28 results about "Retinex algorithm" patented technology

The invention discloses an autoclaved aerated concrete member surface defect intelligent identification system based on image processing, and particularly relates to the field of defect identification, comprising an image acquisition module, an image preprocessing module, a defect candidate region extraction module, a defect identification and classification module, and a result output and alarm module; according to the method, a high-definition industrial camera is used for collecting a component surface image, and adaptive median filtering and a Retinex algorithm are adopted for image denoising and enhancement, so that the influence of noise and uneven illumination is eliminated; utilizing an improved multi-threshold segmentation and Canny edge detection algorithm to accurately extract a defect candidate region; the method comprises the following steps: extracting three types of feature parameters of shape, texture and gray scale, and inputting the three types of feature parameters into a deep learning model taking ResNet50 as a basic network to realize automatic identification and classification of four types of typical defects of cracks, holes, unfilled corners and surface peeling; and finally, the system divides severity levels according to the defect size, and triggers differentiated visual alarm and linkage control.

The application provides a kind of underwater structure apparent disease identification method and system based on deep learning, wherein, method includes: according to the combination of fusion model and target recognition model, generate the pre-set underwater structure apparent disease identification model;Underwater apparent disease is identified by the pre-set underwater structure apparent disease identification model;The fusion model is built by improved CycleGAN model and multi-scale Retinex algorithm (MSR) network, for converting underwater image into clear and clear image with obvious features;The target recognition model is obtained by YOLOv5 model, for realizing the positioning and classification of underwater structure apparent disease.The present application solves the problems of inaccurate classification and low recognition accuracy of underwater structure apparent disease by the underwater structure apparent disease identification model, caused by factors such as camera imaging blur, insufficient contrast, dispersion and noise in complex water area.

The application discloses a camera calibration method and system under uneven illumination conditions, and belongs to the technical field of image processing, and comprises the following steps: S1, processing an input image by using a multi-scale Retinex algorithm; S2, performing Gaussian homomorphic filtering processing on the image obtained in the step S1; S3, processing the image obtained in the step S2 by using an Otsu algorithm; and S4, performing camera calibration on the image processed in the steps S1-S3 by using Zhang Zhengyou plane calibration method. The application firstly enhances image details by using the multi-scale Retinex algorithm and the Gaussian homomorphic filtering, then obtains a final calibration board image by combining Otsu algorithm image segmentation and bilateral filtering processing, and further realizes high-precision calibration of the camera, and is worth popularization and use.

The invention relates to a metal membrane piece position correction method and system based on improved template matching. The method comprises the steps that an adaptive Retinex algorithm is combined with a DnCNN denoising network to carry out image preprocessing; fusing an ASIFT algorithm and a SuperPoint network to extract feature points and a confidence map; initial matching is realized by using the FREAK descriptor and the weighted Hamming distance, and initial mismatching is filtered based on a bidirectional nearest neighbor criterion; designing a double-layer filtering mechanism in which Guided-PROSAC and local topological structure verification are combined to eliminate mismatching; mapping angular points of the template image to a target image to calculate a pose error vector; the pose error vector is transmitted to a mechanical arm controller for metal diaphragm piece position correction; according to the method, the real-time requirement of a production line is met through reasoning on edge equipment, multiple defects of the traditional technology in the aspects of robustness, precision and automatic integration are overcome, and reliable technical support is provided for a precise assembly task in intelligent manufacturing.

The application discloses a night highway pit and pond recognition method and system based on low-illumination enhancement and parallax calculation, and relates to the technical field of intelligent traffic monitoring and road maintenance. The method comprises the following steps: S1: collecting environmental data, calculating a meteorological index to determine a laser compensation power, and obtaining a stereo image pair to generate environmental metadata; S2: determining an enhancement strategy based on the environmental metadata, and obtaining an enhanced image pair by using an improved Retinex algorithm; S3: performing stereo matching on the enhanced image pair, and generating a scene depth map by fusing pose data; S4: based on a double-branch recognition model, fusing image and depth features, detecting and verifying a pit and pond area, and obtaining a pit and pond area mask; and S5: based on the pit and pond area mask, the depth map and the pose data, calculating three-dimensional parameters and a position of the pit and pond, and generating a detection report. Through adaptive image enhancement and multi-source data fusion technology, the accuracy of pit and pond recognition and the three-dimensional measurement precision in a night low-illumination environment are improved, and automatic and efficient inspection without affecting traffic is realized.

