CVMMIVJan 15, 2020

Evaluating image matching methods for book cover identification

arXiv:2001.05200v1
AI Analysis

This work addresses the need for libraries to develop interactive services based on book cover images, though it is incremental as it compares existing methods.

The paper tackled the problem of book cover identification by evaluating various feature detectors and matching methods, achieving encouraging results in terms of speed and accuracy under different image transformations.

Humans are capable of identifying a book only by looking at its cover, but how can computers do the same? In this paper, we explore different feature detectors and matching methods for book cover identification, and compare their performances in terms of both speed and accuracy. This will allow, for example, libraries to develop interactive services based on cover book picture. Only one single image of a cover book needs to be available through a database. Tests have been performed by taking into account different transformations of each book cover image. Encouraging results have been achieved.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes