| Summary: | Recently, extensive research efforts have been dedicated to view-based 3D object retrieval, owing to its advantage of using a set of 2D images to represent 3D objects. Some existing image processing technologies can be employed. In this paper, we adopt Bag-of-Words for view-based 3D object retrieval. Instead of SIFT, DSP-SIFT is extracted from all images as object features. Moreover, two codebooks of the same size are generated by approximate k-means. Then, we combine two codebooks to correct the quantization artifacts and improve recall. Bayes merging is applied to address the codebook correlation (overlapping among different vocabularies) and to provide the benefit of high recall. Moreover, Approximate Nearest Neighbor (ANN) is used to quantization. Experimental results on ETH-80 datasets show that our method improves the performance significantly compared with the state-of-the-art approaches.
|
|---|