Zoo Graph: A New Visualisation for Biometric System Evaluation

Abstract

Biometric authentication systems suffer from several performance limitations. Many performance metrics exist to assess the overall performance of such systems. However, these metrics provide a quantitative assessment in terms of errors without explaining the reasons behind the set of users who significantly contributed for these errors. Towards contributing to solve this problem, we present a novel method (named Zoo Graph) to visualize the performance of a biometric system as a graph thanks to a database of recognition scores. Our approach is an improvement of the Zoo Plot and emphasizes on the relations between the individuals of the database and allows interactive manipulations to track these relations and understand why the biometric authentication method reacts this way. This graph provides researchers with an additional visual assessment tool that would identify problematic users. Such information would allow researchers to update their developed authentication algorithms to reduce those errors.

Evaluation of Biometric Authentication Systems through Visualisation of Partitioned and Bundled Power-Graphs

“…It is also possible to visually evaluate biometric authentication algorithms: the Receiver operating characteristic curve (ROC) [10]: plots the FMR on the x-axis against the corresponding FNMR (more exactly 1-FNMR) on the y-axis depending on the decision threshold; the Zooplot [11] displays all the individuals of the dataset in a scatter plot where their coordinates correspond to their mean genuine and mean impostor scores; the Zoograph [7] improves it by (i) adding an edge between individuals when the source is able, in average, to be recognized as the target and (ii) by using a non linear mapping function on the coordinates ensuring the 25% best and worst individuals take only 25% of the screen space each.…”

“…W and B are respectively set to 80% and 5%. Among the different evaluation methodologies of the literature, we want to compete with the Zoograph [7] which is used as the baseline for local evaluation method, while the ROC curve is used as the baseline for global evaluation method. The proof of concept is written with around 4 000 lines of C++14 and intensively uses the graph display library Tulip 4.11 [18] and its associated plugins; each partition of samples is drawn with GRIP [19], each partition of individual is drawn with Fast Multipole Embedder [20] followed by Fast Node Overlap Removal [21] then followed by a connected component packing method to drastically reduce the drawing size of good partitions; Q groups is drawn with Bubble Tree [22]; finally, the bundling algorithm used by the recursive bundling algorithm is Winding Roads [23].…”

“…Thanks to his analysis, the researcher in biometric authentication could better understand the errors reasons and fix the authentication algorithm. The method proposed in this paper shows more information than the Zoograph [7] which has been designed for the same purpose. A power-graph P G = (V, P V, EV, EP V, EV P V ) is a graphlike structure containing two kinds of nodes: the nodes V and the power-nodes P V with each power-node representing a strong partition of V ∪ P V .…”