Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

32results about How to "High overlap rate" patented technology

Method for three-dimensionally segmenting insubstantial pulmonary nodule based on fuzzy membership model

InactiveCN102324109AHigh overlap rateError Volume Percentage LowImage data processingPulmonary noduleMedicine
The invention relates to a method for three-dimensionally segmenting an insubstantial pulmonary nodule based on a fuzzy membership model. The method comprises the following steps of: manually acquiring a region of interest, which includes the insubstantial pulmonary nodule, and performing subsequent processing in the region of interest; removing substantial parts which have larger gray values and comprise blood vessels, calcified points and the like by using threshold operation; establishing the fuzzy membership model of the insubstantial pulmonary nodule, calculating the membership, of each volume pixel, of the insubstantial pulmonary nodule according to the fuzzy membership model, and classifying the volume pixels based on the calculated membership by using a linear discriminant function; and for the insubstantial pulmonary nodule which is connected with the blood vessels, removing the blood vessels by using a Hessian matrix characteristic value, and thus obtaining a final segmentation result by using a three-dimensional connected region mark. Compared with other domestic and foreign methods for segmenting the insubstantial pulmonary nodule in recent years, the method for three-dimensionally segmenting the insubstantial pulmonary nodule based on the fuzzy membership model has the advantage that: the segmentation accuracy of the insubstantial pulmonary nodule is effectively improved.
Owner:UNIV OF SHANGHAI FOR SCI & TECH

Information classification method and device

The invention provides an information classification method and device. The method comprises the following steps of: obtaining a plurality of example feature tags and obtaining a relationship between each example feature tag and a to-be-classified subject directory; carrying out word segmentation on a plurality of to-be-classified sentences so as to obtain a to-be-processed word set; carrying out similar word replacement processing on to-be-processed words to obtain an updated word set; generating a to-be-classified feature tag according to the frequency of a first word combination included in each to-be-classified sentence in the updated word set; calculating a maximum semantic similarity between the to-be-classified feature tag and the plurality of example feature tags, and when the maximum semantic similarity b is greater than or equal to a preset similarity threshold value, taking an example feature tag corresponding to the maximum semantic similarity as a target feature tag of the to-be-classified feature tag; and labelling the to-be-classified sentence corresponding to the to-be-classified feature tag as a subject directory corresponding to the target feature tag. The method and device provided by the invention can be used for enhancing the information classification efficiency.
Owner:SHANGHAI XIAOI ROBOT TECH CO LTD

Image labeling method and device based on multi-model fusion, computer equipment and storage medium

The invention relates to the field of image detection, and the labeling effect is improved by fusing a binary classification result of a classification model based on a DenseNet network and a binary segmentation result of a segmentation model based on a Vnet network and an FPN network. The invention particularly discloses an image labeling method and device based on multi-model fusion, computer equipment and a storage medium. The method comprises the steps of acquiring a to-be-labeled image, and the to-be-labeled image is preprocessed to obtain a plurality of instance images; inputting each instance image into a classification model based on a DenseNet network for binary classification; splicing the binary classification results corresponding to the plurality of instance images to obtain classification result images; inputting each instance image into a segmentation model based on a Vnet network and an FPN network to carry out binarization segmentation; splicing the binarization segmentation results corresponding to the plurality of instance images to obtain a segmentation result image; calculating a binarized fusion image according to the classification result image and the segmentation result image; and extracting the contour of the fused image to mark the region of interest in the to-be-marked image according to the contour.
Owner:PING AN TECH (SHENZHEN) CO LTD

Order grouping processing method for personalized customized furniture

The invention belongs to the technical field of furniture processing and system planning, and particularly relates to an order grouping processing method for personalized customized furniture. According to the multi-order personalized customized furniture production system, the order classification and gathering, part marking, part clustering and grouping, part sorting according to orders and part packaging according to orders are carried out in sequence, and the purpose that multi-order personalized customized furniture can be integrally and efficiently machined and produced is achieved. The method has the following advantages that 1, order products are divided into parts, the parts are produced in groups according to a plurality of division standards, and it is guaranteed that when the parts in the same group are produced, the stack cutting rate is high, the raw material plate utilization rate is high, and the overall production efficiency is high; 2, the processing cycles of the groups are reasonably matched, and the whole processing cycle of all orders is shortened; and 3, the overall planning of part grouping processing is reasonable and efficient, the subsequent sorting and packaging operation is simple and convenient, and finally finished orders are low in cost, high in quality and short in delivery time.
Owner:DEHUA TB NEW DECORATION MATERIAL CO LTD +1