The invention discloses an unmanned aerial vehicle inspection photovoltaic panel defect detection method and system in a railway line scene in the technical field of electrified railway new energy development. The method comprises the following steps: according to a photovoltaic panel image along a railway collected by an unmanned aerial vehicle, performing image preprocessing by using a retinex algorithm of adaptive bilateral filtering to obtain a preprocessed photovoltaic panel image; and according to the pre-processed photovoltaic panel image, photovoltaic panel defect detection is carried out by using a YOLOv8 detection algorithm introducing a CDA-net attention mechanism, and a detection result is obtained. According to the method, the problems of insufficient detection precision, large algorithm model and the like of unmanned aerial vehicle routing inspection are solved, and the reliability and practicability of unmanned aerial vehicle routing inspection in the aspect of photovoltaic panels along the railway can be effectively improved.

The application discloses a low-illumination image enhancement method based on an improved Retinex algorithm, and applies to the technical field of image enhancement, and comprises the following steps: performing discrete wavelet decomposition on a low-illumination image to obtain low-frequency and high-frequency components of the image; converting the low-frequency component into HSV, separately performing brightness correction on a V channel, then converting back to RGB, performing bilateral filtering, and then converting to HSV to extract the V channel; performing image enhancement on the low-frequency component by using an improved Retinex algorithm based on a joint weighting of a bilateral filter and a Gaussian filter as a new center-surround function, and performing median filtering processing, then converting to HSV to extract the V channel; weighting and fusing the two V channels, retaining the H and S channels after algorithm enhancement, then converting back to RGB, performing discrete wavelet fusion with the high-frequency component after denoising, and stretching and outputting the enhanced low-illumination image. The application can effectively guarantee the color, edge details and avoid local distortion of the image.

The present application relates to the technical field of computer vision, and particularly relates to a keyboard and keycap production material defect detection method, which obtains an initial image and a gray image of a keyboard and keycap to be detected; according to the gray difference of pixel points in the gray image, a suspected defect area is obtained in the gray image; for any suspected defect area, according to the color feature of pixel points in the corresponding area in the initial image, and the distribution feature and the texture feature of pixel points in any suspected defect area, a defect coefficient of each pixel point in any suspected defect area is obtained; using the defect coefficient of each pixel point in the gray image, an adaptive small-scale weight and an adaptive large-scale weight of each pixel point are obtained; according to the adaptive small-scale weight and the adaptive large-scale weight of each pixel point, an enhanced image is obtained by using a Retinex algorithm, and the accuracy of keyboard and keycap production material defect detection is improved.

This application provides a method, system, medium, and device for enhancing images of oral endoscopes. The method includes: acquiring the original image of an oral endoscope; performing illumination enhancement processing on the original image of the oral endoscope using a preset multi-scale Retinex algorithm; inputting the enhanced image into a preset U-Net semantic segmentation network for semantic segmentation processing to determine a binarized oral cyst mask image; performing target region extraction processing on the binarized oral cyst mask image to determine the target region image; performing image enhancement processing on the target region image using a preset super-resolution ESRGAN model to determine the enhanced image of the target region; and superimposing the enhanced image of the target region with the enhanced image according to a preset superposition intensity to determine the enhanced oral endoscope image. This application improves the clarity and diagnostic accuracy of oral cyst region recognition under conditions of low illumination, uneven illumination, and complex tissue backgrounds.

The invention discloses a high dynamic range video tone mapping method, device and equipment, and the method comprises the steps: carrying out the display preprocessing of a target high dynamic range video frame image, and obtaining a linear light image; processing the linear light image by using a Retinex algorithm to obtain an illumination image; estimating a reflection map according to the illumination map by using an illumination reflection theory; converting the illumination image to a frequency domain, and performing spectral analysis to obtain a first radial average power spectrum; converting the reflectogram into a frequency domain, and performing spectral analysis to obtain a second radial average power spectrum; determining homomorphic filtering parameters according to the first radial average power spectrum and the second radial average power spectrum; processing the linear light image by using an illumination reflection model, and converting an obtained processed time domain signal into a frequency domain to obtain a processed frequency domain signal; and performing filtering processing on the processed frequency domain signal according to the homomorphic filtering parameter, and performing tone mapping on an obtained filtering result. According to the invention, detail loss and visual distortion are avoided.

The invention discloses a prison abnormal behavior recognition method and system based on edge intelligent analysis, and belongs to the technical field of intelligent security protection, and the method comprises the steps: deploying edge nodes at each monitoring point of a prison, collecting a synchronous monitoring image flow, recognizing a low-light environment image frame through illumination evaluation, and storing the low-light environment image frame in a database; enhancing the image by using an improved Retinex algorithm optimized by a prison scene noise sample library; inputting the clear enhanced image into a lightweight CNN model, performing multi-dimensional matching with a prison abnormal behavior category knowledge base of a three-layer structure through an embedded behavior classification engine, and outputting a classification result of calibrated confidence; when the confidence exceeds a threshold value, triggering graded early warning, and associating the monitoring platform with peripheral sensor synchronous data to form a multi-mode alarm evidence chain; the edge node regularly encrypts and summarizes the early warning data packet and the negative sample data, and feeds back to the training end to realize model incremental learning; according to the method, the low-light environment adaptability and the feature discrimination capability are improved, and the recognition accuracy and the real-time performance are guaranteed.

The invention relates to the technical field of power transmission line detection, in particular to a nondestructive detection method and system for a power transmission line. The unmanned aerial vehicle is used for putting the airborne nondestructive testing robot to the power transmission line through the special mounting device, and the unmanned aerial vehicle is adaptive to various line structures and the number of sub-wires. And the ground remote workstation drives the robot to move through 5G communication and carries out X-ray detection to obtain a high-resolution image. Based on the normalized matching degree of the X-ray image of the to-be-detected crimping fitting and the corresponding structural feature template, determining an adaptive denoising threshold value of wavelet transform, denoising the X-ray image, and segmenting the X-ray image into a steel core area and an aluminum pipe area through gray histogram analysis; and carrying out local adaptive enhancement by adopting a multi-scale Retinex algorithm, and obtaining a nondestructive testing result of the power transmission line through a multi-task defect identification network fused by attitude correction and a geometric attention mechanism. The nondestructive testing precision of the power transmission line is effectively improved.

The invention relates to the technical field of power station monitoring, and provides a multi-source data fusion power station oil conservator monitoring method and system, and the method comprises the steps: recognizing the actual oil level of an oil conservator through an image processing algorithm based on an infrared image of the oil conservator; the reading of the oil level gauge is compared with the theoretical oil level range, the actual oil level of the oil conservator and the historical average value of the oil level, and whether the reading of the oil level gauge is normal or not is judged; if the reading of the oil level gauge is normal, whether the oil level of the conservator is normal is diagnosed; wherein the image processing algorithm comprises the following steps of: enhancing an infrared image of the oil conservator by adopting a multi-scale Retinex algorithm, calculating the gradient of the enhanced image, retaining a local maximum point in the gradient direction, carrying out edge classification based on the local maximum point, determining a candidate straight line set under length constraint and dip angle constraint, and carrying out image processing on the candidate straight line set; and the straight line with the maximum cumulative gradient value is selected from the candidate straight line set to serve as the optimal liquid level line, and the actual oil level of the conservator is calculated. And high-frequency and accurate monitoring of the oil level is realized.

