Device, method and electronic device for segmenting cohesive objects in images

An object segmentation and image-based technology, applied in the information field, can solve the problems of bacteria count errors, bacteria sticking or overlapping, and inseparability

Inactive Publication Date: 2017-12-08
FUJITSU LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, in the field of biological detection, it is often necessary to count the number of microorganisms such as bacteria. When observing and photographing bacteria with a microscope, since a culture medium usually contains multiple bacteria, these bacteria may stick or overlap together, thereby lead to statistical errors in the number of bacteria
Existing image segmentation methods cannot effectively segment these glued or overlapping objects

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Device, method and electronic device for segmenting cohesive objects in images
  • Device, method and electronic device for segmenting cohesive objects in images
  • Device, method and electronic device for segmenting cohesive objects in images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] figure 1 It is a schematic structural diagram of the segmentation device for sticky objects in an image according to Embodiment 1 of the present invention. like figure 1 As shown, the device 100 includes: a first determination unit 101, a first extraction unit 102, a classification unit 103, a second determination unit 104, and a first segmentation unit 105, wherein,

[0026] The first determining unit 101 is configured to determine candidate segmentation boundaries of cohesive objects in the image;

[0027] The first extraction unit 102 is used to extract the features of all candidate segmentation boundaries;

[0028] The classification unit 103 is used to classify all candidate segmentation boundaries according to the extracted features;

[0029] The second determining unit 104 is configured to determine the dividing line according to the classification result;

[0030] The first segmentation unit 105 is configured to segment the adhered object based on the segmen...

Embodiment 2

[0056] An embodiment of the present invention provides an electronic device, which includes the device for segmenting a cohesive object in an image as described in Embodiment 1.

[0057] Figure 7 It is a schematic block diagram of the system configuration of the electronic device 700 according to Embodiment 2 of the present invention. like Figure 7 As shown, the electronic device 700 may include a central processing unit 701 and a memory 702; the memory 702 is coupled to the central processing unit 701. This diagram is exemplary; other types of structures may also be used in addition to or in place of this structure, for telecommunications or other functions.

[0058] like Figure 7 As shown, the electronic device 700 may further include: a camera unit 703 , a communication module 704 , an input unit 705 , a display 706 , and a power supply 707 . Wherein, the camera unit 703 inputs the captured image to the memory 702 for storage.

[0059] In one embodiment, the functio...

Embodiment 3

[0072] Figure 8 It is a flow chart of the method for segmenting cohesive objects in images according to Embodiment 3 of the present invention, corresponding to the device for segmenting cohesive objects in images in Embodiment 1. like Figure 8 As shown, the method includes:

[0073] Step 801: Determine the candidate segmentation boundaries of cohesive objects in the image;

[0074] Step 802: extracting features of all candidate segmentation boundaries;

[0075] Step 803: classify all candidate segmentation boundaries according to the extracted features;

[0076] Step 804: Determine the dividing line according to the classification result;

[0077] Step 805: Segment the glued object based on the segmentation line.

[0078] In this embodiment, the method of determining candidate segmentation boundaries, the method of extracting features, the method of classifying according to the extracted features, the method of determining the segmentation line according to the classifi...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

Embodiments of the present invention provide a segmentation device, method, and electronic equipment for cohesive objects in an image. The segmentation device includes: a first determination unit, configured to determine a candidate segmentation boundary of a cohesive object in an image; a first extraction unit, configured to extract The features of all candidate segmentation boundaries; the classification unit is used to classify all candidate segmentation boundaries according to the extracted features; the second determination unit is used to determine the segmentation line according to the classification result; the first segmentation unit is used to determine the segmentation line based on the segmentation line The sticky objects are segmented. By classifying the candidate segmentation boundaries according to the extracted features, and determining the segmentation line according to the classification results, the cohesive objects in the image can be accurately and effectively segmented.

Description

technical field [0001] The invention relates to the field of information, in particular to a device, method and electronic equipment for segmenting cohesive objects in an image. Background technique [0002] With the continuous development of information technology, the application of image processing in various fields is becoming more and more extensive. In many cases, it is necessary to segment the cohesive objects in the image. For example, in the field of biological detection, it is often necessary to count the number of microorganisms such as bacteria. When observing and photographing bacteria with a microscope, since a culture medium usually contains multiple bacteria, these bacteria may stick or overlap together, thereby lead to statistical errors in the number of bacteria. Existing image segmentation methods cannot effectively segment these cohesive or overlapping objects. [0003] It should be noted that the above introduction of the technical background is only ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/12
Inventor 刘曦王正翔刘汝杰
Owner FUJITSU LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap