44results about How to "Prevent oversegmentation" patented technology

The invention provides a method for segmenting adhesion cells in an image, which comprises the following steps of: performing image binaryzation, and performing distance transform on a binary image to obtain a distance value of each point; detecting local extreme points in a distance image, and screening to obtain central points representing cells; performing water area segmentation on the distance image, and determining the subjection relation of subblocks and the cells according to the distance between the center of each subblock and the center of each cell; and finally segmenting intermediate blocks adjacent to a plurality of subblocks accurately. By the method, the problems of over-segmentation and segmentation error which are likely to occur in the conventional watershed segmentationare solved effectively, and the method has the good applicability to the adhesion of the cells.

An intelligent monitoring system for a power cable production process, including an image acquisition component, a sensor component, a wireless transmission module, an intelligent monitoring center and a danger alarm module, the sensor component is used to collect environmental data and temperature data on the surface of power cable production equipment, and The collected data is transmitted to the intelligent monitoring center, and the intelligent monitoring center processes the received data and compares it with the preset safety threshold, and when the data is higher than the preset safety threshold, the danger alarm module gives an alarm, and The image acquisition component is used to acquire images of the positions of the sensor nodes that acquire the data, and the acquired images are processed and displayed. The beneficial effects of the invention are: realizing the effective monitoring of the environment of the power cable production workshop and the operating state of the power cable production equipment, and improving the intelligence of the monitoring of the power cable production process.

The invention relates to the field of medical image processing and aims to provide a fully-automatic three-dimensional liver segmentation method based on a convolution nerve network. The fully-automatic three-dimensional liver segmentation method based on the convolution nerve network comprises the following processes: preparing a training set, and training the convolution nerve network, processing CTA volume data of an abdominal liver by utilizing the trained convolution nerve network to obtain a segmentation result of the liver. The liver is segmented by means of the three-dimensional convolution nerve network; the three-dimensional liver segmentation method is fully automatic and can also prevent under-segmentation and over-segmentation phenomena well; and the accurate liver segmentation result is obtained.

The invention provides a distribution uniformity assessment method based on a watershed algorithm and a minimum spanning tree. The method comprises the steps that an image is subjected to gray processing and median filtering; binarization processing is conducted through an OTSU method; morphological operation is conducted to obtain a feature tag image; segmentation is conducted through the watershed algorithm; an adjoining matrix composed of centroids of segmented regions in the segmented image and distances between the centroids is calculated; the minimum spanning tree is calculated through a Prim algorithm; the distribution uniformity of particles or spots in the image is analyzed based on the minimum spanning tree. According to the method, interference, noise and other ineffective information of the image are filtered out, a tag source is provided for the watershed algorithm, and mistaken segmentation caused by inconsistency of sizes of the particles or the spots and over segmentation caused by the noise are avoided; segmentation based on the watershed algorithm better represents the relation among the particles or the spots and the relation between the particles or the spots and overall distribution; since the Prim algorithm is used for obtaining the minimum spanning tree, the time complexity is low, the efficiency is high, and the assessment of distribution uniformity is more accurate.