113 results about "Gaussian pyramid" patented technology

The invention discloses a glass lens surface scratch detection method and system, relates to the technical field of precision optical detection, and aims to solve the problems of scratch false detection, leak detection and poor algorithm adaptability caused by interference fringes, noise coupling and poor form adaptability in a high-reflection / complex coating process scene in the prior art. According to the scheme, an orthogonal polarization state composite light field is generated based on a multi-angle polarization light source array and a near-infrared compensation light source, and candidate regions are extracted through dynamic threshold segmentation and a direction gradient tensor matrix; gaussian pyramid multi-scale feature fusion and refraction angle consistency verification are utilized to eliminate artifact interference; constructing a direction constraint convolution kernel group to decompose scratches and background textures, and dynamically allocating computing resources in combination with a cascade network; feeding back closed-loop calibration light source wavelength and convolution kernel parameters in real time through coating parameters; according to the method, the precision and robustness of high-reflectivity surface scratch detection are remarkably improved, and meanwhile, the requirements for high-resolution image processing and real-time performance in a high-speed production line are balanced.

The invention discloses a data line surface defect rapid nondestructive detection method based on intelligent image recognition, relates to the technical field of image data processing, and aims to solve the technical problems of difficult defect feature separation and low detection accuracy under complex weaving texture noise interference, and the method comprises the following steps: S1, collecting a data line image and carrying out graying processing; s2, constructing a multi-scale image pyramid, accurately segmenting the image by adopting a self-adaptive threshold algorithm, and realizing rapid detection of surface defects of the data line in combination with Hough transform; s3, frequency domain separation of weaving texture and background noise is realized through Fourier transform, interference is filtered out in combination with a band-pass filtering technology, and then the defect contrast is enhanced through histogram equalization; according to the method, the three-layer Gaussian pyramid is constructed for multi-scale decomposition, and the band-pass filtering technology is combined, so that the weaving texture and the defect signal are effectively separated, the detection accuracy is greatly improved, and the problems of missing detection and misjudgment caused by frequency characteristic confusion are thoroughly solved.

The invention provides a low-light large dynamic image enhancement method based on dynamic weight and pyramid fusion. The low-light large dynamic image enhancement method is suitable for complex illumination imaging in security monitoring. According to the method, the global weight and the detail weight of an image are obtained according to the global average brightness, the local brightness and the gradient of an image sequence, and the total weight is obtained through weighting. And the halo phenomenon easily occurring in the fusion process is reduced through guide filtering. And combining Gaussian pyramid and ratio pyramid decomposition and weighting to obtain a final fusion image. According to the method, the problems of detail loss and limited dynamic range in the low-light scene are effectively solved. Experiments show that the method is superior to the prior art in information entropy, average gradient, edge strength, spatial frequency and other key indexes. The technology has an all-time adaptive capability, is suitable for the fields of intelligent transportation, urban security and protection, low-illumination monitoring and the like, and has a wide market prospect.

The invention discloses an infrared and visible light image registration method based on an improved SIFT algorithm, and the method comprises the steps: constructing a Gaussian difference pyramid of infrared and visible light images, so as to effectively capture the multi-scale features in the images; performing local adaptive FAST key point extraction on each layer of the pyramid, and detecting significant feature points of the image on a multi-scale level; based on gradient direction distribution of images in key point neighborhoods, main direction distribution is carried out on key points, so that the key points can still keep consistent under different rotation angles; coding the key points based on the gradient information features and generating corresponding feature descriptors to be applied to subsequent registration operation; and performing initial registration by using the similarity between the descriptors, verifying and optimizing an initial registration result by using an optimized RANSAC algorithm, and eliminating mismatching points. According to the method, the number of infrared and visible light image feature point detection and matching is increased, the time complexity is reduced, and the matching precision is ensured.

