Japanese / English

Detail of Publication

Text Language Japanese
Authors Kazuto NOGUCHI, Koichi KISE, Masakazu IWAMURA
Title Experimental Evaluation of Balancing the Recognition Rate, Processing Time and Memory Requirement for Large-Scale Recognition of Specific Objects
Journal Trans. IEICE
Vol. J92-D
No. 8
Pages pp.1135-1143
Reviewed or not Reviewed
Month & Year August 2009
Abstract For object recognition based on local descriptors, balancing the recognition rate, processing time and memory requirement is an important issue. In conventional methods, local descriptors are vector-quantized to “visual words” for describing images. Although many visual words allow us to improve the recognition rate for recognizing instances (specific objects), they also pose a problem of processing time and memory requirement. On the other hand, even if a recognition method employs local descriptors without vector quantization, approximate nearest neighbor search enables us to cut the processing time drastically. In this report, we propose a method of memory reduction applicable even to methods without vector quantization. The proposed method reduces the memory requirement by limiting the number of bits for the record of each dimension of feature vectors. From experimental results on 100,000 images, it has been confirmed that a representation with 2 bit / dimension subtly decreases the recognition rate, but hardly changes the processing time.
URL http://search.ieice.org/bin/summary.php?id=j92-d_8_1135
Back to list