26 results about "Image subtraction" patented technology

A method for generating a subtraction image for digital subtraction angiography to reduce noise and movement artifacts. Obtaining a plurality of mask images of an object takes place before administering a contrast agent into the object and obtaining a map of the object after administering a contrast agent into the object. A first sum image is obtained from the plurality of mask images in that the plurality of mask images is summed in each case multiplied by an individual weighting. The individual weightings for each of the plurality of mask images are automatically determined by an optimization method, and the subtraction image is ascertained by subtraction of the sum image from the map.

The invention provides a mouse scratching behavior detection method based on machine vision, which belongs to the technical field of image processing and biological behavior recognition, and comprises the following steps: establishing a required shooting environment, and recording mouse behaviors under different conditions such as illumination, darker light, coexistence of two mice and the like at the angle of high-angle shooting of a camera. The system firstly carries out gray processing operation on an image, then obtains a segmentation threshold value through an Otsu algorithm, respectively carries out binary segmentation twice, carries out small object removal, morphological dilation, corrosion and other operations after extracting mouse claw and ear contours through image subtraction operation, so as to reduce other influences except for a required target to the greatest extent. And calculating the area size of the foreground corresponding to the mouse, the coordinates of the central point and the distance between the claw and the ear, and comparing a set corresponding distance threshold value with the calculated distance to judge whether the mouse has a scratching action or not. The method can effectively improve the accuracy of mouse scratching behavior detection and save a large amount of labor cost.

The invention relates to the technical field of image enhancement, in particular to an angiocardiography high-precision angiography enhancement method and system. The method comprises the steps that an ECG curve of electrocardiosignals before and after contrast agent injection of a patient and a blood vessel image are obtained; determining the compressible degree of each wave band according to the change of different wave bands and the change of the heart rate in the QT interval before and after the contrast agent is injected; determining the increment duration of each wave band in combination with the standard duration, the actual duration and the compressible degree; performing standardized adjustment on the ECG time phase of each frame of blood vessel image in combination with the increment time length and the actual time length of each wave band to obtain a standard time phase; determining a mask matched with each negative film according to the standard time phases of the negative films and the masks; and carrying out image subtraction on each negative film and the matched mask, and carrying out angiography enhancement processing. The blood vessel imaging precision after digital subtraction can be improved, the blood vessel artifact phenomenon is reduced, and the blood vessel imaging precision and reliability are enhanced.

The present invention relates to the field of 3D printing technology, and discloses a quality monitoring method, system, equipment and medium for direct writing molding circuits. The method comprises: determining a captured image of a discharge area according to a needle position; performing binarization processing and connected domain analysis on the captured image and a preset template image, respectively, to determine the discharge area of ​​the captured image and the discharge area of ​​the preset template image; performing a difference image subtraction between the captured binary image and the template binary image, and performing connected domain analysis on the difference image to obtain a difference analysis result; calculating the discharge area ratio of the captured image and the preset template image, and monitoring the quality of the direct writing molding circuit according to the discharge area ratio difference analysis result. The present invention analyzes the image of the discharge area, makes the judgment of material breakage more accurate, and can also perform material breakage detection on materials in various states. By calculating the discharge area, an early warning can be given before the material is completely exhausted, thereby ensuring the effect of direct writing molding.

The present application provides a method, device, electronic device, and storage medium for subtracting coronary CT images, including: obtaining an enhanced CT image and a plain CT image of a target patient; extracting a first feature point set of the enhanced CT image using a first feature point extraction model; extracting a second feature point set of the plain CT image using a second feature point extraction model; determining a target transformation matrix based on the first feature point set and the second feature point set; performing coordinate transformation processing based on the plain CT image and the target transformation matrix to obtain a transformed plain CT image; and obtaining a subtracted CT image by subtracting the grayscale values ​​of the corresponding pixels in the transformed plain CT image from the grayscale values ​​of all pixels in the enhanced CT image. The subtraction method provided by this solution can automatically obtain a subtracted CT image, and by accurately registering the enhanced CT image and the plain CT image, the accuracy of the subtracted CT image is improved.