The invention relates to the field of computer vision, in particular to an image feature recognition method based on computer vision, which comprises the following steps of: preprocessing an input image, removing image noise and correcting image gray deviation to obtain a preprocessed image; performing multi-scale feature extraction on the preprocessed image, obtaining image local texture features and global contour features under different scales, performing dynamic weight fusion, calculating dynamic fusion weight based on a feature response value and a local complexity factor, and performing dimension reduction processing on fusion features through a principal component analysis algorithm to obtain a target feature set; and matching the reference features, calculating the Euclidean distance between the target feature set and the reference features, determining an adaptive matching threshold, judging a matching result, and completing image feature recognition. According to the method, through adaptive filtering and gray level equalization preprocessing, Gaussian pyramid multi-scale feature extraction and dynamic fusion and adaptive threshold matching, feature extraction accuracy, characterization capability and recognition robustness are improved.

The invention discloses a color printed matter defect automatic detection system and method based on machine vision, and relates to the technical field of computer vision, and the method comprises the steps: converting a color image into a gray level image, generating a boundary enhanced gray level image through a Canny edge detection algorithm, calculating the offset of edge pixels through sub-pixel recovery, and obtaining a color printed matter defect detection result. Extracting an edge pixel proportion based on the sub-region division table, performing amplification tracking on edge dense sub-regions, and analyzing RGB color deviation; through a multi-scale Gaussian pyramid decomposition and edge refinement technology, analyzing multi-scale features of the boundary enhanced grayscale image and optimizing edge precision; and classifying edge defects and color defects of each sub-region by utilizing a defect threshold value, calculating a comprehensive risk value, increasing a risk level according to a boundary condition, and generating a detection report. According to the method, the Canny edge detection algorithm is combined with sub-pixel recovery, so that the edge extraction precision and the positioning capability of color printed matter defect detection are improved.

The invention discloses a mechanical arm anti-interference control method and system based on visual servo, and relates to the technical field of mechanical arm anti-interference control, and the method comprises the steps: collecting an initial image through an industrial camera during the operation of a mechanical arm, and carrying out the preprocessing; selecting a pixel point from the central area of the initial image as a starting point by using a random walk algorithm, generating a step length in a random direction, calculating the next coordinate of the starting point, cutting, obtaining a walk path set, carrying out pixel value disturbance, generating a pseudo-abnormal image, and carrying out two-dimensional position coding based on the pseudo-abnormal image to obtain an embedded sequence vector; based on the embedded sequence vector, using a repair model to obtain a repair image, and generating a reconstructed image in combination with a deconvolution operation; by introducing the random walk algorithm, the multi-head self-attention mechanism, the Gaussian pyramid and the sparse dictionary, the perceptual robustness, the task execution stability and the generalization ability of the mechanical arm in the disturbed environment are remarkably improved.

The invention discloses a deep learning-based mixed-shooting image correction method and system, and relates to the field of computer vision, and the method comprises the steps: carrying out the illumination normalization processing of a mixed-shooting image group, and constructing a Gaussian pyramid image group; inputting the Gaussian pyramid image group into a ResNet-34 network to extract a multi-scale feature map, and generating spatial position and channel statistical information; and converting the spatial position and the channel statistical information into a DNA sequence fragment through a DNA base mapping rule. Illumination normalization is achieved through Retinex decomposition and Gaussian filtering, the exposure difference of different devices is effectively eliminated, the input quality of follow-up processing is guaranteed, traditional feature description is converted into biological sequence comparison through DNA base coding, geometric parameters are optimized in combination with quantum annealing, and the accuracy of the method is improved. The matching precision of a low-texture area and the correction effect of a large-view-angle-difference scene are remarkably improved, and the sub-pixel-level matching precision is achieved based on weighted RANSAC and multi-scale pyramid fusion.

