Unlock instant, AI-driven research and patent intelligence for your innovation.

A parallel detection method and system for connected regions of a binary image

A technology of connected regions and detection methods, applied in the field of parallelized detection of connected regions of binary images, can solve the problems of low detection efficiency, large storage space, low efficiency, etc.

Active Publication Date: 2016-12-28
宁波胤瑞生物医学仪器有限责任公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This algorithm has the following problems: First, it needs to scan and compare repeatedly, and the required storage space is large and the logic is complex; second, it cannot be calculated in parallel, which is slow and inefficient; finally, the efficiency of detecting a large number of connected regions is low

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
  • A parallel detection method and system for connected regions of a binary image
  • A parallel detection method and system for connected regions of a binary image
  • A parallel detection method and system for connected regions of a binary image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0060] For a binary image composed of 0 and 1, the method for parallel detection of the connected regions of the binary image of the present invention identifies the connected regions in the image, and outputs the number of connected regions.

[0061] E.g image 3 There are 3 connected regions in .

[0062] The parallel detection method of the binary image connected region of the present invention can process the image in a parallel manner. This method refers to dividing the image into several blocks, using multiple computing units, each unit processes a sub-region, and calculates at the same time, thereby significantly improving the computing efficiency. For example, if an image is divided into 16*16 blocks and loaded and processed by 256 GPU operation kernels at the same time, theoretically, the result can be obtained in only 1 / 256 time. The so-called segmentation step does not need to be actually segmented. The image is a matrix. When loading the image, as long as the sta...

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

The present invention discloses a binary image connected region parallel detection method and system. The method comprises: initiating multi-calculation, and segmenting an image into multiple parts; independently performing extreme value construction on each part after segmentation; synchronizing the computed result of each part to obtain a data result the same as the size of the original image; and scanning the data result to obtain the number and positions of extreme points. According to the method, only one scanning and one comparison are needed, the required storage space is small, the logic is simple, parallel computation can be performed, the speed is high, and the efficiency is high, and the method is particularly suitable for detecting problems of a large amount of connected regions.

Description

technical field [0001] The invention relates to the field of detection of connected regions of binary images, in particular to a method and system for parallel detection of connected regions of binary images. Background technique [0002] In high-throughput biological detection, the identification of a large number of reaction sites in data images is one of the core steps. After the image is pre-processed, a binary image reflecting the shape of the hole position of the chip is obtained. How to quickly determine the number, center position, and size of connected regions in the image (that is, the number, position, and size of holes) is the key to recognition technology, which directly affects the performance of image detection algorithms. [0003] The current connected region detection algorithms are mainly based on run-length coding. The idea of ​​the method is as follows: firstly, a complete scan is performed on the binary image, and at the same time when all target pixel...

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): G06T7/00
CPCG06T2207/30072
Inventor 刘元杰俞育德刘文文魏清泉
Owner 宁波胤瑞生物医学仪器有限责任公司