111results about How to "Does not affect detection accuracy" patented technology

A urine comprehensive test method is provided, which is to combine three urine test methods comprising the urine dipsticks analysis, the flow cytometer urine sediment analysis and the microscopic examination on urine sediment. First, test the urine by the urine dipsticks analyzer and the flow cytometer urine sediment analyzer; second, judge if the microscopic examination under the doctor's advice is needed if the urine is tested to be the patient suffered from renal diseases; third, make a smart judgment to the test result of the flow cytometer urine sediment analysis; finally, make comprehensive analysis to the test result of the urine dipsticks analysis and the flow cytometer urine sediment analysis to see if the microscopic examination is needed on he urine sediment. The method can fast and correctly determine the partial important samples needed for manual urine sediment check by the microscopic examination, which saves the human and material resources with reliable test result, and obviously improve the efficiency of the urine test without any influence on the test accuracy.

The invention discloses a method for detecting wireless sensor network sparse events based on compressed sensing and the game theory, which belongs to the field of wireless communication and aims to solve the problem that excessively intensive sensor nodes randomly released in the wireless sensor network probably cause communication interface but sparse sensor nodes probably cause detection leak.The method disclosed by the invention comprises the following steps: (I) dividing M sensor nodes randomly released in the network system into a layers according to the thought of the game theory; (II) determining to activate one or more layers of sensor nodes according to the number (K) of the current events; (III) receiving a data vector y by a data terminal of the network system, and obtaining a measurement matrix [phi]P*N according to the detection process; and (IV) obtaining the specific distribution vector E of K happening events in N event sources by use of a greedy sparse event detection algorithm.

The invention relates to an ultrasonic phased array imaging detection method for steam turbine blade root bolt holes. The detection method comprises the following steps that a first phased array probe is arranged on an inner arc side shoulder on the air inlet side of a blade root, and the air outlet side of the front fork tooth bolt hole and the air outlet side of the rear fork tooth bolt hole are detected; a second phased array probe is arranged on an outer arc front side shoulder on the air outlet side of the blade root, and the air inlet side of the front fork tooth bolt hole is detected; a third phased array probe is arranged on the outer arc rear side shoulder of the air outlet side of the blade root, and the air inlet side of the rear fork tooth bolt hole is detected. The ultrasonic phased array imaging detection method for the steam turbine blade root bolt holes has the advantages that the blade root of a steam turbine does not need to be demounted and mounted, and thus the assembling cost and the time cost of halt operation are saved while the detection precision is not affected. After parameters of a phased array detector are adjusted and stored, a detection result can be obtained without moving of the probes or with little moving of the probes after the phased array probes are attached to a workpiece, the detection efficiency is high, and time cost is saved.

The invention relates to an image processing technology, is applied to the field of smart medical treatment, and discloses an abnormal cell automatic labeling method. The method comprises: performingGaussian convolution smoothing processing on a cell pathology picture to obtain an image pyramid; performing detection fitting on the image pyramid through a Hough transform circle detection method toobtain a low-power fitting region of interest; mapping the low-power fitting region of interest to the acquired cell pathology picture to generate a fitting high-power image; segmenting a region of interest in the fitting high-power image to generate a segmented high-power image; labeling and cutting the segmented high-power image through an adaptive threshold segmentation algorithm to obtain anabnormal cell labeling set; and mapping the abnormal cell labeling set to the cell pathology picture to obtain an abnormal cell labeling picture. The accuracy of abnormal cell labeling is improved, and the calculation and storage pressure is reduced. In addition, the invention also relates to a blockchain technology, and the abnormal cell label set can be stored in a blockchain.

The invention provides a multi-station detection device based on automatic control, belongs to the technical field of detection devices, and aims to solve the problem that errors are easy to generate after a servo motor or other angle motors rotate in one direction for a long time when a multi-station turntable in the existing multi-station detection device rotates. The device comprises a workbench. The upper part of the left side of the workbench is provided with a detection member through a pillar, and the middle side of the upper part of the workbench is provided with a multi-station turntable. The multi-station rotating disc comprises a supporting shaft sleeve and a worm wheel, and a rotating shaft is arranged in the center of the bottom end face of the multi-station rotating disc. After the worm rotates three circles anticlockwise, because the transmission ratio between the worm and the worm gear is 18: 1, the worm gear drives the multi-station turntable to rotate one sixth circle, namely 60 degrees, so that the rotation angle of the multi-station turntable does not generate errors, the detection precision of a detection piece on the multi-station detection device is not influenced, and the reliability of the multi-station detection device in use is greatly improved.

The invention relates to a cigarette automatic detection method based on deep learning in a monitoring scene, and the method comprises the steps: firstly carrying out the overturning, zooming and smoothing of a cigarette data set photographed and downloaded from a network, obtaining a bigger data set, training the data set based on a YOLOv3 deep learning network, and forming a template library; performing corresponding image enhancement processing on the to-be-detected image or video frame by using an image enhancement method; carrying out image segmentation on the large-size image, cigarettesor people with cigarettes in the image are separated out, and the time needed by detection is shortened; then pre-generating prediction boxes on the image to be detected, and comparing each prediction box with a pre-trained template library; and finally, selecting a prediction box higher than a preset threshold value from the detection confidence coefficients of all the prediction boxes, and determining the prediction box as a target object. After the whole image of the current frame is scanned, all detected targets are marked and displayed on the image, and cigarette detection is completed.The method can effectively improve the detection accuracy and shorten the detection time.

