16 results about "Morphological transformation" patented technology

The invention discloses a shaving board target detection system and detection method based on deep reinforcement learning. The method comprises the following steps: acquiring a shaving board defect sample image data set; defining the state and action space of the Agent; designing a data set loader, and building a framework of a deep reinforcement learning target detection model; designing a target detection evaluation index and a reward function; and training a deep reinforcement learning target detection model by using the divided target detection data set, and selecting an optimal deep reinforcement learning target detection model in combination with a target detection evaluation index. According to the method, deep reinforcement learning is used, continuous morphological transformation is carried out on an initial candidate rectangular frame, and target defect position detection is completed; the method can act on the defect position detection task of the shaving board image, the calculation complexity is reduced, the self-adaptive detection capability is high, and the detection accuracy is high.

The present invention relates to the technical field of cell morphology detection. Disclosed are a remote-assisted intelligent blood cell recognition method and apparatus, and a storage medium. The method comprises the following steps: making a peripheral blood cell smear, and scanning a cell image; performing noise processing and isolated-point removal on the cell image on the basis of a first algorithm and a second algorithm; segmenting the cell image into a background area and a target area on the basis of a grayscale value of the cell image; obtaining color features of the cell image on the basis of a color page model, and processing the color features by means of both boundary transformation and morphological transformation, so as to obtain boundary features and morphological features of cells in the cell image; and performing recognition on the boundary features and the morphological features on the basis of a constructed recognition space, and outputting matched cell types. In the present application, an optimization process is added in a cell recognition process, and a coverage problem is taken into consideration from a local area first, and is then extended from the local to the entity, thereby ensuring the comprehensiveness of recognition, and improving the recognition precision.

The invention provides a mitral valve leaflet length automatic measurement method based on 3D-to-2D morphological transformation. The method comprises the following steps: firstly, acquiring three-dimensional medical image data of the heart of a patient, and extracting six partitions of a mitral valve and related heart structures; an orthogonal plane is calculated by fitting a mitral valve structure point set, and a cKDTree algorithm is used to determine a connected area of each partition, and a corresponding projection plane is established. And then extracting the contour of the projection point set through an Alpha shape algorithm, correcting the contour into a linear three-dimensional point set, and finally calculating the length of the valve leaflet of each partition. According to the method, the accuracy, consistency and efficiency of measurement are improved through an automation technology, personal errors are reduced, the method is suitable for various three-dimensional medical image data, and a more reliable basis is provided for clinical diagnosis and treatment of mitral valve diseases.

The invention provides an AI-based multi-terminal-oriented real-time editable data visualization system and method, and the method comprises the steps: building a visual canvas with a dimension field of a business data set in a business data source as a longitudinal axis and a measurement field of the business data set in the business data source as a horizontal axis, and initializing an AI data view of the business data source; recombining the display layout of the AI data view on each display terminal on the basis of the size characteristics of the canvas container in each display terminal, triggering the morphological transformation logic of the editing component to present the matched editing component on each display terminal, receiving the editing operation of a user on the editing component on each display terminal, and displaying the edited editing component on each display terminal. And performing derivative updating on the view state in each display terminal based on the data binding relationship and the layout dependency relationship among the editing components, and the operation type and the semantic context of the editing operation. Based on the scheme, automatic generation and intelligent linkage updating of the multi-end view based on the AI and the responsive rule can be realized.

The application discloses a wild animal video target detection method based on a feature fusion network, and comprises the following steps: collecting and labeling wild animal image and video data; performing morphological transformation, color transformation and contour destruction preprocessing; sequentially inputting the preprocessed image and video data into a feature extraction network to obtain multi-scale features; performing feature fusion on the extracted multi-scale features, fusing multi-scale features and same-scale features of adjacent image frames for the video data, and only fusing multi-scale features for the image data, finally obtaining multi-scale fusion features; inputting the multi-scale fusion features into a feature prediction network to obtain a prediction result; comparing the prediction result with a label in the training stage, calculating a loss function, performing gradient back propagation, completing model parameter updating, and until the network converges; in the inference stage, the prediction result is post-processed to obtain the final output result.

