83 results about "Maximum Pixel" patented technology

The invention discloses a fluorescence in-situ hybridization image contour enhancement method based on illumination fusion and local binary, relates to the field of image processing, and solves the problems of different dye concentrations and the like due to image defects such as non-uniform local illumination and relatively large noise in an acquired image during existing tissue cell fluorescence image preprocessing. The method comprises the following steps: removing noise in an image by adopting a median filtering method, calculating a linear equation to obtain a texture weight of the image, performing analysis processing by utilizing the texture weight and a smoothing function to obtain a brightness image and a smooth image, and performing gray processing to obtain gray distribution information; adopting a local binary algorithm to select a coefficient, and performing enhancement processing on the image to obtain an illumination enhanced image; the contour feature image and the illumination enhancement image are subjected to weighted addition, eight neighborhoods around eight maximum pixel values are analyzed, an area with a high energy gradient is recognized through a piecewise linear function and a thermodynamic diagram, and a high-frequency signal area is the contour area of the fluorescence in-situ hybridization tissue cell image.

A display device includes, a backlight device, and a backlight control circuit. The backlight device includes a plurality of light sources configured to illuminate a display panel. The backlight control circuit is configured to apply a filter to a target part of the input image to generate a filtered image part. The target part of the input image is displayed in a corresponding region of the display panel illuminated by a target light source of the plurality of light sources. The backlight control circuit is further configured to control a luminance level of the target light source based on a maximum pixel luminance level of the filtered image part and a local average picture level (APL) of the filtered image part.

The invention relates to the field of image processing, in particular to a workpiece feature recognition method for a CNC machining center, and the method comprises the steps: obtaining the LAB value of each pixel point of a workpiece image to be machined and the gradient value of each pixel point, and traversing the pixel point distribution complexity of each neighborhood window of the pixel points, selecting a neighborhood window corresponding to the maximum pixel point distribution complexity as a target window of the pixel points, and taking the product of the calculated color difference and gradient difference between the pixel points and other pixel points in the target window and the window distribution complexity of the target window as the local saliency of the pixel points; screening all edge points based on the local saliency value to obtain a contour edge image; and performing matching in a workpiece database based on the contour image so as to match a corresponding processing procedure. According to the method, the edge points are screened in combination with the local significance of the pixel points and the optimal significance threshold, the contour edge of the workpiece can be extracted more accurately, and then the accuracy of workpiece feature recognition is improved.

The invention provides a method and a system for testing optical center deviation of a zoom camera. A calibration plate is arranged below a camera, the camera is progressively switched according to a preset step from high power to low power, and first images are respectively collected; performing threshold segmentation on the first image, extracting circular areas on four corners, and generating a second image sequence; overlapping the circular areas on the four corners corresponding to each second image in the second image sequence to generate a third image; calculating the circle center of the circular area in the third image, and sequentially connecting the circle centers of the circles with different multiplying powers at the same position and fitting the circle centers into a straight line; obtaining coordinates of intersection points between the straight lines; and based on the coordinates of the intersection point and the center coordinates of the first image, determining the maximum pixel offset of the optical center in the corresponding magnification range of the first image and the distance deviation of the optical center of the lens relative to the center of the CCD sensor, thereby facilitating deviation compensation and improvement during camera assembly and lens processing, and improving the optical performance of the camera.

The invention discloses a defect detection control method and system and a medium. The control method comprises the following steps: judging whether the mass center of a laser image belongs to a mass center threshold range or not; analyzing whether laser energy corresponding to the first normal signal belongs to an energy threshold range or not; a laser image corresponding to the second normal signal is collected, the maximum pixel value in each column direction is extracted, and a column maximum value collection curve is formed to reflect the brightness change trend in the row direction of the laser image; and analyzing whether a peak of which the continuous width exceeds a width threshold exists in the column maximum value collection curve, if so, controlling the focusing device to continue focusing, and if not, controlling the focusing device to finish focusing. According to the invention, the normal area and the discontinuous area of the object to be detected can be quickly and effectively identified, so that focusing can be quickly and accurately stopped for the discontinuous area of the object to be detected, the position of the object to be detected relative to focusing equipment does not need to be known in advance, and the application range is wider.

