9 results about "Histogram matching" patented technology

The application discloses a backdoor attack method based on color frequency injection and adaptive local enhancement, and relates to the technical field of machine learning and artificial intelligence security. The method comprises the following steps: introducing low-frequency color offset and weak high-frequency signal into an image in a CIELAB color space to perform global color-frequency injection; using a pre-trained proxy model to locate a high-sensitive perception domain of the model through mixed evaluation of gradients and class activation maps, and generating a binary mask; in an HSV color space, respectively applying nonlinear stretching factors to saturation and brightness of the sensitive domain based on the mask to perform adaptive local enhancement; using Gaussian smoothing, adaptive noise and histogram matching to eliminate edges and statistical abnormalities caused by local enhancement, completing compensation color enhancement to generate a poisoned image; and modeling a trigger core parameter as a constrained optimization problem, and using a particle swarm optimization algorithm to jointly dynamically update the trigger core parameter to obtain an optimal strategy. The application anchors the trigger feature depth in the core semantic area of the model and lurks in the normal data manifold, guarantees a high attack success rate, realizes extreme visual and feature concealment, and has strong anti-defense robustness.

The application provides a style transfer strong similarity-based generation method, device, equipment and medium, the method comprising: S10, redrawing a style reference map, outputting a clear style map; S20, inputting the clear style map into a monocular depth estimation model, outputting a single-channel depth map; S30, inputting the single-channel depth map into an enhanced image generation model for structure optimization, generating a redrawing sketch; S40, using a visual feature extraction model and a deep learning model to perform style fusion and rendering on the redrawing sketch, generating a preliminary style map; S50, pre-training a LoRA model, using the LoRA model to adjust the preliminary style map, outputting an intermediate style map; S60, after upsampling the intermediate style map, performing block optimization, outputting an optimized style map; S70, inputting the optimized style map into a Lab color space, performing histogram matching, and generating a final style map.

The application discloses a kind of micro-light image enhancement methods, including obtaining target micro-light image;Based on gamma correction, RTV correction and histogram matching scheme, the structure diagram and texture diagram of target micro-light image are calculated;According to the structure diagram and texture diagram obtained, based on Retinex model and structure / texture guide scheme, the brightness diagram and reflection diagram of target micro-light image are calculated;The obtained brightness diagram is adjusted and adaptively corrected;Based on RTV correction scheme, the enhanced image of target micro-light image is calculated to complete the image enhancement of target micro-light image.The application also discloses a kind of mine image enhancement method comprising the micro-light image enhancement method.The application not only realizes the enhancement of micro-light image and mine image, but also has higher reliability, better accuracy and better enhancement effect.

The application discloses a high-resolution satellite image urban area shadow-removed ARD production method and device, and belongs to the technical field of remote sensing image processing. The method comprises the following steps: firstly, screening out images covering urban areas; performing radiation calibration on high-resolution satellite images covering urban areas to obtain apparent radiance images; based on the apparent radiance images, performing preliminary shadow detection by using a pre-trained deep learning model; using a near-infrared band of an atmospheric-corrected ground reflectivity image, performing false detection elimination on the preliminary detection result by adaptive threshold segmentation to obtain a final shadow mask; performing histogram matching processing on the shadow area based on the shadow mask on the atmospheric-corrected ground reflectivity image to realize shadow removal; and finally, outputting the shadow-removed ARD product. The application significantly improves the shadow detection precision and the quantitative reliability of the ARD product, and is suitable for large-scale ARD production of high-resolution satellite images in urban areas.

This application provides an anti-interference texture enhancement localization method, system, and medium suitable for low-texture visual scenes. The method includes: acquiring an original image; preprocessing the original image; extracting the texture response of the preprocessed image in different directions and frequency dimensions based on multi-scale Gabor filtering to obtain multiple texture response maps; dividing the preprocessed image into multiple image partitions based on a partitioned LED array and calculating the local gradient contrast of each image partition; independently adjusting the light source brightness of different image partitions to obtain an illumination-optimized image; performing feature fusion processing on the multiple texture response maps and the illumination-optimized image to extract feature points for visual localization; improving the consistency of images acquired at different time periods by normalizing the frequency response of the original image, histogram matching, and adaptive brightness restoration; and improving the local contrast by using a partitioned LED array with spatial illumination modulation to improve visual localization accuracy.

This invention discloses an adaptive enhancement method for low-light images based on physical prior guidance and spatiotemporal decoupling, belonging to the fields of computer vision and autonomous driving perception technology. The method first converts the original low-light image to YUV space to extract the brightness channel and performs inverse mapping. A pseudo-dehazing physical model is used to inversely solve for the transmittance map as the structural prior matrix. Subsequently, a mask decomposition network decouples the original image features into a reflection component containing local texture and an initial illumination component containing global brightness distribution. This invention constructs a dual-branch parallel enhancement architecture: the first branch uses an enhanced Transformer network for detail restoration and introduces a color histogram matching loss function to ensure color fidelity; the second branch uses an adaptive Gamma U-Net to predict pixel-level gamma parameter matrices for brightness compensation and suppresses overexposure through a regularized loss function with a range penalty term. Finally, the enhanced image is reconstructed based on Retinex theory.

Systems and methods for mitigating shadow segments from images are provided. One example computer-implemented method includes accessing an original image of a geospatial location including a first shadow segment and generating, using a model architecture, a matte for the original image. The method also includes generating a first histogram of tones of shadow pixels of the first shadow segment in the original image, generating a second histogram of tones of an adjacent region of the original image, which is proximate to the first shadow segment yet outside a boundary of the first shadow segment, defining a lookup table based on histogram matching between the first histogram and the second histogram, and relighting the original image based on the lookup table.

The present invention relates to a method for generating diagnostic support information for axial spondyloarthritis. The method includes preprocessing an input MRI image through normalization and histogram matching. A first slice feature representing visual characteristics of the MRI image is extracted for each slice of the preprocessed MRI image by applying a first feature extraction model, and a second slice feature representing quantitative characteristics of bone marrow edema (BME) is extracted by applying a second feature extraction model to BME data associated with the MRI image. Slice-level integrated feature vectors are generated by combining the first and second slice features on a slice-by-slice basis and applying attention-based importance weights, and a patient-level final integrated feature vector is obtained by summing the weighted vectors. Diagnostic support information indicating whether axial spondyloarthritis is present is then generated by inputting the final integrated feature vector into a classification model.

The application provides an infrared image enhancement method and device based on histogram matching and curvelet transform. The method comprises: acquiring an infrared image to be enhanced and a reference image; calculating the gray mean value and the gray standard deviation of the infrared image and the reference image respectively; calculating a correction coefficient and an average correction amount based on the gray mean value and the gray standard deviation; generating a histogram matching enhanced image of the infrared image based on the correction coefficient and the average correction amount; respectively performing curvelet transform decomposition on the histogram matching enhanced image and the infrared image to obtain corresponding multi-scale and multi-direction sub-band coefficients, and fusing corresponding sub-band coefficients at the same scale and the same direction to obtain fused sub-band coefficients; and performing curvelet inverse transform on the fused sub-band coefficients to obtain a fused enhanced image. Through the cooperation of the global gray correction of histogram matching and the local detail fusion of curvelet transform, the application realizes the synchronous improvement of the contrast, the definition and the detail information of the infrared image.