Abstract:
The present disclosure relates to an image data classification method, device and system, and relates to the field of computer technology. The method includes: inputting test image data into a neural network model trained by using an original training sample set for classification, and determining an image type to which the test image data belongs and a membership probability of the image data belonging to the image type; establishing an easy-to-classify data set, according to test image data with a membership probability greater than a first threshold; adding test image data in the easy-to-classify data set that has a classification accuracy rate less than or equal to a second threshold and a correct classification result to the original training sample set to generate an augmented training sample set; and using the augmented training sample set to train the neural network model so as to determine an image class
Abstract:
The application provides an image detection method, an image detection apparatus, and a patterning control method, the image detection method including: identifying an input image to obtain image feature data of the input image; comparing the image feature data with preset image feature data in a preset image feature database to obtain deviation data of the input image; wherein the input image is a pattern image of a patterned structure. By intelligently detecting the pattern image of the patterned structure, the accuracy of the detection is improved, thereby reducing the labor input cost.
Abstract:
The present disclosure provides a bill of material conversion method, an electronic apparatus and a non-transitory computer-readable storage medium. A bill of material conversion method, including steps S1 to S4: Step S1: obtaining an unprocessed first node in a first bill of material; Step S2: according to a preset correspondence, creating a second node corresponding to a second bill of material according to the obtained first node, and storing the created second node into a list; Step S3: determining whether the first node currently obtained is a last first node of the first bill of material; in response to the first node currently obtained not the last first node of the first bill of material, repeatedly performing steps S1 through S3; in response to the first node currently obtained being the last first node, performing step S4: converting respective second nodes in the list into the second bill of material.
Abstract:
A measurement assembly includes a first light emitter set including a plurality of light emitters arranged at equal intervals in a first direction, the light emitters emitting lights with frequencies different from one another; a light receiver disposed on an object under measurement and configured to receive incident lights from the light emitter set; and a position determination unit configured to determine a first current position of the object under measurement according to frequencies of incident lights currently received by the light receiver from the first light emitter set.
Abstract:
The present disclosure provides an electricity generating device, an electric source and a sensor. The electricity generating device comprising: a magnet array, and an inductive body having one or more metal wires, the magnet array comprising a plurality of magnets, wherein the inductive body and the magnet array are movable relative to each other; and a magnet mounting structure, on which the magnet array is mounted, wherein the inductive body is fixed to the magnet mounting structure, and the magnet array is movable relative to the magnet mounting structure. The electricity generating device, the electric source and the sensor provided by the present disclosure have simple structures, are easy to manufacture, achieve high efficiency of electricity generation, and are easy to carry.
Abstract:
The present invention provides a monitoring method and a monitoring device, belongs to the field of electronic monitoring technology, and can solve the problem that useless video data occupies storage space and key video cannot be extracted quickly when an event occurs in the existing monitoring device. The monitoring method of the present invention comprises: determining whether or not a first image is changed; generating a storage instruction if it is determined that the first image is changed; collecting and storing images of external environment according to the storage instruction; obtaining a second image according to the collected images of external environment; determining whether or not the second image is changed; and stopping storing images of external environment if it is determined that the second image is not changed.
Abstract:
This disclosure relates to a liquid crystal display and a display device. A plurality of photosensitive detectors is arranged in the frame region of the liquid crystal display panel. Light intensity distribution in the display region is estimated by a light intensity estimation module based on the light intensity detected by each photosensitive detector. Light intensity in a position corresponding to each light emitting pixel of the backlight source is determined based on the light intensity distribution in the display region estimated by the light intensity estimation module. Depending on the determined light intensity in a position corresponding to each light emitting pixel of the backlight source, luminance of the light emitting pixel in this corresponding position is controlled by a backlight driving circuit.
Abstract:
The present invention discloses a touch identification device on the basis of Doppler effect, a touch identification method on the basis of Doppler effect and a touch screen, wherein the touch identification device comprises: a first transceiving module used for transmitting a first detection wave along a first direction and receiving a first feedback wave formed from the first detection wave after being reflected by a touch body; a second transceiving module used for transmitting a second detection wave along a second direction and receiving a second feedback wave formed from the second detection wave after being reflected by the touch body; and a calculation module used for calculating a moving speed and a moving direction of the touch body at the touch point according to the first detection wave, the first feedback wave, the second detection wave and the second feedback wave.
Abstract:
The present disclosure provides data processing methods and apparatuses, an electronic device and a storage medium. The method includes: obtaining a product sample set; obtaining combination features in specified dimensions of the product sample set by processing a second parameter based on a preset dimension reduction algorithm; obtaining influence scores respectively for the combination features in specified dimensions based on a first parameter and the combination features in specified dimensions; obtaining at least one combination feature ranked top by sorting the combination features based on the influence scores, and taking a raw parameter corresponding to the at least one combination feature as a cause of the product defect. In the embodiments of the present disclosure, combination features in R dimensions may be a combination of raw parameters having similarity such that similar parameters are associated while raw information of the product samples is retained, thus helping fast locating the cause of the product defect, and improving the detection efficiency.
Abstract:
A method and a device for processing product manufacturing messages, and an electronic device are disclosed. The method for processing product manufacturing messages includes: monitoring a plurality of product manufacturing messages; establishing a product defect analysis task queue based on the plurality of product manufacturing messages; distributing product defect analysis tasks to product manufacturing assisting devices based on the product defect analysis task queue, wherein the product defect analysis tasks include a task of identifying product defect content based on a defect identification model; wherein the product defect content includes any one or more of: product defect type, product defect location, and product defect size.