A survey of image quality defects and their effect on the performance of an automated visual evaluation classifier
David Levitz, Sandeep Angara, José Jerónimo, Ana Cecilia Rodríguez, Sílvia de Sanjosé, Sameer Antani, Mark W. Schiffman · 2022
Cervical cancer disproportionately affects low and middle income countries. Automated visual evaluation – using deep learning to analyze a digital cervix photograph – has been proposed for patient management. Image quality remains a key challenge, as it can be degraded by many types of image defects. A series of such defects were artificially added to a test set consisting of N=344 digitized cervigram images from existing studies. Replicate test sets were created for different image defects: blur, recoloring, obstructions of different colors and directions, rotations, and white Gaussian noise. The augmented images were evaluated by a classifier. The two most significant image defects were blur and Gaussian noise.