The present invention discloses a method for removing stains from scanned images based on deep learning. First, the contrast of the scanned image is improved by improving traditional contrast enhancement using the results of deep learning contrast classification. Then, the main components of the scanned image are labeled, and after deep learning training to obtain a model, the main components of the scanned image are detected. Based on the main components, stains at the edge are obtained by image subtraction. Furthermore, the detection of point-like stains is completed under the premise of eliminating page number interference using deep learning. Finally, the stain area is automatically filled by analyzing the color distribution around the stain. The system includes: an image preprocessing module, a contrast classification offline training module, a principal component detection offline training module, a point-like stain and page number detection offline classification module, and a stain online detection module. The present invention proposes to use principal component detection and page number detection, combined with deep learning technology and contrast improvement, to achieve higher accuracy than existing algorithms.

The invention discloses an achromatic metamaterial lens based on a long focal depth light beam and an imaging method, and the method comprises the steps: generating a zero-order Bessel light beam and a high-order Bessel light beam through a polarization multiplexing metamaterial lens, carrying out the imaging of an object, obtaining a zero-order image and a high-order image, subtracting the high-order image from the zero-order image, and obtaining a high-order image; and obtaining an achromatic image of the to-be-measured object. According to the invention, a large focusing depth of field is obtained through a conical phase, and then broadband imaging is obtained by using a focal depth overlapping region in a broadband, so that achromatic imaging of a visible light waveband is realized; the lens size is not limited, the area can reach the centimeter level or above, meanwhile, image blurring caused by side lobes is effectively eliminated through image subtraction, and the imaging quality is remarkably improved.

The application discloses a shooting method, device and system for removing ambient light, and the shooting method comprises the following steps in sequence: S1, obtaining a first image and a second image through camera acquisition; S2, performing image subtraction operation on the second image by using the first image to obtain a calculation image; the first image is acquired by a first linear array camera, and the second image is acquired by a second linear array camera; the shooting modes of the first linear array camera and the second linear array camera for a shooting object are as follows: the two cameras move in the same direction relative to the shooting object, and in the relative movement process, the two cameras sequentially shoot each shooting area covered by each of the two cameras, and the shooting area of one camera in the last shooting has an overlapping part with the shooting area of the other camera in the next shooting. The shooting device and system are used for realizing the shooting method. By using the technical scheme provided in the application, the influence of ambient light change on image results can be effectively reduced.

The application discloses an endoscope image enhancement method and device, equipment and medium, and relates to the technical field of endoscopes. The method comprises the following steps: performing guided filtering on an original image returned by an endoscope to obtain an original base layer image of the original image, and performing image subtraction processing on the original image and the original base layer image to obtain an original detail layer image of the original image; performing non-local mean filtering on the original detail layer image to obtain a filtered detail layer image, and performing gain control on the filtered detail layer image to obtain a target detail layer image; processing the original base layer image by using a limited contrast adaptive histogram equalization algorithm, a non-uniform illumination correction algorithm and a linear weighted fusion algorithm to obtain a target base layer image; and performing image fusion on the target detail layer image and the target base layer image to obtain an enhanced target image of the original image. The endoscope image can be reasonably enhanced to improve the image quality.

This invention discloses an achromatic metalens based on a long depth-of-focus beam and its imaging method. The method utilizes a polarization-multiplexed metalens to generate a zero-order Bessel beam and a higher-order Bessel beam, which are used to image an object, obtaining a zero-order image and a higher-order image respectively. The higher-order image is then subtracted from the zero-order image to obtain an achromatic image of the object under test. This invention achieves a large depth of field through a conical phase and utilizes the overlapping area of ​​the depth of field within a wide wavelength band to obtain broadband imaging, realizing achromatic imaging in the visible light band. The lens size is not limited, and the area can reach the centimeter level or above. Simultaneously, image subtraction effectively eliminates image blurring caused by side lobes, significantly improving image quality.