The invention relates to the technical field of remote sensing image on-orbit real-time processing, in particular to a low-redundancy-rate image segmentation method and system based on an FPGA, and the method comprises the steps: determining the maximum physical size of a target object; calculating a first maximum pixel value occupied by the target type object in the remote sensing image according to the maximum physical size of the target type object; performing correction calculation on the maximum physical size according to the side-sway angle during satellite imaging to obtain the maximum physical size of the target object after side-sway distortion is considered; calculating a second maximum pixel value occupied by the target type object in the remote sensing image according to the maximum physical size of the target type object after side-sway distortion is considered; taking the maximum value from the first maximum pixel value and the second maximum pixel value as an overlapping region setting value; setting an overlapping region setting value as a sliding window segmentation step length; and carrying out sliding window segmentation on the segmented sub-graphs according to the sliding window segmentation step length. According to the method and the device, the minimization of the overlapped region of the segmented sub-images is realized, the segmentation redundancy rate is reduced, and the data storage and transmission quantity is reduced.

The invention discloses a guided wave self-adaptive enhanced time reversal imaging method and system for vehicle structure damage and a computer program product, and belongs to the technical field of aircraft structure health monitoring. The envelope of the damage scattering signal is calculated through Shannon continuous complex wavelet transform and Hilbert transform, and m wave bands with the maximum peak value are selected as potential damage scattering signal wave bands; the damage factor of each potential wave band is calculated, the wave band with the maximum damage factor is a real damage scattering wave band, other signals are set to be zero, and therefore guided wave self-adaption enhancement is achieved, and the signal-to-noise ratio is increased; on the basis of extraction of a damage scattering wave band, a time reversal focusing imaging method is adopted, imaging results generated when all the sensors serve as excitation are superposed, and the point with the maximum pixel value is the damage position. The implementation process is accurate and efficient, and damage positioning can be achieved through the piezoelectric sensor monitoring network on the main load-bearing structure.

The embodiment of the invention discloses an image splicing method and device of a deviation rectification linear array camera, electronic equipment and a medium. The method comprises the following steps: enabling at least two line-scan digital cameras to directly face a checkerboard calibration plate for image acquisition to obtain target images acquired by the line-scan digital cameras respectively; for target images acquired by two adjacent linear array cameras, determining adjacent checkerboard demarcation points as feature points according to a pixel point with the maximum pixel gradient in the target images and pixel points adjacent to the pixel point with the maximum pixel gradient; and according to the image coordinates of the feature points in the target image and the plane coordinates of the feature points in a plane coordinate system established by taking the checkerboard calibration plate as a reference, determining a perspective transformation matrix for transformation between the image coordinates and the plane coordinates. According to the scheme, under the condition that the line-scan digital camera keeps a large view field range, the images of the line-scan digital camera are precisely spliced, and the fusion degree of the spliced images is improved.

The invention discloses a polyp image size estimation method and system based on a deep learning model. The method comprises the following steps: acquiring a plurality of image frames; the frame with the maximum pixel diameter is used as a representative frame; estimating a target polyp depth value by adopting a depth estimation model, and calculating a representative depth value by adopting a median-based mode; and calculating a product of the representative pixel diameter, the representative depth value and a given scale factor to obtain a size estimation value of the target polyp. According to the unified polyp size estimation method, a depth estimation model and a segmentation model are combined, and the requirement for clear calibration of a camera is eliminated by estimating an absolute depth size scale factor; meanwhile, a plurality of visual angles are collected and analyzed, and a frame capable of presenting the maximum apparent diameter is selected, so that the polyp cross section is measured through an approximately vertical visual angle, the influence caused by the angle problem is effectively solved, and more accurate and reliable polyp size measurement can be provided.

