Evaluation of different distortion correction methods and interpolation techniques for an automated classification of celiac disease

Abstract

Due to the optics used in endoscopes, a typical degradation observed in endoscopic images are barrel-type distortions. In this work we investigate the impact of methods used to correct such distortions in images on the classification accuracy in the context of automated celiac disease classification.For this purpose we compare various different distortion correction methods and apply them to endoscopic images, which are subsequently classified. Since the interpolation used in such methods is also assumed to have an influence on the resulting classification accuracies, we also investigate different interpolation methods and their impact on the classification performance. In order to be able to make solid statements about the benefit of distortion correction we use various different feature extraction methods used to obtain features for the classification.Our experiments show that it is not possible to make a clear statement about the usefulness of distortion correction methods in the context of an automated diagnosis of celiac disease. This is mainly due to the fact that an eventual benefit of distortion correction highly depends on the feature extraction method used for the classification.

Is a Precise Distortion Estimation Needed for Computer Aided Celiac Disease Diagnosis?

“…In [2] the authors showed, that the classification accuracy does not decrease in case of simple DC models. In opposite, they argue that the converse might well be so, as the best results are achieved with the simplest model.…”

“…Since the authors in [2] argued, that the simplest distortion model leads to the best classification results, we will investigate if the model can be simplified even more. For celiac disease diagnosis, images patches (128 × 128 pixels) are extracted from the original images.…”

“…Distortion correction (DC) techniques are able to rectify the images. However, although the lens distortion can be undone, especially in peripheral regions the images are blurred because of the required interpolation during image stretching [2].…”

“…In [2], the authors extensively analyzed computer aided celiac disease diagnosis in combination with lens distortion correction. Various distortion models have been investigated in combination with various interpolation methods and numerous feature extraction techniques.…”

Getting one step closer to fully automatized celiac disease diagnosis

“…For the experimental analysis, we deploy the following feature extraction techniques, which proved to the adequate for celiac disease classification in previous work [13], [5]:…”