Cancelable biometric schemes for Euclidean metric and Cosine metric

Metric and Euclidean TSP

Euclidean vs Graph Metric

The theory of sparse graph limits concerns itself with versions of local convergence and global convergence, see e.g. [41]. Informally, in local convergence we look at a large neighborhood around a random uniformly chosen vertex in a graph and in global convergence we observe the whole graph from afar. In this note rather than surveying the general theory we will consider some concrete examples...

Quasi Cosine Similarity Metric Learning

It is vital to select an appropriate distance metric for many learning algorithm. Cosine distance is an efficient metric for measuring the similarity of descriptors in classification task. However, the cosine similarity metric learning (CSML)[1] is not widely used due to the complexity of its formulation and time consuming. In this paper, a Quasi Cosine Similarity Metric Learning (QCSML) is pro...

Metric Transforms and Euclidean Embeddings

It is proved that if 0 < c < 0.72/« then for any «-point metric space (X, d), the metric space (X,dc) is isometrically embeddable into a Euclidean space. For 6-point metric space, c = j log2 | is the largest exponent that guarantees the existence of isometric embeddings into a Euclidean space. Such largest exponent is also determined for all «-point graphs with "truncated distance".

Cosine Similarity Metric Learning for Face Verification

Face veri cation is the task of deciding by analyzing face images, whether a person is who he/she claims to be. This is very challenging due to image variations in lighting, pose, facial expression, and age. The task boils down to computing the distance between two face vectors. As such, appropriate distance metrics are essential for face veri cation accuracy. In this paper we propose a new met...