The invention discloses a partition backlight adjusting method and system, and the method comprises the steps: analyzing the background environment brightness and a frame image signal of an HUD display region, and enabling a system to judge whether to start a lowest backlight mode or not after the environment brightness is detected; in the lowest backlight mode, calculating the maximum pixel value of the sub-image in each subarea, and adjusting the backlight and pixel values of the subareas according to the maximum value; in the non-lowest backlight mode, backlight and pixel values of the partitions are determined directly according to the maximum pixel value of the frame image; and the system generates an image pixel compensation curve for each partition, and carries out filtering processing on the backlight value to obtain a filtered backlight value. The pixel value of each subarea is adjusted through the compensation curve and the filtered backlight value, and therefore it is ensured that the display effect is clear and visible under different environment brightness. Therefore, the interference of HUD light leakage at night and overhigh ambient brightness in daytime on display content is effectively relieved, the visual experience of a driver is improved, and the interference in driving is reduced.

The invention relates to the technical field of image processing, and provides an image rain removal method and system based on multi-scale prior injection, and the method comprises the steps: carrying out the subtraction of a gray image formed by a maximum pixel value and a minimum pixel value of a rainy day image along a channel dimension; extracting multi-scale potential background prior features of the initial rough rain-free image through a residual branch of a pre-trained U-Net network; under the guidance of the multi-scale potential background prior features, multi-scale rain stripe features of the rainy day image are extracted through a PITform branch, and first-scale decoder rain stripe features are obtained; and the image passes through a Tform module and a convolution module and then is added with a rainy day image to obtain a rain-removed image. According to the method, the U-Net network is adopted, the prior information is introduced into each scale layer, the network is guided to generate the rain-free image with rich texture details, accurate image recovery is realized, and the rain removal performance is improved.

A display device includes a backlight device and a backlight control circuit. The backlight device includes a plurality of light sources configured to illuminate the display panel. The backlight control circuit is configured to apply a filter to a target portion of an input image to generate a filtered image portion. A target portion of the input image is displayed in a corresponding area of the display panel illuminated by a target light source of the plurality of light sources. The backlight control circuit is further configured to control a brightness level of the target light source based on a maximum pixel brightness level of the filtered image portion and a local average image level (APL) of the filtered image portion.

The embodiment of the present invention proposes an image filtering method, apparatus, terminal device and storage medium, which relates to the field of image processing technology, and can dynamically adjust the filter kernel according to the local gradient structure of the image area where different pixels to be filtered are located, and retain the edge detail information of the image while filtering out image noise. It includes: for each direction of multiple directions where the pixel to be filtered is located, calculating the pixel difference of the pixel to be filtered relative to the adjacent pixel in this direction; according to the pixel difference of the pixel to be filtered in multiple directions, obtaining the target direction corresponding to the maximum pixel difference of the pixel to be filtered; controlling the filter kernel of the pixel to be filtered to stretch along the orthogonal direction of the target direction, obtaining the pixel values ​​of the sample pixel points around the orthogonal direction of the target direction, and filtering the pixel to be filtered.

The invention provides a vehicle length determination method and apparatus, a terminal device and a storage medium. The method comprises the steps of obtaining a side image of a to-be-processed vehicle; determining the horizontal maximum pixel length of the side surface of the to-be-processed vehicle according to the side surface image of the to-be-processed vehicle; the vehicle length of the to-be-processed vehicle is determined according to the horizontal maximum pixel length of the side face of the to-be-processed vehicle and preset conversion parameters, the preset conversion parameters are determined according to the side face images of the multiple reference vehicles and the standard vehicle lengths corresponding to the reference vehicles, and the vehicle types of the reference vehicles are the same. Therefore, the conversion relation between the pixel length in the image and the actual vehicle length is obtained by obtaining the preset conversion parameter, so that after the horizontal maximum pixel length of the side face of the to-be-processed vehicle is obtained, the vehicle length of the to-be-processed vehicle can be obtained in combination with the horizontal maximum pixel length and the preset conversion parameter; therefore, the vehicle length data of the vehicle can be determined without camera calibration, and the method is simple and effective.

The embodiment of the invention provides a pleural effusion grading model training method, a pleural effusion grading method and electronic equipment, and relates to the technical field of image processing. The method comprises the following steps: acquiring a pleural effusion ultrasonic image, inputting the pleural effusion ultrasonic image into a pre-trained pleural effusion grading model to obtain an effusion binary mask, performing template matching on the pleural effusion ultrasonic image, identifying at least two reference scale marks with a known physical distance marked on a scale in the image, and determining the pleural effusion grading model according to the identified reference scale marks. Determining the pixel coordinates of each reference scale in the image, performing connected domain analysis on the binary mask, extracting a connected domain with the maximum longitudinal extension length as a target effusion region, calculating the maximum pixel length of the target effusion region in the longitudinal axis direction of the image, and determining the target effusion region according to the physical spacing, the two pixel coordinates and the maximum pixel length. The physical depth of the pleural effusion is calculated, and clinical grading is conducted. Therefore, evaluation from the pleural ultrasound image to the physical depth of the effusion can be realized.

