Abstract
The cosine distance compares the feature vectors of two images by returning the cosine of the angle between two vectors. Other cosine- and angle-based measures are here presented, including Tanimoto dissimilarity and Jaccard index, together with other correlations; they have been employed in algorithms relying on PCA, ICA, NN, and Gabor wavelets, especially on bi-dimensional facial data. Only correlation coefficients have been applied on three-dimensional point clouds.
Keywords: Angle distance, cosine distance, cosine similarity measure, Pearson correlation, Tanimoto dissimilarity, Jaccard index.
About this chapter
Cite this chapter as:
Enrico Vezzetti, Federica Marcolin ;Cosine-Based Distances, Correlations, and Angles for Face Recognition, Similarity Measures for Face Recognition (2015) 1: 47. https://doi.org/10.2174/9781681080444115010007
DOI https://doi.org/10.2174/9781681080444115010007 |
Publisher Name Bentham Science Publisher |