The invention discloses a peach vibration measurement point positioning and alignment control method based on vision. The method comprises the following steps: carrying out tree peach image enhancement processing by using an automatic multi-scale Retinex algorithm; training an on-tree peach fruit recognition model based on YOLOv8, and obtaining pixel coordinates of a center point of an on-tree peach fruit recognition frame; acquiring depth information of a target object based on binocular stereoscopic vision, and calculating to obtain three-dimensional coordinates of a central point of a peach recognition frame; a laser Doppler vibrometer, a binocular camera and a holder are utilized to construct an acoustic vibration response automatic acquisition device for peaches on a tree, and combined calibration of the laser Doppler vibrometer and the binocular camera is completed based on a PnP algorithm. The mapping relation between the peach vibration measurement points and the rotation angle of the laser Doppler vibration measurement instrument under a camera coordinate system is solved based on a PnP algorithm, the laser Doppler vibration measurement instrument is controlled to rotate through a holder, one-by-one automatic alignment of the peach vibration measurement points on the tree is achieved, and the method is used for assisting field automatic collection of sound and vibration response data of the peaches on the tree.

The invention provides an automatic face feature recognition system and method based on image processing, relates to the technical field of face recognition, and aims to guide multi-scale feature fusion and illumination decomposition by using a thermodynamic diagram generated by face structure information, effectively enhance feature expression of key areas of five sense organs, suppress background interference and improve recognition efficiency. An improved Retinex algorithm is combined with a thermodynamic diagram to realize adaptive illumination component estimation, the halo effect of a traditional method in an edge region is overcome, illumination invariance of reflection component features is ensured, and the illumination invariance of the reflection component features is ensured by generating an accurate shielding mask from a reflection component diagram and extracting local discriminative features from an unshielded region. The method can effectively cope with challenges brought by shelters, finally, weighted fusion of global reflection component features and local discriminative features is combined with principal component dimensionality reduction and nearest neighbor classification, a recognition process with clear hierarchy and cooperative work is formed, and reliable identity recognition under double difficulties of illumination variation and local sheltering is realized.

The application provides a kind of face feature automatic identification system and method based on image processing, it is related to face recognition technical field, the present application is generated by using face structure information and is guided multi-scale feature fusion and illumination decomposition by heat map, effectively enhance the feature expression of key area of five organs, while inhibiting background interference, improved Retinex algorithm combines heat map and realizes adaptive illumination component estimation, overcome the halo effect of traditional method in edge area, ensure the illumination invariance of reflection component feature, by generating accurate occlusion mask from reflection component map, and extracting local discriminative feature to unoccluded area, it can effectively deal with the challenge brought by occlusion, finally, the weighted fusion of global reflection component feature and local discriminative feature, combined with principal component dimension reduction and nearest neighbor classification, constitute clear, collaborative work identification process, realize reliable identity recognition under the double difficulty of illumination change and local occlusion.

The application relates to the technical field of plant recognition, in particular to a natural image processing and analyzing method for plant recognition. Through the synergistic effect of a multi-scale Retinex algorithm and learnable weight parameters, accurate compensation of dark area illumination is realized, noise interference is effectively inhibited while the texture details of a plant main body are reserved, and a step-by-step processing mechanism combining a non-local mean filter and a directional convolution kernel is used to extract high-frequency details and strengthen edge outlines, so that the technical contradiction between noise suppression and detail reservation under low-illumination conditions in traditional methods is solved; and based on a correction system of color card matching and color distribution migration, through HSV space segmentation and histogram similarity measurement, the color deviation problem caused by artificial light sources is overcome, so that the color features of the plant main body are in a natural state.

The invention discloses a punch forming operation detection method and system based on industrial vision, and the method comprises the steps: triggering a polarized light source to irradiate the surface of a to-be-detected stamping part, and collecting an image of the to-be-detected stamping part at multiple angles through an industrial camera; carrying out image enhancement on the image by using a self-adaptive Retinex algorithm, and segmenting the enhanced image by using an Otsu dual-threshold method; carrying out morphological skeleton extraction on the segmented image, calculating an Hu invariant moment, and generating a feature vector containing seven dimensions; calculating a standard template; and based on the standard template, three-level matching strategy comparison is carried out, the stamping parts are sorted according to the comparison result, and the defect types of the unqualified stamping parts are recorded. Through polarized light imaging, morphological feature fusion and a dynamic compensation mechanism, stable detection without a neural network is realized.

The application discloses a slope subsidence positioning method and system based on radar combined with video, relates to the technical field of geological disaster early warning, and comprises the following steps: collecting and processing point cloud data and images based on a slope radar and a camera, generating simulated SAR images based on the point cloud data, and applying a Retinex algorithm to generate enhanced video images; extracting time sequence features of the point cloud data, obtaining radar features through VAE coding based on the time sequence features, extracting multi-scale features in the enhanced video images, combining to create three-dimensional frustum features to generate a spatial feature map, generating video features based on the spatial feature map, and combining the spatial feature map and the radar features to generate fusion features; generating a two-dimensional Gaussian heat map based on the point cloud data, generating a predicted heat map using the fusion features, and combining the two-dimensional Gaussian heat map to generate an ROI feature map. Through multi-modal feature fusion and adaptive optimization, the application effectively improves the precision, robustness and real-time early warning capability of slope subsidence monitoring.

This invention relates to the field of image processing technology and discloses an underwater image enhancement method based on the Retinex algorithm. This method first acquires the original underwater image and then extracts multi-dimensional feature information through a preprocessing module (including histogram analysis, filtering analysis, etc.). It supports multi-scale processing, detecting the target processing scale when processing at multiple scales simultaneously, and calculating feature confidence to select the optimal features. The Retinex algorithm processing unit adopts a multi-branch fusion structure (color correction, contrast adjustment, and detail restoration branches), generating coefficients and fusing them to achieve enhancement. It can also dynamically adjust weights and parameters based on coefficient differences. The method comprehensively extracts features, adaptively processes at multiple scales, balances enhancement effects, improves underwater image quality, and is suitable for underwater image optimization.

The application discloses a garden plant health state monitoring method based on image analysis and belongs to the technical field of image analysis and plant health monitoring, and comprises the following steps: collecting reflection images and polarized light images of the same plant area under multiple wave bands; calculating the penetration depth of each wave band in the plant medium based on a radiation transmission model and a plant optical parameter library; enhancing the reflection images by adopting a multi-scale Retinex algorithm, removing the specular reflection interference by utilizing the polarized light images, and obtaining corrected images; extracting abnormal texture areas of the corrected images, combining the penetration depth information, and constructing a multispectral feature fusion matrix; based on the fusion matrix, shallow normal and deep abnormal areas and areas with abnormal layers are compared and analyzed, internal abnormal classification discrimination rules are executed, the tomographic distribution of the plant internal health state is determined, and a tomographic imaging diagram distinguishing areas by different colors is generated, so that nondestructive, non-contact and accurate detection of the internal hollow rot of the tree trunk is realized, and the detection result is intuitive and visual.

The invention relates to the technical field of underwater image processing and three-dimensional reconstruction, in particular to a three-dimensional reconstruction method and system for an underwater concrete apparent disease. The method comprises the following steps: acquiring a multi-view original image, and performing adaptive color correction including pixel-level compensation and quantile color balance based on a channel loss relationship; through double-branch enhancement, including a detail enhancement branch and an edge enhancement branch based on an improved Retinex algorithm, fusing the detail enhanced image and the edge enhanced image through an image fusion algorithm to obtain an enhanced image; and finally, carrying out three-dimensional reconstruction after refraction correction to generate a high-precision three-dimensional model. According to the method, a complex underwater environment is adapted through adaptive color correction, details are enhanced through double branches, edges are enhanced, halo is avoided, image features are enriched through multi-scale fusion, feature point extraction and matching precision is remarkably improved, a high-quality image basis is provided for three-dimensional reconstruction with low calculation cost, and the method is adapted to engineering field application.

The application belongs to the technical field of image data processing, and discloses a driver fatigue state early warning method and system based on face recognition tracking, which comprises the following steps: extracting a face area through semantic segmentation and splitting a single-channel grayscale image, then calculating pixel point local complexity and noise degree to obtain a window adjustment coefficient, and further determining an adaptive window size, so that different pixel area features can be adaptively fitted, and processing deviation caused by a fixed window can be effectively reduced; subsequently, a light component is extracted based on the adaptive window and an image is enhanced through a Retinex algorithm, so that the quality of a face image under complex light can be improved, and the detail definition is improved; finally, the fatigue degree is detected in combination with a PERCLOS algorithm, so that the facial fatigue features of a driver can be more accurately captured, and effective recognition and early warning of the fatigue state are realized. The application can continuously and stably monitor during driving, and provides reliable protection for driving safety of a driver, and reduces the risk of accidents caused by fatigue driving.

The application discloses a kind of water turbine generator stator hole positioning method and system, belong to water turbine maintenance technical field.The method includes: acquisition stator hole image, using the improved Retinex algorithm of bilateral filter based on HSV color space is carried out image enhancement;By setting HSV threshold value, extract black pixel, establish two-dimensional coordinate system and filter non-target pixel;By quadrant analysis and coordinate average method, accurately position hole center pixel coordinate;In combination with similar triangle ranging algorithm and coordinate system transformation, calculate hole actual space coordinates.Realize the full-process automation from image recognition to space positioning, greatly improve the positioning accuracy and operation efficiency, provide reliable technical support for subsequent automatic cleaning operation.

The invention provides a real-time detection method and system for micro-defects of a breathable film based on multi-scale feature enhancement, and the method comprises the steps: carrying out the preprocessing of a breathable film image through an improved multi-scale Retinex algorithm, so as to enhance the contrast and visibility of the micro-defects; extracting multi-scale features by using a hierarchical feature enhancement network, and introducing a multi-scale channel enhanced attention module MCEA to perform cross-scale fusion and optimization on the features; and the ProbIoU loss function is adopted to synchronously optimize the detection precision and the bounding box regression efficiency, so that high-precision real-time micro-defect detection is realized, and the defect identification robustness and the reasoning speed in an industrial scene are effectively improved.

The application discloses a kind of HAR microstructure bottom interference image contrast and signal-to-noise ratio enhancement method, belong to optical precision measurement technical field.This method helps to improve the contrast and signal-to-noise ratio of bottom interference image collected when low coherence microscopic interference system measures high aspect ratio microstructure, finally promotes the measurement accuracy of HAR microstructure three-dimensional topography.It contains the following steps: first, using near-infrared microscopic interference system to collect HAR microstructure bottom low-contrast interference image;Subsequently, using EMD (Empirical Mode Decomposition) algorithm to do background processing to bottom low-contrast interference image;Finally, using improved JIEP-Retinex algorithm to process bottom interference image after background removal, and obtain contrast and signal-to-noise ratio enhanced bottom interference image.The application enhances the contrast and signal-to-noise ratio of HAR microstructure bottom interference image without changing the interference system, improves the measurement accuracy of HAR microstructure three-dimensional topography.

The present application relates to the technical field of image processing, and more particularly to an identity recognition method and system based on image processing. In the present application, when performing identity recognition, the collected image is subjected to image illumination compensation operation through a closed-loop process of semantic perception, type classification, and mode compensation fusion. The type classification is divided into low-light scene and overexposure scene. For the low-light scene, a Retinex algorithm guided by face region distribution is used to perform image enhancement processing on the pre-screened face image. For the overexposure scene, the cliplimit parameter of the CLAHE algorithm is adjusted in a targeted manner by perceiving the gradient features of the highlight region and the key texture area, so as to perform image enhancement processing on the pre-screened face image. The present application realizes accurate adaptation to the face structure and retains key details in the illumination repair, solves the global defects of the existing method, and lays a high-quality image foundation for subsequent occlusion repair and posture correction.

This invention provides a method for recognizing low-light signs and determining vehicle refueling behavior, comprising: preprocessing input low-light video or images of gas stations based on the Retinex algorithm to output an enhanced image with optimized brightness and contrast; inputting the enhanced image into a YOLO detection model to detect and classify refueling signs and vehicles, outputting structured detection data including target category, bounding box coordinates, and recognition confidence; establishing a mapping relationship between image coordinates and real-world coordinates based on target vehicle coordinate information and homography transformation, combining the functional area division of the gas station to complete spatial constraint determination, and correcting the detection confidence to eliminate targets in unreasonable spatial locations; completing continuous frame trajectory tracking of vehicles through Kalman filtering, statistically analyzing the dwell time of vehicles in the effective refueling area, and combining vehicle type classification dynamic thresholds and spatial constraints to complete refueling behavior determination, outputting the final recognition and analysis results.