An Effective Color Addition to Feature Detection and Description for Book Spine Image Matching
The source image in each channel is independently convolved with a Gaussian kernel at differing values of , and then adjacent images are differenced to produce a Difference of Gaussians. The channel DoG is shown in (b), the in (c), and the in (d). Different strong edges are visible in each channel. A grayscale feature detector would only find those visible in the channel and miss the very obvious features in the chrominance channels.
(a) Original book spine image
(b) DoG image in channel
(c) DoG image in channel
(d) DoG image in channel
Article of the Year Award: Outstanding research contributions of 2020, as selected by our Chief Editors. Read the winning articles.