According to an exemplary embodiment of the present disclosure, a method, device, medium and product for determining the radius of corneal curvature are provided. The method includes: determining the minimum pixel number range and the maximum pixel number range occupied by the outer diameter of the backlight ring based on multiple first keratometer images with the minimum corneal curvature radius and multiple second keratometer images with the maximum corneal curvature radius; determining the backlight ring area range based on the maximum pixel number range and the preset offset; collecting human eye images; performing circular detection and fitting on the human eye images based on the maximum pixel number range and the minimum pixel number range to obtain the number of pixels occupied by the outer diameter of the backlight ring in the human eye image; and determining the corneal curvature radius of the human eye image based on the number of pixels occupied by the outer diameter of the backlight ring obtained by the preset formula. In this way, the calculation accuracy of the corneal curvature radius can be improved.

To provide an image display device capable of displaying an image with high picture quality even if a pixel of high luminance that an original image does not have is included in a frame of a video signal.SOLUTION: A maximum luminance information acquisition section 1 extracts meta data indicating a maximum luminance value and acquires maximum luminance information. A cumulative histogram generation section 10 divides a range from lightness corresponding to a minimum pixel value determined by a bit number of a video signal to lightness corresponding to a maximum pixel value into a plurality of lightness levels and, while defining lightness of a pixel having lightness equal to or higher than a threshold which is set based on lightness indicated by the maximum luminance information as 0, generates a cumulative histogram indicating a ratio of cumulative pixel numbers equal to or lower than each lightness level on one or more frames basis. A gradation curve setting section 4 sets a gradation curve formed from an input pixel value and an output pixel value in accordance with a lightness level having maximum lightness indicated by the cumulative histogram, and the input pixel value is converted into the output pixel value in accordance with the gradation curve and supplied to a drive section 5.SELECTED DRAWING: Figure 1

A decoding device includes a transformer sets a decoded luminance component of a prediction target block to the same number of samples as that of the chrominance component corresponding to the decoded luminance component of the prediction target block and generates a luminance reference signal. A specificator specifies luminance pixels having minimum and maximum pixel values of the decoded luminance component adjacent to the decoded luminance component of the prediction target block, respectively, outputs luminance pixel values obtained from specified luminance pixels, and outputs chrominance pixel values from pigment pixels corresponding to the luminance pixels. A derivator derives a linear prediction parameter from the two pixel values and a linear prediction model. A chrominance linear predictor obtains chrominance prediction signal applying the linear prediction model based on the linear prediction parameter to the luminance reference signal. The chrominance prediction and residual signals are summed to generate a reconstructed chrominance signal.

The object of the present invention is to provide an X-ray inspection apparatus that can adjust the sensitivity without passing an article through it multiple times. [Solution] The X-ray inspection apparatus 10 comprises a conveyor 12, an X-ray irradiator 13, an X-ray line sensor 14, a foreign object inspection unit 21b, an HDD 25, a controller 20, and a monitor 30. The foreign object inspection unit 21b performs predetermined processing on the X-ray transmission image of the item G, which is generated based on the detection result of the X-ray line sensor 14, to create a judgment image. Furthermore, the foreign object inspection unit 21b determines whether the item is good or bad by comparing the pixel value indicated by each pixel of the judgment image with a preset threshold. The HDD 25 stores the maximum pixel value Pmax, which is the maximum value of the pixel, as a feature quantity. The controller 20 aggregates the maximum pixel value Pmax to generate statistical data 33. The monitor 30 displays the statistical data 33.

