Approximate Image Matching using Strings of Bag-of-Visual Words Representation

Abstract

Abstract:The Spatial Pyramid Matching approach has become very popular to model images as sets of local bag-ofwords. The image comparison is then done region-by-region with an intersection kernel. Despite its success, this model presents some limitations: the grid partitioning is predefined and identical for all images and the matching is sensitive to intra-and inter-class variations. In this paper, we propose a novel approach based on approximate string matching to overcome these limitations and improve the results. First, we introduce a new image representation as strings of ordered bag-of-words. Second, we present a new edit distance specifically adapted to strings of histograms in the context of image comparison. This distance identifies local alignments between subregions and allows to remove sequences of similar subregions to better match two images. Experiments on 15 Scenes and Caltech 101 show that the proposed approach outperforms the classical spatial pyramid representation and most existing concurrent methods for classification presented in recent years.

Deep Image Annotation and Classification by Fusing Multi-Modal Semantic Topics

“…Given an image, image classification tells people what is the theme of the image according to its visual content from a high-level semantic meaning perspective. There has also been work on applying traditional supervised learning methods to perform classification, including support vector machine [12,13], random forest [14,15], and probabilistic topic models [16,17,18,19,20,21,22,23]. It can be seen that probabilistic topic model has become popular in the computer vision community due to its solid theoretical foundation and promising performance.…”