ROC curves for recognition of visual patterns

ROC Curves for Steganalysts

There are different approaches in the literature for the assessment of steganographic algorithms and steganalytic attacks. In the early papers it was considered sufficient to show the existence of an effect for one or a few examples only. The more the area of steganography evolved, the more diverse became the goals and the harder to measure the improvements. Many branches of science are facing ...

ROC curves predicted by a model of visual search.

In imaging tasks where the observer is uncertain whether lesions are present, and where they could be present, the image is searched for lesions. In the free-response paradigm, which closely reflects this task, the observer provides data in the form of a variable number of mark-rating pairs per image. In a companion paper a statistical model of visual search has been proposed that has parameter...

Confidence Bands for ROC Curves

We address the problem of comparing the performance of classifiers. In this paper we study techniques for generating and evaluating confidence bands on ROC curves. Historically this has been done using one-dimensional confidence intervals by freezing one variable—the false-positive rate, or threshold on the classification scoring function. We adapt two prior methods and introduce a new radial s...

Recollection and familiarity in recognition memory: Evidence from ROC curves

Resampling ROC curves

Receiver operating characteristic (ROC) curves are very popular for evaluating a diagnostic test or score performances in various decision making applications: medicine, marketing, credit scoring etc. The ROC curve provides a concise graphical representation of the trade off between sensitivity and specificity. We will focus here on supervised classification into two groups. Error rate estimati...