The invention relates to the technical field of image processing, and discloses a panoramic photoelectric radar imaging brightness consistency processing method. According to the method, when a system runs, each frame of image is collected, low-pass filtering processing is carried out before splicing, a low-pass filtering algorithm is adopted to obtain a low-frequency image Img (i), summation is carried out on continuous 50 frames of panoramic low-frequency images, then an average value is calculated, normalization processing is carried out on an average value image, the average value of low-frequency components is reduced to zero, and a corrected background image is obtained. According to the method, each frame of image of the panoramic photoelectric radar is corrected by using the correction background image, the corrected images are spliced and displayed, and the background image with non-uniform illumination is calculated by carrying out image subtraction processing on a real-time video and using the non-repeated imaging characteristic of a panoramic field image, so that the illumination is uniform, and the continuity of the overall effect of the image is improved.

A leak-detection system comprises networked imaging packages including an infrared camera based on microbolometer arrays, one or more filters, and a processor. The processor uses one or more novel processing methods for identifying gas leakages in a monitored facility. In some embodiments, the imaging packages are installed at various locations in the monitored facility. In some other embodiments, the leak-detection system is embodied as a mobile platform, wherein the networked imaging packages are coupled to drones that fly throughout the monitored facility to monitor for gas leakages. The flight path of the cameras may be pre-programmed and may further be alterable in real time. The novel processing technique(s) employed by the leak-detection system disclosed herein involve the use of multiple unique filters that facilitate enhancing the signal-to-noise ratio of captured images; that is, enhancing the contrast of a monitored gas against other objects. The novel processing techniques include one or more of the following: (i) two-image subtraction; (ii) time-resolved imaging; and (iii) multi-filter detection. Additionally, in some embodiments, the imaging packages include a visible (light) camera in addition to an IR camera.

The application provides an image subtraction method, system and storage medium. The method can include at least one operation. A contrast image and a plurality of mask images can be obtained. At least two mask images of the plurality of mask images can be combined based on the contrast image to obtain a combined mask image. The method disclosed in the application can combine at least two mask images according to the contrast image to reduce the influence of motion artifacts on the subtraction image.

The invention relates to a valve abnormal state detection method and system, electronic equipment and a storage medium. The method comprises the following steps: acquiring a state change image of the valve; wherein the state change image is a difference image obtained by performing image subtraction operation on images acquired by an opening indicator of the valve at at least two different moments in the rotating process of the valve; identifying a change area contour in the state change image; calculating an interval variable quantity or an interval change rate through the change region contour; wherein the interval variable quantity is the variable quantity of valve rotation in a time interval between two different moments, and the interval change rate is the change rate of valve rotation in the time interval; and the abnormal state condition of the valve is evaluated through the interval variable quantity or the interval change rate. The abnormal state of the key area is evaluated according to the specific condition of the valve, the whole process of the valve opening and closing action does not need to be completely analyzed, and therefore the analyzed data size is reduced, and the requirement for rapid positioning of the overhaul area is met.

Embodiments of the present application relate to an image generation method and a printing method of a light painting, the image generation method comprising: obtaining a target image; performing a grayscale inversion on the target image to obtain a first inverted image; performing a bilateral filtering on the first inverted image to obtain a filtered image; performing a grayscale inversion on the filtered image to obtain a second inverted image; subtracting the second inverted image from the target image to obtain a first processing image representing a difference between the target image and the second inverted image; and generating a line drawing of the target image based on the first processing image. Thus, the line drawing of the image can be obtained by sequentially performing the operations of grayscale inversion, bilateral filtering, grayscale inversion and image subtraction on the image, so that the accuracy and efficiency of generating the line drawing can be improved.

The application discloses a microwave imaging and scattering source separation method based on a revolution-rotation composite motion system, and the revolution-rotation composite motion system is used for radar microwave measurement on a target system to be measured, wherein the target system to be measured comprises a target to be measured, a hanging rope, a rotating rhombic support rod and a revolving turntable, and the rotating rhombic support rod is located above the revolving turntable, that is, the rotating rhombic support rod and the revolving turntable perform revolution-rotation composite motion, so that the tip of the rotating rhombic support rod always faces the radar incident direction, thereby reducing the rhombic support rod scattering; meanwhile, a point target model is used to verify the influence of the self-rotation of other targets on the revolving turntable on the measurement of the revolution scattering characteristics of the target to be measured, the real situation of the target motion during the measurement is analyzed theoretically, and the calculation and analysis of a two-dimensional image are carried out, and the image subtraction method is further used to reduce the rhombic support rod scattering, so that the microwave imaging and the scattering source separation can be realized.