This invention discloses a method and system for polyp image size estimation based on a deep learning model. The method includes: acquiring multiple image frames; using the frame with the largest maximum pixel diameter as a representative frame; estimating the depth value of the target polyp using a depth estimation model; calculating a representative depth value using a median-based approach; and calculating the product of the representative pixel diameter, the representative depth value, and a given scaling factor to obtain the estimated size of the target polyp. This invention provides a unified polyp size estimation method that combines a depth estimation model and a segmentation model. By estimating the absolute depth-size scaling factor, it eliminates the need for explicit camera calibration. Simultaneously, by acquiring and analyzing multiple viewpoints and selecting the frame that presents the largest apparent diameter, it measures the polyp cross-section from an approximately vertical viewpoint, effectively solving the influence of angle issues and providing more accurate and reliable polyp size measurements.

The invention discloses a line scanning imaging device, a correction method of the line scanning imaging device and a control panel of the line scanning imaging device. The correction method comprises the following steps: obtaining a maximum pixel brightness value in a plurality of first images generated by a plurality of line scanning camera modules when a light source is started, wherein the plurality of first images are spliced in a scanning line extension direction; obtaining a plurality of second images generated by the plurality of line scan camera modules when the light source has a predetermined light intensity, the light intensity of the light source when the maximum pixel brightness value is less than or equal to a first predetermined brightness value being the predetermined light intensity, the brightness value of each pixel in the second image of each line scanning camera module is smaller than or equal to the first preset brightness value; obtaining a plurality of third images generated by the plurality of line scan camera modules when the light source is turned off; and generating correction information according to the plurality of second images and the plurality of third images. The correction method can improve the accuracy of image correction.

Disclosed is a method for detecting a line in an image or a video. The method includes smoothing the image, selecting an area in which a line is to be detected, determining a center pixel in the selected area, applying a window centered on the center pixel, detecting a sum of gradient angle differences of pixels surrounding the center pixel, classifying the center pixel determined as the line candidate into a ridge or a valley, and eliminating a non-maximum pixel.

The present invention discloses a smoothing method for a suspension crossbeam after profile optimization, including: S1. Defining an optimization area on the digital model of the suspension crossbeam, and conducting profile optimization design on the stiffeners within the optimization area; S2. Obtaining the geometric features of the plane where the optimization area is located and converting them into a binary image; S3. Calculating the maximum pixel distance H between adjacent isolated stiffeners X in the binary image; S4. Performing a first morphological operation on the isolated stiffeners X in the binary image using a circular structural element J1 to obtain the overall stiffeners Y; S5. Extracting the central skeleton of the overall stiffeners Y and obtaining the pixel length L of the central skeleton; S6. Performing a third morphological operation on the central skeleton using a circular structural element J2 to obtain the optimized stiffeners Z; S7. Extracting the numerical features of the optimized stiffeners Z and projecting them onto the digital model of the suspension crossbeam to obtain the digital model of the suspension crossbeam after smoothing processing. The smoothing method for the suspension crossbeam after profile optimization provided by the present invention can effectively eliminate the phenomena of uneven profile edges and excessive isolated areas existing after the profile optimization design of the suspension crossbeam.

The embodiment of the invention provides an image segmentation method and device, equipment and a medium, which are used for solving the problems of low efficiency and low accuracy of image segmentation in the prior art. In the embodiment of the invention, a user only needs to specify the target pixel point in the region where the organ is located and whether the target pixel point is located on the organ, and does not need to determine each pixel point in the organ, so that the image segmentation efficiency can be improved, the electronic equipment can accurately determine the updated maximum pixel value and minimum pixel value, and the user experience is improved. Therefore, each pixel point on the organ can be accurately determined, and the accuracy of image segmentation can be improved.

The present invention relates to a structural vibration analysis method and device based on video images, comprising: acquiring a video image of an object to be tested vibrating along a vibration direction frame by frame, converting each frame of the video image into a grayscale image, intercepting a specified area of each grayscale image frame, and calculating the maximum pixel value in the specified area of each grayscale image frame, and analyzing the vibration frequency and / or vibration amplitude of the object to be tested based on the maximum pixel value in the specified area of each grayscale image frame, wherein the specified area of each grayscale image frame has the same position on each grayscale image frame and includes a boundary in the vibration direction of the object to be tested and a column of pixel points in the neighborhood of the boundary. The technical solution provided by the present invention can accurately analyze and obtain the vibration frequency and / or vibration amplitude of the object to be tested by using the real pixel values corresponding to the grayscale image of the intercepted video image of the object to be tested vibrating along the vibration direction, with low computational complexity and high speed.

