Moreover, Star Student Project
the network traffic of Star Student Project is heavy, as
a bunch of local features from different machines has to be
transmitted to all servers Star Student Project for
quantization and ranking.In our consideration, the above issues arise
from using the Star Student Project local indexing
architecture in Star Student Project. By contrast, the global
indexing is more efficient in communication as the quantized Star
Student Project words are only transmitted to its corresponding
machine(s). In this paper, we prefer the Star Student Project
scheme to deploy our distributed visual search system. And as
quantitatively shown in Star Student Project Section , we
can achieve better performance over the local indexing
schemes in Star Student Project.