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

84results about How to "Less intervention" patented technology

Environment noise identification classification method based on convolutional neural network

InactiveCN109767785AUniversalSolve problems that are easy to fall into the optimal solutionSpeech analysisMel-frequency cepstrumEnvironmental noise
The invention relates to an environment noise identification classification method based on a convolutional neural network. The method comprises the following steps of: S1, extracting natural environment noise, and editing the natural environment noise into noise segments with duration of 300ms to 30s and a converted frequency of 44.1kHz; S2, carrying out short time Fourier transformation on the noise segments, and converting a one-dimensional time-domain signal into a two-dimensional time-domain signal to obtain a sonagraph; S3, extracting a MFCC (Mel Frequency Cepstrum Coefficient) of the signal; S4, forming a training set with 80% of all the noise segments and forming a testing set with the residual 20% of all the noise segments; S5, carrying out noise classification by a convolutionalneural network model; and S6, training a classification model by the training set, and verifying accuracy of the model by the testing set so as to complete environment noise identification classification based on the convolutional neural network. According to the invention, the sound segments are input, sound feature information is extracted, an output is a classification result, and automatic extraction on the sound feature information can be implemented.
Owner:HEBEI UNIV OF TECH

Method, system and software for correcting image defects

A method, system and software are disclosed for correcting defects formed in a physical medium of an original image. Multiple scans of the original image are recorded, where the multiple scans have different properties. For example, the angle of the light incident to the physical medium or the properties of the light may be changed between scans of original image. The multiple scans can be used to generate a reference image from which defect corrections are made. Alternatively, a reference image can be generated directly from the original image. The multiple scans can also be used to determine the degree of defectiveness and / or an estimate of the signal strength of each portion of the original image. A decision is made on whether or not an image portion having one or more defects should be corrected, where the decision can be based on an evaluation of the potential benefit compared to the potential damage caused by correction of an image portion. In one embodiment, the potential benefit is proportional to the degree of defectiveness, while the potential damage is proportional to the image information that may be removed by correction. If the decision is made to correct an image portion, a variety of methods may be implemented to correct the image portion, such as cloning information from non-defective image portions surrounding the defective image portion. The present invention finds particular use in image capturing systems, such as flatbed scanners, photocopiers, facsimile machines, and the like.
Owner:KODAK ALARIS INC

Method for extracting contour of image of printed circuit board (PCB)

The invention aims to provide a method for extracting a contour of an image of a printed circuit board (PCB). By the method, the defect of inaccuracy in extraction of the contour of the image of the PCB in the conventional contour extraction method is overcome, the accuracy and stability of contour detection are improved, and working efficiency is improved. The method comprises the following steps of: 1) acquisition of an original image of the PCB; 2) Gaussian Laplacian operator processing: processing the original image by using a Gaussian Laplacian operator to obtain a processed Gaussian Laplacian image; 3) gradient operator mutant processing: processing the original image by using a gradient operator to obtain a gradient image which is subjected to mutant processing through the gradientoperator; 4) processing the original image by using high and low threshold values to obtain a binary image; 5) establishing coordinate graphs of sub-pixel contour points, determining the pixel position of the contour according to the boundary of the binary image, and thus obtaining the coordinates of the sub-pixel contour points according to a Gaussian Laplacian value, a pixel value and a gradient value in the corresponding direction of the contour; and 6) connecting the sub-pixel contour points to form the contour, and connecting the sub-pixel contour points into a set in a certain sequence according to the coordinates of the sub-pixel contour points, wherein the coordinates are obtained in the step 5).
Owner:浙江欧威科技有限公司

Mechanical, fully-automatic and intelligent vacuum packaging machine for non-particulate materials

A mechanical, fully-automatic and intelligent vacuum packaging machine for non-particulate materials comprises a chassis, a feed hopper, a vibration feeding mechanism, a metering mechanism, a bag supplying device, a bag opening device, a bag filling mechanism, a bag sealing and cutting mechanism and a vacuum sealing device. A vacuum packaging device comprises a left cavity and a right cavity, wherein the left cavity and the right cavity are drawn together to form a vacuum chamber; a sealing component used for sealing a packaging bag under the conditions of high temperature and hot pressing isarranged at the upper side of an inner cavity of the vacuum chamber; the middle part of the inner cavity of the vacuum chamber is provided with an anti-sticking positioning device used for positioning and clamping the packaging bag; the anti-sticking positioning device comprises a frame body seat; the two lower side parts of the frame body seat are respectively provided with a positioning shaft in a penetrating way; a pair of supporting plates that can be drawn together in a crossing way so as to support the lower part of the packaging bag are articulated on the two positioning shafts; channels for the crossing of the two supporting plates are arranged on the supporting plates at intervals; the supporting plates are positioned under the frame body seat; and a pair of clamping plates that can be drawn together oppositely so as to clamp the upper part of the packaging bag are articulated on the two positioning shafts in an inner cavity of the frame body seat.
Owner:李康彪 +1

Device and method for automatically detecting and adjusting gluing position of tipping paper of cigarettes

The invention discloses a device for automatically detecting and adjusting a gluing position of tipping paper of cigarettes. The device comprises a detection module, an automatic adjusting device, a man-machine interface, a state indicator, a power module and a master control module, wherein the master control module controls the automatic adjusting device to adjust the left-right offset of a paper guide block according to glue position offset transmitted by the detection module and controls the gluing device to operate. The method disclosed by the invention comprises the following steps: shooting and sampling by a high-speed camera, and processing images by an image processor so as to obtain the glue position offset; and judging whether the glue position is qualified by the master control module according to the glue position offset, enabling the gluing device to continuously operate when the glue position is qualified, and transmitting an adjusting instruction to the automatic adjusting device and corresponding adjusting the paper guide block when the glue position is unqualified. According to the device and method disclosed by the invention, the offset occurring at the gluing position of the tipping paper can be automatically adjusted and corrected, all the processes are automatically monitored and executed by the master control module, the automation level is improved, the adjusting precision is guaranteed, and wastes are reduced.
Owner:CHINA TOBACCO GUANGXI IND
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