Fisher Encoding of Adaptive Fast Persistent Feature Histograms for Partial Retrieval of 3D Pottery Objects

Abstract

Cultural heritage is a natural application domain for partial 3D object retrieval, since it usually involves objects that have only been partially preserved. This work introduces a method for the retrieval of 3D pottery objects, based on partial point cloud queries. The proposed method extracts fast persistent feature histograms calculated adaptively to the mean point distances of the point cloud query. The extracted set of vectors is refined by a denoising component, which employs statistical filtering. The remaining vectors are further refined by a filtering component, which discards points surrounded by surfaces of extremely fine-grained irregularity, often associated with artefact damages. A bag of visual words scheme is used, which starts from the final set of persistent feature histogram vectors and estimates Gaussian mixture models by means of an expectation maximization algorithm. The resulting Gaussian mixture models define the visual codebook, which is used within the context of Fisher encoding. Experiments are performed on a challenging dataset of pottery objects, obtained from the publicly available Hampson collection.