This application relates to an image subtraction method, apparatus, and storage medium. The method includes: registering a current frame's overlay image and a previous frame's target mask image to determine the current frame's target mask image; and determining the current frame's subtraction image based on the current frame's target mask image and the current frame's overlay image. Through this application, the current frame utilizes the previous frame's target mask image during the registration process, transferring the registration trend of the previous frame to the current frame. This is equivalent to the current frame undergoing several registrations, thereby reducing the computational load during image registration and improving the registration effect.

To provide a non-destructive evaluation device that reduces the influence of uneven heating and surface roughness.SOLUTION: A non-destructive evaluation device 5 used in a lock-in thermography system that includes: an infrared heater 2 that heats a sample 1; a pulse power supply unit 4 that supplies heating power to the infrared heater 2 through on / off control; an infrared camera 3 that images the sample 1 at a frame interval shorter than the on / off control cycle; and a synchronized imaging unit 50 that notifies the infrared camera 3 of start timing of the on / off control of the pulse power supply unit 4, includes: an averaging image processing unit 53 that performs averaging processing on multiple on / off control cycles for the on-period imaging frame and off-period imaging frame; and an image subtraction processing unit 54 that performs subtraction processing on the on-period imaging frame and off-period imaging frame averaged by the averaging image processing unit 53 according to an elapsed time from the start timing of the on / off control.SELECTED DRAWING: Figure 2

The application discloses a shooting method, device and system for removing ambient light, and the shooting method comprises the following steps in sequence: S1, obtaining a first image and a second image through camera acquisition; S2, performing image subtraction operation on the second image by using the first image to obtain a calculation image; the linear array camera moves linearly relative to a shooting object, and the linear array camera shoots the shooting object multiple times in the relative motion process; in two adjacent shootings, one shooting is used to obtain the first image, and the other shooting is used to obtain the second image; in three adjacent shootings, the first shooting and the third shooting are both used to obtain the first image or the second image, and the shooting areas of the first shooting and the third shooting are connected or intersected. The shooting device and system are used for realizing the shooting method. By using the technical scheme provided in the application, the influence of ambient light change on image results can be effectively reduced.

The present application relates to a kind of fabric one-way wet detection methods based on image processing, the main steps of the present application are: first, water drop experiment is carried out to fabric, obtains the diffusion image of its in different time of fabric inner and outer layer, after pre-processing, the water drop contour map is segmented using image subtraction method, the radius and area of water drop at each time are calculated, obtain the diffusion rate of moisture in fabric, then the one-way wet ability of fabric is detected, and the correlation analysis of image method detection result and MMT detection result is carried out.Finally, the wet index of each item measured by image method is used as input function, the wet grade of fabric corresponding to MMT measured is used as output function, and it is substituted into the rating training of BP neural network, the rating of fabric wet performance is realized, the fabric wet theory and fluid equation are introduced into the mutual calculation of water absorption rate and diffusion rate, the diversity of image method performance index is increased, and the accuracy and scientificity of the detection result of this method are improved.

The application relates to the technical field of image enhancement, in particular to a high-precision blood vessel imaging enhancement method and system for cardiovascular imaging. The method comprises the following steps: acquiring an ECG curve of an electrocardiosignal before and after injection of a contrast medium of a patient, and acquiring a blood vessel image; determining the compressibility of each wave band according to the changes of the QT interval of each wave band and the heart rate before and after injection of the contrast medium; determining the incremental time length of each wave band by combining a standard time length, an actual time length and the compressibility; standardizing and adjusting the ECG phase of each frame of the blood vessel image according to the incremental time length and the actual time length of each wave band to obtain a standard phase; determining the matched mask of each negative film according to the standard phase of the negative film and the mask; and performing image subtraction on each negative film and the matched mask and performing blood vessel imaging enhancement processing. The application can improve the imaging precision of the blood vessels after digital subtraction, reduce the blood vessel artifact phenomenon, and enhance the imaging precision and reliability of the blood vessels.

