Project Details
Description
Bacterial colony counting is widely used in both industry and research laboratories in a wide range of applications; these include quality control, environmental monitoring, immunological studies and medical testing. The number of colonies on an agar plate can be used to estimate the number of viable bacteria (total viable count) present in a test sample. This can then be used as an indicator of the cleanliness of a surface, the sterility of a product or the presence of a bacterial infection.
Traditionally, colony counting was performed manually or using a light box which was time-consuming and prone to human error. The advent of automated colony counters, which use sophisticated algorithms to detect and count colonies based on shape or colour, has overcome these drawbacks. The popular technologies exploited for bacteria colony counting are edge detection techniques for image processing.
However, a number of challenges remain in automated colony counting: identifying and splitting touching colonies, background noise, colony density variance etc. Hence, more advanced and sophisticated techniques need to be developed to cope with these issues while taking efficiency into account.
The aim of this project is to propose and implement new algorithms which are robust to noise for rapid bacterial colony detection and counting.
Traditionally, colony counting was performed manually or using a light box which was time-consuming and prone to human error. The advent of automated colony counters, which use sophisticated algorithms to detect and count colonies based on shape or colour, has overcome these drawbacks. The popular technologies exploited for bacteria colony counting are edge detection techniques for image processing.
However, a number of challenges remain in automated colony counting: identifying and splitting touching colonies, background noise, colony density variance etc. Hence, more advanced and sophisticated techniques need to be developed to cope with these issues while taking efficiency into account.
The aim of this project is to propose and implement new algorithms which are robust to noise for rapid bacterial colony detection and counting.
Status | Finished |
---|---|
Effective start/end date | 1/03/19 → 28/02/23 |
Keywords
- QA75 Electronic computers. Computer science
- image processing
- density based clustering
- bacteria colony counting
Fingerprint
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.