Bright Field Droplet Image Recognition Based on Fast Hough Circle Detection Algorithm

Digital polymerase chain reaction (PCR) bright-field droplet image recognition not only requires manual marking of the diameter and length, which is time-consuming and laborious, but also the existing circle detection algorithm has the problems of slow recognition speed and poor diameter measurement accuracy. In response to these problems, this paper proposes a fast Hough circle droplet detection algorithm. The algorithm mainly includes three steps: firstly, use the gradient information of the edge points and the geometric properties of the circle to determine the candidate circle; secondly, if the distance from the edge point in the set range to the center of the candidate circle is approximately equal to the radius, then the circle is determined as a true circle; finally, the circle with the largest radius among the neighboring true circles is taken as the final detection result. It is verified by comparative experiments that the algorithm can significantly improve the efficiency of droplet recognition and the accuracy of diameter measurement.

• Publication year

  2022

• Venue

  International Conference on Computer Research and Development

• Publication date

  2022-01-07

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/ICCRD54409.2022.9730227
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• An occlusion-resistant circle detector using inscribed triangles

  2021cited by this paper
• A fast and accurate circle detection algorithm based on random sampling

  2021cited by this paper
• An Improved Hough Transform for Circle Detection using Circular Inscribed Direct Triangle

  2020cited by this paper
• A sparse structure for fast circle detection

  2020cited by this paper
• A sub-pixel circle detection algorithm combined with improved RHT and fitting

  2020cited by this paper
• On the Improvement of Multiple Circles Detection from Images Using Hough Transform

  2019cited by this paper
• Automatic detection of particle size distribution by image analysis based on local adaptive canny edge detection and modified circular Hough transform.

  2018influential reference
• Advances in digital polymerase chain reaction (dPCR) and its emerging biomedical applications.

  2017cited by this paper
• Line and circle detection using dense one-to-one Hough transforms on greyscale images

  2016cited by this paper
• Summary of image edge detection

  2005cited by this paper
• An Efficient Randomized Algorithm for Detecting Circles

  2001cited by this paper
• Randomized hough transform (rht) : Basic mech-anisms, algorithms, and computational complexities

  1993influential reference
• A new curve detection method: Randomized Hough transform (RHT)

  1990influential reference

• Smartphone Platform for Multisignal Parallel Detection, Processing, and Visualization in Fluorescence Biosensing

  2025cites this paper
• Basketball Posture Recognition Using Neural Networks

  2025cites this paper
• Nut Geometry Inspection Using Improved Hough Line and Circle Methods

  2023cites this paper