The present invention proposes a method for automatically measuring the length of the mitral valve leaflets based on 3D to 2D morphological transformation. The method first obtains three-dimensional medical image data of the patient's heart and extracts six partitions of the mitral valve and related heart structures. By fitting the mitral valve structure point set, the orthogonal plane is calculated, and the cKDTree algorithm is used to determine the connecting areas of each partition, and the corresponding projection plane is established. The contour of the projected point set is then extracted by the Alpha shapes algorithm and corrected to a linear three-dimensional point set, and finally the length of each partitioned leaflet is calculated. This method improves the accuracy, consistency and efficiency of measurement through automation technology, reduces human errors, is applicable to a variety of three-dimensional medical imaging data, and provides a more reliable basis for the clinical diagnosis and treatment of mitral valve disease.

The present invention discloses a method and system for identifying marine-related books based on computer vision, comprising: collecting a first cover page image of a marine-related book, recognizing text through grayscale and binarization processing and morphological transformation, and generating a feature data set for identifying marine-related books; constructing a CNN network with an AdamOptimier optimizer and a cross entropy function as a loss function, training through the feature data set, and recognizing the second cover page image of the book based on the trained CNN network to determine whether the book is a marine-related book; the present invention overcomes the problems of excessive operations and misjudgment in the current recognition of Chinese marine-related books, and saves machine running memory and time costs.

The paper medical record digitization information extraction method, system, equipment and medium based on image edge detection and Res-CRNN, the method comprises: sequentially performing gray processing, edge sharpening processing, image line recognition and rotation correction, mask processing and projection transformation on the original image with color information, generating handwritten digital training data through morphological transformation, and performing character recognition on the processed image based on the generated handwritten digital training data and Res-CRNN deep learning model to obtain the final text digital recognition result; the system, equipment and medium are used for realizing the paper medical record digitization information extraction method based on image edge detection and Res-CRNN; the original image is processed through gray processing, edge sharpening processing, image line recognition and rotation correction, and the digitization information extraction of the medical record image is realized through Res-CRNN, so that the paper medical record digitization information extraction method has the characteristics of efficient and accurate extraction of case image information and simple operation steps.

The invention relates to the technical field of information identification, in particular to a medicine information identification method and system based on AI vision, and the method comprises the following steps: importing a medicine outer package image, adjusting the contrast and brightness of the image, removing background noise, and obtaining a processed image. According to the method, the image of the external package of the medicine is processed, so that the definition of the image is improved, and high-quality input is provided for feature extraction. And after conversion to the gray mode, through analysis and morphological transformation of the convolutional neural network, accurate capture of drug shapes and textures is improved, and more accurate drug category classification is realized. According to the method, the accuracy of medicine identification is effectively improved, particularly the diversity and complexity of medicine processing are excellent, the error rate in medicine distribution is reduced, the problems of wrong distribution, missed distribution and frequent distribution in the medicine distribution process are reduced, and the medicine circulation efficiency is optimized.

The present application discloses a method, apparatus, device, medium, and product for three-dimensional modeling of an ore body based on contour lines. The method comprises: performing a three-dimensional morphological transformation on the second contour line based on a first centroid of the first contour line and a second centroid of the second contour line to generate a third contour line; determining characteristic points of the ore body contour line based on the closure type of the first contour line and the closure type of the second contour line; constructing a quality evaluation function for the ore body three-dimensional model based on at least one preset evaluation index; if a second evaluation function exists in an initial three-dimensional model set, decomposing the second evaluation function of the initial three-dimensional model set until the second evaluation function no longer exists in the initial three-dimensional model set, and generating a set consisting of multiple decomposed sub-evaluation functions; and generating a three-dimensional model of the ore body based on the set consisting of multiple sub-evaluation functions.

The invention provides a PCB defect detection method and device and electronic equipment, and the method comprises the steps: carrying out the multi-scale morphological transformation operation of a PCB gray image after collecting and obtaining the PCB gray image of a to-be-detected PCB, and obtaining a transformation image; and performing RGB pseudo color space mapping in combination with the transformed image and the PCB template drawing to generate a fused image. And processing the fused image by using a pre-trained detection model, and outputting defect information of the PCB. According to the scheme, after the multi-scale morphological transformation operation is carried out on the PCB gray level image, the RGB pseudo color space mapping processing is carried out, more comprehensive feature representation is obtained, deep analysis of a detection model is further facilitated, and high-precision recognition and positioning of PCB defects are achieved.

