13 results about "Binary image" patented technology

The invention discloses a segmentation method of pathological section unconventional cells based on a multi-scale hybrid segmentation model. The method comprises steps that positive and negative samples are respectively scaled to low-resolution, medium-resolution and high-resolution images, the full convolutional network algorithm is utilized for training to acquire a convergent low-resolution segmentation model, a medium-resolution segmentation model and a high-resolution model; a multi-scale hybrid segmentation model is acquired through fusion by a model integration method; after the effective discriminating area of a new pathological section is processed through utilizing the data enhancement method during testing, the processed effective discriminating area is inputted to the multi-scale hybrid segmentation model, the probability of each pixel in the effective segmentation area is outputted, pixels with probability values greater than the threshold t are taken as abnormal cell pixels and are recorded as 1, remaining pixels are taken as normal cell pixels and are recorded as 0, binary images predicted by the multi-scale hybrid segmentation model are acquired, and post-processingon the binary images is carried out to acquire the final segmentation result. The method is advantaged in that high precision is realized, and a Dice value is above 0.869.

A method, medium, and system effectively compressing and/or restoring binary images. By compressing pixel values making up a 2×2 block in an input image, using representative values representing the pixel values and a pattern of the pixel values represented by the representative values, it is possible to effectively compress and/or restore binary images having little similarities between pixel values. In addition, by extracting compressed values and a pattern of pixel values making up a 2×2 block in an image, from compressed data of the 2×2 block, and restoring pixel values using the compressed values and the pattern, it is possible to effectively restore binary images.

The invention discloses an image segmentation method for flaw detection of a cell tail end. Firstly, an initial BGR image at the cell tail end is converted into a gray scale image by considering image characteristics of intelligent flaw detection of the cell tail end, then the gray scale image is subjected to binaryzation processing so as to obtain a binaryzation image, and then coordinates of four key pixel points on the outer contour of the cell tail end are determined on the binaryzation image. The size of an ROI rectangular area where the cell tail end exists is determined according to the coordinates of the four key pixel points on the outer contour of the cell tail end, therefore the ROI rectangular area where the cell end tail exists is marked off in the initial BGR image, and a target area is not damaged. High accuracy in image dividing is ensured, operation is simple, and an early-stage guarantee is provided for accuracy of follow-up processing algorithms (such as the image characteristic extracting and matching algorithm). In addition, the ROI rectangular area is marked off in the initial BGR image, so that the processing of the whole image comprising the background with the follow-up processing algorithms is avoided, detecting efficiency of a cell is improved, and detecting cost is reduced.

A medical image inclination correction method based on a B spline is provided. The method comprises the steps of acquiring the medical image to be corrected, and performing binarization processing onthe medical image to be corrected to obtain a binary medical image; carrying out edge detection on the binary medical image according to the B spline gradient operator, and obtaining a binary edge image; calculating the bounding box of the edge image to obtain the actual size of the edge image, and then capturing the sub-image of the medical image to be corrected according to the actual size of the edge image; calculating the mass center of the sub-image and the normalized center moment to obtain a rotation angle; reversely rotating the medical image to be corrected according to the rotation angle to obtain the corrected medical image, so that the correction of the inclination image with uneven gray level can be realized.

The invention discloses a denoising method and a denoising device aiming at linear interference, which relates to the computer technical field. An embodiment of the method includes: preprocessing an original image to obtain a binary image; determining a coordinate interval corresponding to each character in the binarized image; determining the coordinates of the first end point and the end point corresponding to the character according to the coordinate interval corresponding to the character; solving a noise curve expression according to the coordinates of a head-end point and an end point corresponding to each character; noise being predicted and removed using a noise curve expression. The embodiment can precisely solve the segmented expression of the noise curve, better fit the noise curve, realize more accurate character recognition, and further improve the recognition success rate of the whole verification code.

A scanner-characteristic correcting unit converts read image data into normalized image data. A first image processing unit applies a first image processing on the normalized image data. A color determining unit performs a color determination of the normalized image data. A controller image processing unit that applies a second image processing on the normalized image data is provided in a removable manner. When a B&W plotter unit is connected to an image processing apparatus without the controller image processing unit, the first image processing unit generates binary image data of the image data before a result of the color determination is output.

The invention provides a plant leaf image extraction method and device. The method is characterized by carrying out threshold processing on subimages on red/green/blue color channels and obtaining binary images; and after obtaining the binary images, carrying out fitting on pixel points in the binary images and extracting target plant leaves. According to the technical scheme, interference of field complex environment can be overcome, and the target plant leaves can be segmented accurately and intactly; the method not only can improve leaf edge detection precision and reduce leaf identification error probability, but also can be applied to mobile terminals, such as a smart phone; the method is suitable for field operation; and the application range of the method is broadened.

The invention provides a method and device for measuring blood flow in a blood vessel and a processor. The method comprises the following steps: acquiring multiple frames of continuous original blood vessel images; pre-processing the original blood vessel images through an artificial intelligence algorithm, obtaining a plurality of binary images, and blood vessels in the binary images being continuous; extracting one or more target blood vessels from the binary image; and constructing a 3D blood vessel model of the target blood vessel. The transient flow, the transient flow velocity, the average flow and the average flow velocity of the target blood vessel are measured at least according to the 3D blood vessel model. According to the scheme, the transient flow rate, the transient flow rate, the average flow rate and the average flow rate of the blood vessel are obtained based on the segmented images of the continuous frames.

The invention provides a fixed scene moving object extraction method and device. The method comprises the steps of: S101, obtaining and marking N frames of images in a video stream; S102, setting that the ith frame is an object image, subtracting the ith frame of image from other images respectively, calculating the differences, taking the absolute values, and obtaining a group of difference images; S103, converting the difference images into binary images through a threshold; S104, for all images, accumulating all corresponding position elements and obtaining one accumulated image; S105, carrying out screening on the values of the accumulated image, and selecting all the matrix image blocks whose value is N-1, namely moving objects. The sampling frame number is adjusted, so that the moving object extraction effect and efficiency of the algorithm are balanced, and the algorithm is enabled to applicable to various hardware platforms. The algorithm is free from the influences of sampling frame intervals and sequences, so that the algorithm is more flexible. A relatively large image frame number is utilized to avoid the condition that the objects are not staggered among all frames, so that the integrity of the obtained moving objects is greatly improved.