Steel bar mechanical connecting device

The invention provides a reinforcing steel bar mechanical connecting device which is used for connecting a first reinforcing steel bar and a second reinforcing steel bar which are oppositely arranged, a lengthened reinforcing steel bar wire head is machined at the end of the first reinforcing steel bar, and a reinforcing steel bar wire head is machined at the end of the second reinforcing steel bar. The reinforcing steel bar mechanical connecting device comprises a threaded sleeve and a connecting sleeve, an internal thread of the threaded sleeve and a reinforcing steel bar wire head of a second reinforcing steel bar can form second threaded connection, and an internal thread at one end of the connecting sleeve and a lengthened reinforcing steel bar wire head of a first reinforcing steel bar can form first threaded connection. The internal thread at the other end of the connecting sleeve can form third threaded connection with the external thread of the threaded sleeve; a protruding shoulder is formed at the end, close to the second steel bar, of the threaded sleeve. According to the invention, a larger thread pair axial adjusting gap is formed by three pairs of matched threads, so that the probability of superposition of spiral tracks is greatly improved, and the connection of reinforcing steel bars becomes very convenient and rapid.
Owner:CENT RES INST OF BUILDING & CONSTR CO LTD MCC GRP +1

Method for three-dimensionally segmenting insubstantial pulmonary nodule based on fuzzy membership model

InactiveCN102324109BHigh overlap rateError Volume Percentage LowImage data processingPulmonary noduleMedicine
The invention relates to a method for three-dimensionally segmenting an insubstantial pulmonary nodule based on a fuzzy membership model. The method comprises the following steps of: manually acquiring a region of interest, which includes the insubstantial pulmonary nodule, and performing subsequent processing in the region of interest; removing substantial parts which have larger gray values and comprise blood vessels, calcified points and the like by using threshold operation; establishing the fuzzy membership model of the insubstantial pulmonary nodule, calculating the membership, of each volume pixel, of the insubstantial pulmonary nodule according to the fuzzy membership model, and classifying the volume pixels based on the calculated membership by using a linear discriminant function; and for the insubstantial pulmonary nodule which is connected with the blood vessels, removing the blood vessels by using a Hessian matrix characteristic value, and thus obtaining a final segmentation result by using a three-dimensional connected region mark. Compared with other domestic and foreign methods for segmenting the insubstantial pulmonary nodule in recent years, the method for three-dimensionally segmenting the insubstantial pulmonary nodule based on the fuzzy membership model has the advantage that: the segmentation accuracy of the insubstantial pulmonary nodule is effectively improved.
Owner:UNIV OF SHANGHAI FOR SCI & TECH

A lysosome-targeted hypochlorous acid molecular fluorescent probe and its preparation method and application

The invention discloses a lysosome targeted fluorescence probe for detecting hypochlorous acid molecules, as well as a preparation method and application thereof, and belongs to the technical field of analytical chemistry. The molecular formula of the fluorescence probe is C37H35N5O5S, with a structure represented by formula I shown in the description. The synthesis of the probe includes four steps, and the after-treatment process is relatively simple; the selective quick detection of the hypochlorous acid molecule probe is achieved, the selectivity is good, and the capability of resisting interference from other molecules is strong; in addition, the change in color of the solution can be observed with the naked eyes, and the change in fluorescence color can also be observed under an ultra-violet lamp, therefore, the fluorescence probe for detecting hypochlorous acid molecules is one with the chromogenic sensing function, can be applied to detection of hypochlorous acid in lysosome in the cells of the biological system, and can be used as a probe for detecting hypochlorous acid in lysosome in the cells. The lysosome targeted fluorescence probe for detecting hypochlorous acid molecules, provided by the invention, is a simple, quick and sensitive reagent for detecting the hypochlorous acid molecules, and has a wide application prospect in the field of biomolecule detection.
Owner:UNIV OF JINAN

Multi-primary-color LED light-emitting system

The invention relates to the technical field of LED illumination, and provides a multi-primary-color LED light-emitting system, which comprises a multi-channel power supply control module, light-emitting modules, a sensor and data operation module and a light uniformity control module, and is characterized in that the light-emitting modules are independently controlled by the multi-channel power supply control module through current change, the sensor and operation module can calibrate each light-emitting module by controlling the multi-channel power supply module to ensure that the spectrum of the device can coincide with a standard spectrum, and the light-emitting module comprises four single-color light-emitting modules with different colors. According to the invention, the different light-emitting modules are adopted for cooperative use so as to improve the light-emitting efficiency, the spectrum coincidence rate is improved based on mixing of the multiple different light-emitting modules, the spectrum of a T84 standard light source can be achieved through the multi-primary-color LED, and the LED light source has the advantages of environmental protection, low energy consumption, variable volume and the like, and is suitable for wide application.
Owner:XUYU OPTOELECTRONICSSHENZHEN CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products