The invention relates to the technical field of computer vision and robot positioning, and discloses a dynamic 3DGS-SLAM method and system based on Gaussian pyramid and adaptive densification. The method comprises the following steps: generating a semantic mask through real-time dynamic target detection so as to distinguish a static background from a dynamic object; constructing a 3D Gaussian map model of the scene; rendering images in parallel on a full-resolution view and a down-sampling resolution view by adopting a motion perception Gaussian pyramid rendering method, and fusing rendering results by utilizing a dynamic mask so as to eliminate motion edge artifacts; a self-adaptive densification strategy based on a monotonic attenuation function is adopted, the initialization radius of the Gaussian ellipsoid is dynamically adjusted based on the training progress, and high-density initialization and progressive redundancy pruning are executed to optimize the geometric fidelity; and finally, performing coarse-to-fine camera pose optimization, and outputting a precise pose and a high-fidelity static map. According to the method, the problems of tracking drift and rendering artifacts under dynamic interference are effectively solved, and the positioning precision and the rendering quality are improved.

The invention relates to the technical field of image data processing, in particular to a tourism management-oriented scenic spot three-dimensional modeling method and system, and the method comprises the steps: obtaining a scenic spot image of a target scenic spot, and determining the character possibility information and Gaussian pyramid in the scenic spot image; correcting a difference image between adjacent layers of the Gaussian pyramid by utilizing the character possibility information to obtain a target Gaussian difference pyramid; and based on the target Gaussian difference pyramid, determining multi-view three-dimensional modeling of the target scenic area. According to the method, the Gaussian difference pyramid for removing the influence of the passengers is constructed, so that the feature points selected by SIFT only comprise key points of the scenic spot as far as possible and do not comprise key points causing interference of the passengers, the precision and reliability of three-dimensional modeling of the scenic spot are improved, and the situations of deformity, missing, distortion and the like during three-dimensional reconstruction are avoided.

The invention discloses a filtering adjustment method and system based on an adaptive clock, and relates to the technical field of filtering adjustment, and the method comprises the steps: carrying out the time domain framing processing of a collected input signal through employing a sliding window, and combining DCT and compressed sensing to reconstruct the signal, and the main frequency of the signal and the dynamic change of the main frequency in the time sequence are accurately extracted through FFT, Gaussian pyramid layering and a multi-scale optical flow method, so that the frequency identification capability of the non-stationary signal is effectively enhanced, the frequency spectrum resolution is ensured, the data processing amount is remarkably reduced, the response speed of the signal frequency change is improved, and the method is suitable for popularization and application. Through the main-sub clock structure, the quick response of the center frequency of the filter to the change of the main frequency is ensured, the selectivity of the filter and the signal fidelity are improved, through the compensation adjustment of environmental factors, the influence of temperature and voltage changes on signal processing can be effectively reduced, and the robustness and stability of the system are enhanced.

The invention provides a depression image detection method fusing a Gaussian pyramid and a spatial domain. The method comprises the following steps: acquiring an original face image to be processed; the trained detection model is used for processing the original face image to obtain a detection result, and the detection model comprises a primary feature extraction module, a fusion module, a Gaussian pyramid attention module, a spatial domain attention module and a post-processing module. A Gaussian pyramid attention module is constructed and used for capturing the dynamics and diversity of multi-scale features, so that the perception ability of the model to different-scale information is enhanced; further mining significant features in the image by introducing a spatial domain attention module and based on a self-adaptive perception mechanism of a key region; and finally, through deep fusion of a Gaussian pyramid attention module and a spatial domain attention module, the integrity and discrimination of feature expression are improved, so that the detection precision of the detection model is effectively improved, and the model is low in calculation complexity and high in applicability.

The invention discloses a robot visual servo control system and control method based on dense tracking, and the method comprises the steps: carrying out the environment perception of a target robot, obtaining environment perception information, carrying out the image preprocessing of the environment perception, and obtaining the preprocessed environment perception information; a three-level Gaussian pyramid is constructed, multi-scale optical flow field construction is carried out according to the preprocessed environment perception information, and a bidirectional optical flow verification mechanism is set to carry out mismatching elimination; extracting a plurality of feature points of the current frame of image according to the constructed multi-scale optical field, introducing a DBSCAN spatial clustering algorithm to perform active point extraction to obtain a dynamic active point set, analyzing whether an error exists between a real-time operation track of the target robot at the current moment and a preset path based on the dynamic active point set, and if an error exists, determining that the target robot is in a real-time state. And if so, constructing a servo control scheme to carry out real-time error compensation. Therefore, high-precision and high-robustness visual servo control is realized.

