Scalable Feature Matching by Dual Cascaded Scalar Quantization for Image Retrieval

In content-based image retrieval using local features, the key problem is the feature matching among images which is well formulated as a ??-neighborhood problem without any assumption on the feature distribution. In this paper, we investigate the problem of scalable visual feature matching in large-scale image search and propose a novel cascaded scalar quantization scheme in dual resolution. We formulate the visual feature matching as a range-based neighbor search problem and approach it by identifying hyper-cubes with a dual-resolution scalar quantization strategy. Specifically, for each dimension of the dimension-reduced feature by PCA, scalar quantization is performed at both coarse and fine resolutions. The scalar quantization results at the coarse resolution are cascaded over multiple dimensions to index an image database. The scalar quantization results over multiple dimensions at the fine resolution are concatenated into a binary super-vector and stored into the index list for efficient verification. The proposed cascaded scalar quantization (CSQ) method is free of the costly visual codebook training and thus is independent of any image descriptor training set. The index structure of the CSQ is flexible enough to accommodate new image features and scalable to index large-scale image database. We evaluate our approach on four public benchmark datasets for large scale image retrieval. Experimental results demonstrate the competitive retrieval performance of the proposed method compared with seven recent retrieval algorithms on feature quantization.