The invention provides a three-dimensional object generation method and device based on a large model, equipment and an intelligent agent, relates to the technical field of artificial intelligence, in particular to the technical fields of computer vision, deep learning, large models and the like, and can be applied to scenes of virtual reality, 3D clothing generation and the like. The three-dimensional object generation method based on the large model comprises the following steps: performing morphological transformation on an initial graph for a target object to obtain an object morphological graph representing that the object has a specified morphological; performing feature fusion on the object texture feature and the object form graph of the initial graph by using a visual large model to obtain a basic target object graph; performing multi-view conversion on the basic target object graph to obtain a plurality of expanded target object graphs related to a plurality of preset views; and generating a three-dimensional object based on the plurality of extended target object maps.

The present invention proposes a method for calculating the effective permeability of a digital core based on morphological transformation and graph theory algorithms, including: obtaining a three-dimensional digital image of a target digital core sample; extracting effective seepage pores of the three-dimensional digital image based on a morphological refinement method; constructing a topological graph network of the effective seepage pores; obtaining the maximum flow rate and flow distribution based on the minimum seepage resistance according to the topological graph network; and calculating the overall permeability of the target digital core sample according to the maximum flow rate and flow distribution. The present invention can extract the effective pore network in the seepage direction based on the three-dimensional microscopic image of the rock and soil material, apply the graph theory method to characterize the seepage capacity of each pore branch of the material and their mutual influence, and deduce its permeability. It has the characteristics of convenient application and comprehensive characterization.

The application discloses a signal fluctuation extraction method combining a Hadamard matrix and mathematical morphology, and comprises the following steps: determining the order m of the Hadamard matrix and the specific number l of rows to be selected according to signal characteristics and sampling accuracy; taking the lth row of the selected Hadamard matrix as a structure element g to perform mathematical morphology operation on an input signal f to obtain a signal fluctuation part and complete the extraction operation. According to the application, a certain row in the Hadamard matrix is selected as the structure element according to signal characteristics, and the order of the matrix is determined; the characteristics that the Hadamard matrix only takes values of 1 and -1 are utilized; the fundamental component in the signal is suppressed through the morphological operation; and the fluctuation part is extracted. The orthogonality of the Hadamard matrix is fully utilized, the Hadamard matrix is used as the structure element for the morphological transformation, the signal can be processed simply and quickly, and the characteristic information is extracted. The application of the mathematical morphology can accurately analyze the signal in the time domain.

The invention discloses a network advertisement release management method and system based on big data, and relates to the technical field of big data, the system comprises a management center, and the management center is connected with a network acquisition module, an intelligent processing module, a management analysis module and a comprehensive adjustment module; user instruction data and advertisement comprehensive data are acquired through a network acquisition module; the intelligent processing module performs image extraction and region inspection on the advertisement comprehensive data to obtain an advertisement feature map; the management analysis module performs morphological transformation on the advertisement feature map to obtain an advertisement feature signal, and sets a regional dynamic coefficient to perform filtering collection and feature filtering on the advertisement feature signal to obtain an advertisement filtering coefficient; performing morphological transformation and feature filtering on the user instruction data in a comprehensive adjustment module to obtain a user filtering coefficient, and performing shielding check on the user filtering coefficient to obtain an updated advertisement coefficient graph and a qualified matching interest spectrum; the accuracy and safety of network advertisement release are improved, and bad advertisements are effectively recognized.

The present invention relates to an equipment for cleaning and morphological transformation of wastes so that same are manageable, comprising at least one reactor (1) made up of several modules (2a, 2b, 2c, 2d) that can be disassembled and coupled together, each of which internally incorporates means to carry out a specific function that, at least, covers the function of loading, cleaning and morphological transformation of process wastes, discharge and dehydration, and control and electrical power. Preferably, the modules are four modules consisting of: a loading module (2a), a module that contains the process reactor body (2b), a discharge (2c) and dehydration module, and a control (2d) and power module and same are removable, are manufactured with measurements and exterior design meeting the ISO 20 and ISO 40 requirements stipulated for maritime containers or the like.