The invention belongs to the technical field of image enhancement, and particularly discloses a low-illumination image enhancement method based on an information fusion strategy, and the method comprises the steps: carrying out the processing of an inputted low-illumination image through an image enhancement algorithm based on adaptive Gamma correction, and generating a first group of multi-exposure image sequences; processing the same input image through an improved quadratic function enhancement algorithm to generate a second group of multi-exposure image sequences; and performing multi-scale fusion on the first group of multi-exposure image sequences and the second group of multi-exposure image sequences, including distributing the weight of each image through a weight strategy, performing multi-scale decomposition on the images by using a Gaussian pyramid and a Laplacian pyramid, and reconstructing and generating a final enhanced image after layer-by-layer fusion. According to the method provided by the invention, the advantages of brightness enhancement and color optimization are combined, and an image with balanced brightness, rich details and natural colors can be generated in a low-illumination scene.

Method for detecting surface defects of metal strip based on CFLOW-AD model, obtaining surface images of defect-free metal strip, constructing a training data set after amplification, building a PatchSVDD feature extraction model, importing the training data set for feature extraction pre-training to obtain a pre-trained model; passing the pre-trained model into the encoding layer of the CFLOW-AD model as a feature extractor; extracting features of the Gaussian pyramid of normal metal strip to construct a multi-scale feature pyramid; training independent decoders for each scale layer using the training data set; using the trained CFLOW-AD model to detect defective test sample images to determine the area of the defect on the image. Self-supervised learning is carried out using defect-free samples, solving the problem of difficult collection of defect samples, and solving image noise caused by imaging factors through data amplification, improving robustness and reducing noise misdetection.

The invention belongs to laser stripe image data processing, and particularly relates to a multi-scale gradient gravity center laser center line extraction method and system, and the method comprises the steps: S1, carrying out the feature extraction and enhancement of a laser stripe image, intensifying detail branches through a space channel weight map, obtaining a bounding box positioning result based on depth separable convolution and residual connection, and obtaining a bounding box positioning result; s2, acquiring a prediction center for each column by adopting a prediction method, and searching a gray peak value in a normal adaptive window to realize coarse positioning; the method comprises the following steps: S1, building a local coordinate system and an elliptical window along the coarse center line, and constructing a multi-scale Gaussian pyramid to carry out background suppression and image enhancement, S4, generating a weighted graph through cross-scale fusion, calculating a weighted gray gravity center in each window, and carrying out image enhancement on the weighted graph. And after smoothing, a high-precision laser stripe center line is output. And the accuracy and robustness of extracting the laser center line are improved.

The invention discloses an underwater image enhancement method and system based on three-input multi-scale fusion. The method comprises the following steps: carrying out visibility recovery on an image to be processed; performing contrast enhancement through a nonlinear mapping function; carrying out enhancement processing on the contour of the high response area; respectively calculating a Laplacian contrast weight map, a saliency weight map and a saturation weight map of the three processed images; linearly combining all types of weight maps to obtain an aggregation weight map, and normalizing the aggregation weight to obtain a normalized weight map; decomposing the three processed images into a Laplacian pyramid, decomposing the normalized weight map into a Gaussian pyramid, and performing fusion through upward sampling and addition reconstruction; carrying out smoothing processing and edge-preserving sharpening processing on the fused image to obtain an image after underwater image enhancement and restoration; according to the method, the color cast problem of the underwater image is solved, the image contrast is effectively improved, and the texture details of the image are improved.

