Progressive transmission based on wavelet used in mobile visual search

Mobile visual search has become a hot topic in both academia and business circles. A typical MVS system uses the camera phone to initiate search queries, following a client-server architecture. Transmission overload turns out to be a bottleneck. An effective way to reduce this is exploiting progressive transmission strategy. However, the acceleration effects of existing methods are limited because they only decrease the amount of descriptors delivered. To compress the descriptors, many methods have been offered. One problem is that they cannot restore the original descriptor and the more compressive the descriptor is, the lower the precision is. To conquer these problems, we propose a progressive transmission strategy based on wavelet theorem, which can both compress the descriptor and restore the original data. Extensive experiments have been done on Stanford database, demonstrating that our strategy outperforms other strategies, when delivering the same amount of data.