Research Article

An Effective Color Addition to Feature Detection and Description for Book Spine Image Matching

Figure 5

The source image in each channel is independently convolved with a Gaussian kernel at differing values of ğœŽ , and then adjacent ğœŽ images are differenced to produce a Difference of Gaussians. The 𝑌 channel DoG is shown in (b), the 𝐶 𝑟 in (c), and the 𝐶 𝑏 in (d). Different strong edges are visible in each channel. A grayscale feature detector would only find those visible in the 𝑌 channel and miss the very obvious features in the chrominance channels.
(a) Original book spine image
(b) DoG image in 𝑌 channel
(c) DoG image in 𝐶 𝑟 channel
(d) DoG image in 𝐶 𝑏 channel