Embodiments of the invention provide a living body detection method and device and electronic equipment. The method comprises the steps of extracting spatial features and time features of multiple frames of to-be-detected face images; inputting the spatial features and the time features into a first convolutional neural network model, and obtaining low-dimensional spatial features and low-dimensional time features output by a global pooling layer in the first convolutional neural network; inputting the multiple frames of face images into a second convolutional neural network model, and obtaining biological motion features output by a full connection layer in a second convolutional neural network; and calculating a living body detection result of the multiple frames of face images accordingto the low-dimensional spatial features, the low-dimensional time features and the biological motion features.

The invention discloses a high-sensitivity solid-state color image sensor. Particularly, a large-area MOS (Metal Oxide Semiconductor) capacitor is used as a photoelectric conversion region, the generated and collected photoelectrons are transferred to a channel region arranged below the grid electrode of an adjacent small-sized MOSFET (Metal-Oxide-Semiconductor Field Effect Transistor) storage, furthermore, the transferred photoelectrons are injected into a storage layer of the storage to enable the threshold voltage of the storage to change, and finally, the intensity of the detected light is determined through reading the drain current of the storage. Pixel units of the color image sensor are as follows: each pixel unit of the color image sensor is composed of three pixel subunits which have the same structures and are respectively red, green and blue, and each of the red, green and blue pixel units is respectively composed of one MOS capacitor and one MOSFET structural storage tube. A manufacturing process of the color image sensor is completely compatible with a CMOS (Complementary Metal-Oxide-Semiconductor) process; and the color image sensor is matured in process, low in cost and easy to achieve.

A detection apparatus of long stroke leading screw installation precision and an application method thereof relate to the detection apparatus of a driving leading screw of a numerical control turret punch and a numerical control laser cutting machine workbench and the application method thereof. The detection apparatus of the long stroke leading screw installation precision and the application method thereof are provided. By using the apparatus and the method of the invention, under the condition of conforming to a natural law, detection data can be accurately obtained and the product installation precision can be increased. The leading screw is flexibly connected on a rack. A pair of Y direction guide rails which is parallel to the leading screw is arranged on the rack. A leading screw nut is connected on the leading screw. The detection apparatus comprises a portal frame, an X axis guide rail, an X axis slide block, a table 1 and a table 2. The application method of the invention comprises the following steps: 1) Installing the detection apparatus on the pair of the Y direction guide rails; 2) Moving the leading screw nut to a middle position of the leading screw; 3) Overcoming deflection; 4) Detecting one end; 5) Detecting the other end; 6) Finishing.

The invention relates to detection equipment, in particular to ceramic tile quality automatic detection equipment. The technical problem to be solved is how to design the ceramic tile quality automatic detection equipment which can replace manpower to detect the quality of ceramic tiles, is labor-saving and does not influence the detection accuracy. The tile quality automatic detection equipment comprises a base, wherein four vertical plates are fixedly connected to one side of the base at intervals; and first small supports which are symmetrically and fixedly connected to the middle of the side, away from the vertical plates, of the base. Ceramic tiles are placed on a left belt, a gear motor is started to rotate forwards, the left belt can drive the ceramic tiles to move rightwards, a first sliding rod drives the ceramic tiles to move upwards to make contact with a suction cup to be sucked and fixed, and when the suction cup loosens the ceramic tiles, the ceramic tiles fall onto the left belt to be subjected to quality detection. Thus, a rubber hammer does not need to be continuously waved by people to beat the ceramic tiles, the labor is saved, and the detection accuracy is not influenced.

The invention discloses a phased array detection method for a fillet weld of a pipe base. The method comprises the following steps: drawing weld graphic expressions corresponding to different angles; connecting a probe with a phased array ultrasonic test instrument; converting an ultrasonic beam into a scanning image by the phased array ultrasonic test instrument; introducing the weld graphic expressions corresponding to different angles into the phased array ultrasonic test instrument, converting the weld graphic expressions to a corresponding angle following the probe once moving the probe for a certain angle while detecting and then correspondingly matching the introduced graph with a practical S scanned image, thereby guaranteeing one-to-one correspondence of the detected signal wave and the weld graphic expressions; if the position of a generated echo is overlapped with a workpiece loading graph, confirming the echo as the echo generated at a workpiece boundary; if not, confirming the echo as the echo generated by defect. The detection data can be acquired after the probe is adhered to the workpiece and is used for scanning from a starting point to a destination, the detection efficiency is high and the time cost is saved. The defects of the fillet weld of the pipe base can be detected and the omission ratio is lower.

The invention provides a high-side current sampling voltage expansion circuit which comprises a sampling resistor, a high-side current detection chip, a voltage dropping resistor, an MOS tube, a voltage stabilizing diode and a current limiting resistor, the two ends of the sampling resistor are connected with the input end of the high-side current detection chip, the sampling resistor is arranged on the high side, namely the positive electrode, of an output loop, the current is output to a load through the sampling resistor; the output end of the high-side current detection chip is connected to one end of the dropping resistor, and the other end of the dropping resistor is connected with the source electrode of the MOS tube; the grid electrode of the MOS tube is connected with one end of the current-limiting resistor, one end of the current-limiting resistor is further connected with the anode of the voltage-stabilizing diode, and the cathode of the voltage-stabilizing diode is connected with the anode of the circuit; the other end of the current-limiting resistor is grounded; and the drain electrode is used as a current output end.