Bacterial colony identifying and counting method based on Hough circle transformation

By using a colony identification and counting method based on Hough circle transform, the problem of traditional colony counting relying on manual operation is solved, achieving efficient and accurate colony counting, reducing labor costs and improving the objectivity and repeatability of counting results.

CN118967780APending Publication Date: 2024-11-15NANJING TECH UNIV
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410986376.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

Traditional colony counting methods rely on manual operation, which is labor-intensive, slow, and prone to subjective errors. The accuracy and efficiency of existing computer vision technology in colony identification need to be improved.

Method used

A colony identification and counting method based on Hough circle transform is adopted, which includes image acquisition, grayscale loading, image enhancement, smoothing, binarization, morphological operations, Hough circle transform identification and post-processing steps. It combines weighted averaging, contrast-limited adaptive histogram equalization, Gaussian blur, adaptive thresholding and morphological operations to improve the accuracy of colony feature parameter identification.

Benefits of technology

It achieves efficient and accurate colony counting, reduces manual operation costs, and improves the objectivity and repeatability of counting results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118967780A_ABST
    Figure CN118967780A_ABST
Patent Text Reader

Abstract

The invention provides a colony identifying and counting method based on Hough circle transformation. Firstly, bacterial colony image quality is optimized through a series of preprocessing steps. And then, identifying and counting bacterial colonies by using a Hough circle transformation algorithm. And finally, the counting precision is further improved by adopting a post-processing technology, including colony counting correction and optimization, so that the counting accuracy is remarkably improved. The method combines contrast limited adaptive histogram equalization, Gaussian blur, adaptive threshold processing, opening operation, expansion operation, overlapped circle removal, adjacent circle combination and other algorithms, effectively realizes accurate identification and automatic counting of bacterial colonies, has high accuracy and efficiency, greatly reduces the dependence of manual operation, and improves the working efficiency. The operation cost and the time consumption are reduced, and meanwhile, the objectivity and the repeatability of a result are ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the fields of microbiology and image recognition, and in particular to a colony recognition and counting method based on Hough circle transformation. Background Art

[0002] Colony counting is of great significance in microbiological research. Traditional colony counting methods rely on manual operation, which has problems such as high labor consumption, slow speed and subjective errors. In recent years, computer vision technology has been widely used in the field of colony identification. The Hough circle transform algorithm can accurately locate the center and radius of each colony and detect circular colonies in the image, greatly reducing the reliance on manual operation, thereby reducing operating costs and time consumption, and ensuring the objectivity and repeatability of the counting results. Summary of the invention

[0003] In view of this, the present invention proposes a highly efficient colony identification and counting method.

[0004] The technical solution of the present invention is implemented as follows: The present invention provides a colony identification and counting method based on Hough circle transform, which comprises the following steps:

[0005] (1) Collecting colony image samples on the culture medium;

[0006] (2) Upload images to the system;

[0007] (3) Load the image in grayscale mode;

[0008] (4) Performing image enhancement processing on the image;

[0009] (5) Smoothing the image;

[0010] (6) Binarize the image;

[0011] (7) Perform morphological operations on the image;

[0012] (8) Using Hough circle transform to identify colony characteristic parameters;

[0013] (9) post-processing the detected bacterial colonies;

[0014] (10) marking the counted colonies;

[0015] (11) Count the number of colonies.

[0016] On the basis of the above counting scheme, preferably, in the step (3), the pixel values ​​of the color channels (R, G, B) are converted into gray values ​​using a weighted average method, so that the color image is loaded in the mode of a gray image, that is, when Gray = 0.299 × R + 0.587 × G + 0.114 × B, the most reasonable gray image is obtained.

[0017] Based on the above counting scheme, preferably, in step (4), the image after grayscale loading is enhanced using a contrast-limited adaptive histogram equalization method, the limiting threshold is set to 2.0, and the image is divided into small blocks of 8x8 size.

[0018] Based on the above counting scheme, preferably, in step (5), the image after equalization is smoothed using a Gaussian blur method, the Gaussian kernel size is 5x5, and the standard deviation of the Gaussian kernel in the X and Y directions is set to 0, that is, the standard deviation is automatically calculated from the kernel size.

[0019] Based on the above counting scheme, preferably, in step (6), the image after Gaussian blur processing is binarized using an adaptive threshold method, and an inverted binary image is generated by using inverse binary thresholding.

[0020] Based on the above counting scheme, preferably, in step (7), an opening operation and a dilation operation are used to perform morphological operations on the image after the adaptive threshold binarization process, and after the opening operation is performed once, the dilation operation is repeated three times.

[0021] Based on the above counting scheme, preferably, in step (8), Hough circle transform is used to identify the characteristic parameters of the colony.

[0022] Based on the above counting scheme, preferably, in step (9), the operations of removing overlapping circles and merging adjacent circles are used to further improve the colony counting result.

[0023] Based on the above counting scheme, preferably, in step (10), the original image is compared with the processed and marked image.