The invention relates to the technical field of digital image processing, in particular to a real-time image quality enhancement method for a vehicle-mounted camera EMC test, and the method comprises the steps: obtaining real-time image data and historical image data; and performing multi-branch collaborative decoupling processing on the real-time image data to generate a frequency domain purification graph, a core structure graph, a space domain purification graph and a time domain stability graph. And performing local statistical analysis on the real-time image data to generate an artifact intensity map and a perception saliency map. Under a multi-resolution Laplacian pyramid framework, fusing the frequency domain purification graph and the space domain purification graph; the weight of the fusion process is intelligently regulated and controlled spatially and hierarchically by an artifact intensity graph, a perception saliency graph and a time domain stabilization graph which are constructed based on a Gaussian pyramid, and finally a high-quality enhanced image is reconstructed and generated. According to the invention, through a multi-branch cooperative decoupling and intelligent fusion method, real-time enhancement of the vehicle-mounted camera image under EMC interference is realized.

The invention discloses a depression detection method fusing a multi-modal attention mechanism, and relates to the technical field of auxiliary psychological health diagnosis, and the method comprises the steps: respectively extracting a facial image and a voice signal from an original video, extracting a global feature map from the facial image through a deep convolutional network, and introducing a local fusion module and a global fusion module; combining a Gaussian pyramid attention module with a spatial domain attention module; speech signals are converted into a Mel spectrogram through preprocessing, speech features are extracted through a SincNet network, and the speech features are further sent to a time-frequency attention module to highlight depression-related intonation and energy changes; in the feature fusion stage, a self-adaptive attention mechanism is adopted, self-attention modeling is performed on face and voice modes, cross-mode fusion and context modeling are completed through a Query-Key-Value structure, and a depression score is output through a full connection layer. According to the scheme, the problem that cross-modal nonlinear correlation is difficult to dynamically capture is solved, and effective technical support is provided for mental health assessment and intervention.

The invention relates to a riverway ice condition identification method based on optics-SAR fusion and adaptive segmentation, and belongs to the technical field of remote sensing image processing and application. Riverway ice condition features are extracted from the optical remote sensing image, and a Ka-SAR feature map is extracted from the Ka-SAR image by adopting an improved high-resolution network; carrying out multi-modal and multi-scale feature fusion on the extracted features, carrying out scale specificity feature extraction by adopting a Gaussian pyramid, and then carrying out weighted fusion on the river ice condition features and the Ka-SAR features on each scale based on a scale specificity weight distribution principle; aggregating the multi-scale fusion features into a final fusion feature map by adopting a bottom-up pyramid reconstruction strategy; improved Kuan filtering is used to optimize the fused feature map, and adaptive threshold segmentation is used to realize ice surface and non-ice surface binary classification in the feature map. The method can achieve the precise segmentation of the ice condition region, and improves the recognition precision of the thin ice region.

The present invention discloses a method and system for monitoring and identifying the running state of a train at a station based on images, which relates to the technical field of train state identification. The method includes collecting image data for two-dimensional wavelet decomposition, applying a soft threshold for denoising processing and regenerating the denoised aligned image data; constructing a Gaussian pyramid of the aligned image data, performing equalization mapping through histogram equalization, and merging each layer of the Gaussian pyramid into complete image data. The method of the present invention significantly enhances the local details of the image under different lighting conditions through CLAHE adaptive contrast adjustment, making the originally low-contrast areas clearer. Through multi-scale feature extraction, the Gaussian pyramid decomposition generates image levels with different resolutions, ensuring that the structural information of the image at different scales is retained. Through the combination of SGM and RANSAC, the point cloud still has strong noise resistance in complex scenes and can adapt to environmental conditions such as light changes and reflection interference.

This application discloses a real-time image stitching method and apparatus. The method includes: receiving images uploaded to the cloud by a camera device in real time; extracting feature points from the images and matching feature points between the current frame and the previous frame; calculating the ratio of the homography matrix score to the sum of the homography matrix score and the fundamental matrix score to determine whether to use the homography matrix or the fundamental matrix to recover the image's pose parameters and map points, and initializing the map; estimating the pose of the current frame and optimizing the pose of the current frame using candidate frames; converting the coordinates of the map points to two-dimensional coordinates and performing plane fitting; converting the coordinates of the image corner points in the camera coordinate system to the object coordinate system, calculating perspective transformation parameters and performing geometric transformation on the image; and performing Gaussian pyramid fusion on the generated tiles. This method solves the problems of low efficiency in scene reconstruction using motion reconstruction algorithms and the inability to process real-time photogrammetric data.

