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 re… Show more
“…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.…”
Section: Evaluation For Biometric Authenticationmentioning
confidence: 99%
“…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].…”
Section: Modeling Of Partitioned Power-graphsmentioning
confidence: 99%
“…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 .…”
Biometric authentication systems verify the identity of individuals based on what they are. As they are error prone, they can reject genuine individuals or accept impostors. Researchers of the field quantify the quality of their algorithm by benchmarking it on several databases. However, although the standard evaluation metrics state the performance of their system, they are unable to explain the reasons of their errors. This paper presents a novel way to visualize the evaluation results of a biometric authentication system which helps to find which individuals or samples are sources of errors. This knowledge could help to fix the algorithms. A biometric database of scores is modeled as a partitioned power-graph with nodes representing biometric samples and power-nodes representing individuals. A novel recursive edge bundling method is also applied to reduce clutter. This proposal has been successfully applied on several biometric databases and has proved its efficiency.
“…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.…”
Section: Evaluation For Biometric Authenticationmentioning
confidence: 99%
“…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].…”
Section: Modeling Of Partitioned Power-graphsmentioning
confidence: 99%
“…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 .…”
Biometric authentication systems verify the identity of individuals based on what they are. As they are error prone, they can reject genuine individuals or accept impostors. Researchers of the field quantify the quality of their algorithm by benchmarking it on several databases. However, although the standard evaluation metrics state the performance of their system, they are unable to explain the reasons of their errors. This paper presents a novel way to visualize the evaluation results of a biometric authentication system which helps to find which individuals or samples are sources of errors. This knowledge could help to fix the algorithms. A biometric database of scores is modeled as a partitioned power-graph with nodes representing biometric samples and power-nodes representing individuals. A novel recursive edge bundling method is also applied to reduce clutter. This proposal has been successfully applied on several biometric databases and has proved its efficiency.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.