[0024] Based on the above counting scheme, preferably, in step (11), the final counting result is displayed.

[0025] The colony identification and counting method based on Hough circle transform of the present invention has the following beneficial effects compared with the prior art:

[0026] (1) The colony characteristic parameters are extracted by morphological methods, and these characteristic parameters are used as input parameters of Hough circle transform for colony recognition, and finally colony counting is performed.

[0027] (2) Use post-processing methods to correct colony counts and improve the accuracy of colony counts.

[0028] (3) The contrast-limited adaptive histogram equalization method, Gaussian blur method, adaptive threshold method, opening operation and dilation algorithm are used to realize the recognition and automatic counting of colonies with good accuracy and high efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments, and the above and / or other advantages of the present invention will become more clear.

[0030] Figure 1 The present invention is a flow chart of a colony identification and counting method based on Hough circle transform. DETAILED DESCRIPTION

[0031] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] like Figure 1 As shown, a colony identification and counting method based on Hough circle transform of the present invention comprises the following steps:

[0033] (1) Collect colony image samples on the culture medium.

[0034] (2) Upload the image to the system.

[0035] (3) Load the image in grayscale mode. Specifically, use the weighted average method to convert the pixel values ​​of the color channels (R, G, B) into grayscale values, so that the color image is loaded in grayscale mode, that is, Gray = 0.299 × R + 0.587 × G + 0.114 × B, and the most reasonable grayscale image is obtained.

[0036] (4) Perform image enhancement processing on the image. Specifically, use the contrast-limited adaptive histogram equalization method to perform image enhancement processing on the grayscale loaded image, set the limit threshold to 2.0, and divide the image into small blocks of 8x8 size.

[0037] (5) Smoothing the image. Specifically, the image after equalization is smoothed using a Gaussian blur method, the Gaussian kernel size is 5x5, and the standard deviation of the Gaussian kernel in the X and Y directions is set to 0, that is, the standard deviation is automatically calculated from the kernel size.

[0038] (6) Binarizing the image. Specifically, the image after Gaussian blur processing is binarized using an adaptive threshold method, and an inverted binary image is generated by using inverse binary thresholding.

[0039] (7) Performing morphological operations on the image. Specifically, using opening and dilation operations to perform morphological operations on the image after the adaptive threshold binarization process, after the opening operation is performed once, the dilation operation is repeated three times.

[0040] (8) Using Hough circle transform to identify colony characteristic parameters. Specifically, using Hough circle transform to identify colony characteristic parameters.

[0041] (9) Post-processing the detected colonies. Specifically, using operations such as removing overlapping circles and merging adjacent circles can further improve the colony counting results.

[0042] (10) Marking the counted colonies. Specifically, the original image is compared with the processed and marked image.

[0043] (11) Count the number of colonies.

[0044] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A colony identification and counting method based on Hough circle transform, characterized in that: The steps include: (1) Collecting colony image samples on the culture medium; (2) Upload images to the system; (3) Load the image in grayscale mode; (4) Performing image enhancement processing on the image; (5) Smoothing the image; (6) Binarize the image; (7) Perform morphological operations on the image; (8) Using Hough circle transform to identify colony characteristic parameters; (9) post-processing the detected bacterial colonies; (10) marking the counted colonies; (11) Count the number of colonies.

2. The method according to claim 1, characterized in that In the step (3), the pixel values ​​of the color channels (R, G, B) are converted into grayscale values ​​using a weighted average method, so that the color image is loaded in the mode of a grayscale image, that is, when Gray = 0.299×R+0.587×G+0.114×B, the most reasonable grayscale image is obtained.

3. The method according to claim 1, characterized in that In the step (4), the image after grayscale loading is enhanced using a contrast-limited adaptive histogram equalization method, the limiting threshold is set to 2.0, and the image is divided into small blocks of 8x8 size.

4. The method according to claim 1, characterized in that: In the step (5), the image after equalization is smoothed using a Gaussian blur method, the Gaussian kernel size is 5x5, and the standard deviation of the Gaussian kernel in the X and Y directions is set to 0, that is, the standard deviation is automatically calculated from the kernel size.

5. The method according to claim 1, characterized in that In the step (6), the image after Gaussian blur processing is binarized using an adaptive threshold method, and an inverted binary image is generated by using inverse binary thresholding.

6. The method according to claim 1, characterized in that In the step (7), the image after the adaptive threshold binarization processing is subjected to morphological operations using opening and dilation operations. After the opening operation is performed once, the dilation operation is repeated three times.

7. The method according to claim 1, characterized in that In the step (8), the colony characteristic parameters are identified using Hough circle transform.

8. The method according to claim 1, characterized in that In the step (9), the operations of removing overlapping circles and merging adjacent circles are used to further improve the colony counting result.

9. The method according to claim 1, characterized in that: In the step (10), the original image is compared with the processed and marked image.

10. The method according to claim 1, characterized in that In the step (11), the final counting result is displayed.

Citation Information

Cited By

  • A machine vision-based colony counting method and a colony counter

    CN122841391A