The invention discloses a method and equipment for detecting the liquid level of bottled liquid and a storage medium. The method comprises the following steps: acquiring a ray signal of bottled liquid, and converting the ray signal into a target image; extracting pixel points on a longitudinal center line of the bottled liquid based on the target image; carrying out difference calculation on the pixel points on the longitudinal center line to determine a liquid level segment with the maximum pixel value change; determining a first upper edge point and a first lower edge point of the liquid level segment; and determining the liquid level position according to the first upper edge point and the first lower edge point to identify the liquid level height so as to detect the liquid level of the bottled liquid. By means of the scheme, the liquid level height of the bottled liquid can be efficiently and accurately recognized.

The invention provides a display method and electronic equipment, and is applied to the technical field of display driving. The display method comprises the steps of determining a target display scene; determining a target refresh rate and a target pixel turn-on voltage corresponding to the target display scene; wherein the target refresh rate limits the maximum pixel charging duration of the target display scene, the target pixel turn-on voltage is in negative correlation with the maximum pixel charging duration, and the display device is controlled to display the target scene at the target refresh rate and the target pixel turn-on voltage so as to reduce the display power consumption of the display device.

The present application discloses a method for structural shock location based on adaptive time-reversal focusing imaging and image fusion, the method comprising extracting multiple narrowband wave signals of different frequencies of the shock stress wave signal through complex Morlet wavelet transform; setting the initial parameters of the algorithm, for each of the narrowband wave signals, obtaining the adaptive time-reversal focusing imaging result images of all narrowband wave signals based on the set initial parameters of the algorithm, and then calculating the image focusing index of each imaging result image, setting the focusing index threshold of the imaging result image according to the actual shock location imaging accuracy requirements, multiplying and fusion all the imaging result images above the focusing index threshold, and obtaining the grid point coordinates corresponding to the maximum pixel value of the fused image as the predicted shock position. The shock location accuracy of the present application can reach a relatively high level. The present application also discloses a corresponding system.

The present invention relates to an integrated circuit of an image capture device for automatically optimizing the ratio (A1 / A0) of the output image area (A1) to the main window area (A0), and for optimizing (preferably maximizing) the product D1×A1 of the output pixel density (D1) multiplied by the output image area (A1) of the motion detection area that defines an output image (P1) consisting of a predetermined maximum number (N1m) of pixels. The integrated circuit includes an array light sensor for capturing an input image (P0) and a processing unit configured to perform the following actions: - in an image detection mode, a series of consecutive reference images (Prefj) are captured at different times by a subarray of Nr reference light sensors, and a number (Nm) of motion pixels (pm) whose value difference between the two reference images exceeds a predetermined threshold deviation for detecting motion within an area of ​​the reference image is determined, and then switching; - in an image capture mode, the parameters of the captured output image are defined as follows: ● an output window (W1) with an output window area (A1) surrounding at least a predetermined number (Nmt) of the motion pixels (pm), and ● an output pixel density D1 = N1 / A1 ≦ DO, where N1 ≦ N1m; ● capturing an output image (P1) defined by the output window (W1) having the output window area (A1) and the output pixel density (D1) and transferring the output image (P1) including N1 pixels from the integrated circuit.

The invention provides an image coding method and device. The method comprises the following steps: acquiring a pixel value corresponding to a target pixel point with data overflow in a target image after image processing is completed; determining a multiple relationship between the pixel value and a maximum pixel value in a pixel value range which can be represented by the pixel depth of the target pixel point; determining at least one flag bit corresponding to the multiple relation in a plurality of data bits contained in the target pixel point; wherein the at least one flag bit is used for indicating data overflow information of the target pixel point; and encoding a pixel value corresponding to a target pixel point in the target image according to at least one flag bit corresponding to the target pixel point and the remaining data bits in the plurality of data bits to obtain an encoded target image. According to the image processing method and device, the image precision can be improved on the premise that the existing image processing efficiency is not affected.