression processing on the pixel coding data in the data group through a Delta compression mode or a self-sorting 422 mode to obtain compressed video data so as to transmit the high-resolution compressed video data under a limited bandwidth. On the premise that the video quality is maintained, the transmission bandwidth requirement is remarkably reduced, and an efficient solution is provided for high-resolution video transmission in a 10G-12G link.

A computer-implemented method for increasing the image resolution of a digital image. The method includes performing bicubic upsampling on the digital image to generate a base high-resolution (HR) image. The digital image is converted from a red-green-blue (RGB) color space to a luminance (Y), chrominance blue difference (Cb), and chrominance red difference (Cr) (YCbCr) color space to generate a low-resolution (LR) residual image. Multiple convolutional layers of a neural network model are applied to the LR residual image to convert the LR residual image into multiple HR residual sub-images corresponding to the digital image. An HR image corresponding to the digital image is generated using the base HR image and the multiple HR residual sub-images.

The present invention relates to a method for transmitting five-primary-color image signals based on a standard three-channel approach, comprising the following steps: calculating an encoding matrix for an additional CGB color space to encode the CGB signal into a pseudo-YCbCr signal, and calculating a CGB decoding matrix; calculating an encoding matrix for an additional RGY color space to encode the RGY signal into a pseudo-YCbCr signal; and calculating an RGY decoding matrix. At the transmitting end, the five-primary-color signal is divided according to the color space, with each pixel consisting of three color components (RGB, CGB, or RGY). Standard RGB encoding, CGB encoding, or RGY encoding are used, respectively, to encode the signal into a YCbCr signal for transmission. If the C component value is greater than the R component, the CGB encoding format is used; if the Y component value is greater than the B component, the RGY encoding format is used; otherwise, the RGB encoding format is used. Upon receiving the YCbCr data, the receiving end uses a blind recognition scheme to determine the composition of the three primary colors.

The embodiment of the invention relates to the technical field of audio and video broadcasting, in particular to a video coding transmission method and device and a video transmission system. Judging whether the source format video is a target format video or not, if yes, executing the next step, and if not, decomposing the source format video into a plurality of target format videos through a video decomposition algorithm; and encoding the target format video to generate an IP video stream, and transmitting the IP video stream in an IP transmission mode. According to the method provided by the invention, the YCbCr 4: 4: 4 and YCbCr 4: 2: 2 videos can be converted into multiple paths of YCbCr 4: 2: 0 videos for transmission at the transmitting end, and the multiple paths of YCbCr 4: 2: 0 videos are synthesized into the original format video at the receiving end, so that the ultra-high definition and high fidelity of the source video can be maintained, and the video transmission cost is greatly reduced.

The invention discloses a double-branch defogging method and system based on a visual Mama module, and relates to the technical field of image defogging, and the method comprises the steps: obtaining a to-be-defogged image, converting the to-be-defogged image from an RGB color space to a YCbCr color space, and obtaining a YCbCr image; based on brightness channel information and chrominance channel information in the YCbCr image, respectively inputting the brightness channel information and the chrominance channel information to a brightness enhancement module and a defogging module to correspondingly obtain brightness enhancement features and chrominance enhancement features; inputting the chromaticity enhancement feature and the chromaticity channel information into a supervision attention module to obtain a chromaticity comprehensive feature; the brightness enhancement feature and the chromaticity comprehensive feature are fused and then input to an output module to obtain a defogged YCbCr image; and converting the defogged YCbCr image into a corresponding defogged RGB image, and taking the defogged RGB image as a defogged image. Therefore, accurate defogging of the image is realized, and the image quality recovery effect is improved.