<inline-formula> <tex-math notation="LaTeX">$\ell m_p$ </tex-math></inline-formula>: A Novel Similarity Measure for Matching Local Image Descriptors

• Main Author: Guohua Lv
• Format: Article
• Language: English
• Published: IEEE 2018-01-01
• Series: IEEE Access
• Subjects: Similarity measure; <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">ℓ</italic><italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">ₚ</italic>-norm distance; <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">m</italic><italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">ₚ</italic>-dissimilarity; local descriptors; accuracy; image registration
• Online Access: https://ieeexplore.ieee.org/document/8476570/

m_p-dissimilarity is a recently proposed data-dependence similarity measure. In the literature, how m_p-dissimilarity is generally used for matching local image descriptors has been formalized, and three matching strategies have been proposed by incorporating &#x2113;_p-norm distance and m_p-dissimilarity. Each of these three matching strategies is essentially a two-round matching process that utilizes &#x2113;_p-norm distance and m_p-dissimilarity individually. This paper presents two novel similarity measures for matching local image descriptors. The first similarity measure normalizes and weights the similarities that are calculated using &#x2113;_p-norm distance and m_p-dissimilarity, respectively. The second similarity measure involves a novel calculation that takes into account both spatial distance and data distribution between descriptors. The proposed similarity measures are extensively evaluated on a few image registration benchmark data sets. Experimental results will demonstrate that the proposed similarity measures achieve higher matching accuracy and are able to attain better recall results when registering multi-modal images compared with the existing matching strategies that combine &#x2113;_p-norm distance and &#x2113;_p-dissimilarity.