
i
i
i
i
i
i
i
i
11.5 Compression of Image Descriptors 231
Figure 11.6 The coding process of SIFT descriptors in one image.
a small integer (e.g., 1 or 2), the residual vector v − ¯v is coded by transformation,
quantization, and entropy coding. For the rest of the octaves, since the scale in-
dices are small, retrieved patches are too small to help image reconstruction. Those
SIFT descriptors are discarded directly. Selecting part of the SIFT descriptors is a
common method of mobile applications [254]. Although it may have a negative im-
pact on search results and reconstructed quality, it is a cost-effective way for practical
applications.
The coding process ...