This invention relates to an image denoising method, system, and readable storage medium. The method includes: performing Gaussian filtering and downsampling on a current frame image to obtain a first downsampled image; performing Gaussian pyramid decomposition to obtain a current frame image group; upsampling to obtain an upsampled image, and subtracting it from the current frame image to obtain high-frequency information; performing motion estimation and texture estimation at different scales on the current frame image group and a reference frame image group, and correcting them with guided filtering; performing spatiotemporal filtering on the first downsampled image and the reference frame image based on motion estimation weights; upsampling the denoised downsampled image to obtain a denoised upsampled image; and weighted fusing the denoised upsampled image and high-frequency information according to texture estimation weights to obtain a final image; downsampling the final image and performing Gaussian pyramid decomposition to obtain a reference frame image group for denoising the next frame image. This invention can preserve more texture details while increasing the image signal-to-noise ratio.

The application discloses an environment monitoring method and device, which is used for realizing accurate counting of river floating objects in a river monitoring image, so that a more accurate and real-time monitoring result of the river environment quality is obtained. The environment monitoring method provided by the application comprises the following steps: determining a river monitoring image; performing Gaussian filtering and smoothing processing on the river monitoring image, and performing down-sampling on the image obtained through the Gaussian filtering and smoothing processing for a preset number of times; constructing a Gaussian pyramid model by using the image obtained through the Gaussian filtering and smoothing processing and the image obtained through each down-sampling; the Gaussian pyramid model comprises multiple layers of images, wherein the bottom layer of image is the image obtained through the Gaussian filtering and smoothing processing, and each layer of image other than the bottom layer is the image obtained through one down-sampling; determining a region of interest of the river monitoring image by using each layer of image of the Gaussian pyramid model; counting the river floating objects in the region of interest; and determining the river environment quality based on the counting result.

This invention discloses a near-infrared image dehazing method based on bright area clustering optimization. The method is characterized by first acquiring a hazy near-infrared image, then constructing an image dehazing model and building a Gaussian pyramid for the hazy near-infrared image. Candidate bright area binary masks are extracted and refined at each scale, and after mapping and fusion, a baseline candidate bright area binary mask and scale persistence features are obtained. Next, feature extraction and cluster analysis are performed on the baseline candidate bright area binary mask, and a physical consistency cost function is constructed based on an atmospheric scattering model for verification, obtaining a global atmospheric light estimate. Then, the global atmospheric light estimate is used for normalization and adaptive dark channel extraction and fusion to obtain an initial transmittance distribution, which is then refined and constrained to obtain an optimized transmittance distribution. Finally, the dehazed image is reconstructed based on the atmospheric scattering model. The advantages are improved transmittance estimation accuracy and edge preservation capability, achieving high-quality restoration of hazy near-infrared images.

The invention relates to the technical field of medical image processing, and discloses a chronic obstructive pulmonary emphysema distribution quantitative method and system based on multi-scale segmentation, and the method comprises the steps: carrying out the anisotropic diffusion filtering noise reduction of a chest CT image; segmenting a lung field and removing a blood vessel bronchial structure by adopting a region growing algorithm; multi-scale image representation is constructed based on a Gaussian pyramid, an emphysema candidate area is identified in a coarse scale layer, and a boundary is accurately drawn by adopting a self-adaptive threshold value in a fine scale layer; extracting local texture features to distinguish the lobular central emphysema and the total lobular emphysema; dividing severity levels according to spatial aggregation characteristics and density gradient distribution, and calculating an air swelling volume ratio and a distribution heterogeneity index; the three-dimensional pseudo-color volume is used for drawing visualization, a structured quantitative report is generated, accurate segmentation and subtype classification of the emphysema area are achieved, and comprehensive quantitative analysis indexes are provided.

