The application of adaptive texture filters to the automated visual inspection of antibiotic susceptibility tests

摘要

Computer vision systems have been used in recent years to perform automated antibiotic susceptibility tests based on the disk-diffusion method. However, certain organisms do not reflect light very well. As such, the reliabiliyt of such automated inspection systems is sometimes not as high as expected. This paper proposes to sue texture analysis to improve the quality of test images and thereby simplify the inspection tasks. Adaptive texture filters are used to maximise the difference between regions of interest in a test image and the background, enabling a thresholding operation to be carried out easily. The principles of adaptive filtering for texture analysis are discussed. A training algorithm is presented to generate optimised filters for generic texture inspection problems. An experimental study is carried out on investigate the performance of this technique in highlighting poorly reflecting organisms in antibiotic susceptibility tests.