This invention provides a method, apparatus, system, and storage medium for processing ring artifacts in CT images, belonging to the field of image processing technology. The method includes: acquiring an original CT image; performing a first filtering process on the original CT image to extract ring artifact images; performing a first transformation process on the ring artifact images to obtain a first ring artifact transformed image, and performing a second filtering process on the first ring artifact transformed image to obtain a second ring artifact transformed image; performing a second transformation process on the second ring artifact transformed image to obtain a third ring artifact transformed image, the second transformation process being the reverse of the first transformation process; and performing image subtraction between the original CT image and the third ring artifact transformed image to obtain a target CT image that does not contain ring artifacts. This invention effectively improves the accuracy of ring artifact processing, obtains higher quality artifact-free images, preserves image edges completely, and has a high signal-to-noise ratio.

Method (1000) to operate a wearable sensory device for real-time image processing, wherein said sensory device comprises an image detector (100) and a Neural Processing Unit (NPU), wherein said image detector (100) takes at least two consecutive images (201, 202), a first image (201) and a second image (202), wherein the method (1000) is performed by NPU and comprises an algorithm design phase (1200) comprising an acquiring operation (1201), wherein said acquiring operation (1201) acquires said at least two consecutive images (201, 202), a subtracting operation (1202) which subtracts the first image (201) from the second image (202) and obtains a differential image, a POSITIVE PATH operation (1210) which reconstructs a positive event-like image (32) from said differential image, a NEGATIVE PATH operation (1220) which reconstructs a negative event-like image (31) from said differential image, an addition operation (1230) which adds said negative event-like image (31) to positive event-like image (32) obtaining an event-like image.

The present application relates to the technical field of intelligent sensor, specifically to a Raman spectrum-based monk fruit agricultural residue fluorescence background suppression imaging method, which comprises the following steps: recognizing the gap between the hairy tissues of monk fruit by using a distance sensor, locking a three-dimensional pixel coordinate matrix and extracting local curvature feature mapping as a capillary pressure gradient field, guiding noble metal nano-probes to enrich at the root of the gradient field to construct a local enhanced hot spot, and outputting an enhanced signal stream; adopting frequency shift excitation combined with polarization differential phase detection, using polarization difference to strip scattering interference caused by the hairy tissues, and performing differential processing through image subtraction algorithm to obtain an agricultural residue differential image; and establishing an attenuation correction model based on surface topography and normal angle to perform pixel-level gain compensation on the signal and restore the real distribution concentration of agricultural residues. The present application is suitable for agricultural product detection scenes with complex hairy structure and strong fluorescence background, and can significantly improve the signal sensitivity, spatial imaging resolution and quantitative analysis capability of agricultural residue detection in a strong interference environment.

The present invention provides an image encoding / decoding technique that is capable of achieving the higher compression efficiency. An image encoding method comprises: an intra prediction step which performs intra prediction on a block basis to generate a predicted image; a subtraction step which calculates the difference in prediction between the predicted image generated by the intra prediction step and an original image; a frequency conversion step which performs frequency conversion processing for the difference in prediction; a quantization step which subjects the output of the frequency conversion step to quantization processing; and a variable-length encoding step which subjects the output of the quantization step to variable-length encoding processing; wherein the intra prediction encoding step predicts a target pixel to be encoded by use of pixel values of two reference pixels between which the target pixel to be encoded is located.

The present application relates to a method for producing a pictorial jacquard fabric, comprising: obtaining structural information and an initial image of the fabric, and determining an interval value based on the initial image; determining the width and height of the initial image in pixels based on the structural information and the interval value; performing image subtraction processing on the initial image using an indexed color mode and custom color dithering to obtain a first preprocessed image; adding intermediate color bits to the first preprocessed image based on the interval value to obtain a second preprocessed image; and performing weave planning processing and mesh weaving processing on the second preprocessed image. By setting the minimum number of warp yarns spanning the weft float length of the fabric surface pattern to 2 and the minimum warp yarn distance between the weft float point position of the fabric surface pattern and the mesh weave point position to 1, the pictorial jacquard fabric can be weaved using mesh weaving, ensuring that the weft yarns on the back of the fabric are not messy, thereby not affecting the fabric quality and subsequent processing.