The invention discloses an SIFT (Scale Invariant Feature Transform) algorithm hardware circuit implementation, which optimizes the hardware circuit implementation of an original SIFT algorithm, and solves the problems of slow operation of the SIFT algorithm and large resource consumption when the SIFT algorithm is deployed on an FPGA (Field Programmable Gate Array). According to the specific implementation scheme, the method comprises the steps that a one-layer six-group Gaussian pyramid is built, and an independent precalculated 21 * 21 Gaussian filtering kernel is used in each group; extreme points of three adjacent groups of differential pyramids are detected by adopting a threshold method, and edge response points are eliminated; a CORDIC algorithm is adopted to calculate the gradient direction and amplitude of a Gaussian image where the feature points are located, and a 16-row 16-column calculation result is output for gradient histogram statistics and descriptor generation; and normalization of a 128-dimensional descriptor is realized by using a single divider. The method has the advantages of low resource consumption, high real-time performance and the like, and is suitable for scenes, such as an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit) and the like, needing hardware acceleration of the SIFT algorithm.

The invention discloses an image definition assessment method and device, equipment and a storage medium, and relates to the technical field of image processing, and the method comprises the steps: obtaining a to-be-assessed grayscale image; performing Gaussian pyramid downsampling processing of the target layer number on the to-be-evaluated grayscale image to obtain a to-be-evaluated multi-scale image corresponding to the target layer number; based on a dynamic gradient threshold denoising method, carrying out definition score calculation on the to-be-evaluated grayscale image and each to-be-evaluated multi-scale image to obtain an image definition score corresponding to the to-be-evaluated original image and each to-be-evaluated multi-scale image; and determining target image definition corresponding to the to-be-evaluated original image based on the to-be-evaluated original image and the image definition scores corresponding to the to-be-evaluated multi-scale images. According to the method, comprehensive evaluation of the image definition is realized by analyzing the multi-scale features of the image and performing dynamic threshold processing, meanwhile, noise is effectively suppressed, important details such as image edges and the like are reserved, and the accuracy and robustness of image definition evaluation are improved.

The present application relates to a kind of microbial microscopic image target feature identification method, device and storage medium, applied to image processing technical field, comprising: by marking the image on the target to be identified, convert the target to be identified into different scale space and construct multiple groups of Gaussian pyramid and convert into feature pyramid, according to feature pyramid, obtain feature point, obtain the feature parameter of each feature point, when the target needs to be identified, convert the image to be identified into multiple groups of Gaussian pyramid, and the pixel point in Gaussian pyramid is matched with feature point, if the number of pixel point on the image to be identified is matched exceeds the number of pre-set, then consider that there is identification target on the image;By the present application, without using convolutional neural network, microorganism image features can be quickly and accurately automatically identified, and then automatically identify white blood cells, clue cells, spores, blastospores, hyphae, trichomonas and other microorganisms.

The invention discloses an initial value search algorithm for SIFT feature point matching based on GPU acceleration, and belongs to the technical field of computer vision and image processing. Constructing a multi-scale space of adjacent multi-frame Gaussian pyramids based on the GPU to obtain a complete Gaussian pyramid and a Gaussian difference pyramid, and performing acceleration calculation on the Gaussian blur GPU; calculating the feature point descriptors; matching the SIFT feature points; and constructing a control point matching equation based on calculation of SIFT feature points. According to the invention, GPU-based parallel optimization is carried out in the strain measurement process of the core synchronization mechanism of the synchronous automatic clutch, and scale space construction and descriptor calculation in an SIFT feature point detection algorithm are optimized, so that the measurement speed of strain measurement of the core synchronization mechanism of the synchronous automatic clutch is improved; an initial matching value is obtained through a least square method, so that the searching precision of the initial value is improved.