A Semi-Automatic Reconstruction of Archaeological Pottery Fragments from 2D Images Using Wavelet Transformation

Abstract

The problem of matching fragments of three-dimensional (3D) objects has gained increasing attention, and several approaches have been developed to solve this problem. To date, however, to the best knowledge of the authors, there is no computer-based method supporting archaeologists in this activity. For this purpose, in this paper, a semi-automatic approach is proposed for the reconstruction of archaeological pottery fragments based on two-dimensional (2D) images. Firstly, the method, considering the curves as features, involves the extraction of edge curves by applying the Canny filter algorithm to the fragments’ image. Next, the wavelet transformation method is used to fit the edge curves and obtain the approximation coefficients. Then, the correlation coefficients between fragments are computed and the matching of fragments is done by comparing their values. The proposed approach is tested on some real cases. The results of the experimentation show, if compared with the state-of-the-art, that the method seems to be efficient and accurate in the reconstruction of pottery from 2D images of their fragments.

Selecting the Important Features to Classify the Archaeological Fragments by Using Statistical Tools

“…Despite rapid technological development, many artifacts have not yet been repaired and assembled [4]. Although several methods have been proposed to solve this problem, archaeologist's have not utilized them to facilitate their work [5]. Statisticians have presented hypotheses, theories, and statistical methods to help researchers reach accurate conclusions from available data.…”

Research Ancient Artifact Identification Methods under Intelligent Perception and Recognition Technology

“…While determining the features, the digital ancient artifacts will add up the core features of artifacts throughout various historical periods and evaluate the law of artifact identification, which acts as a guide for determining the authenticity and dating of ancient relics. The preservation of two-dimensional image information into three dimensions using machine learning technology and wavelet transformation technique seems to be the latest research path for ancient relics [3]. This paper is going to discuss all the critical factors and aspects regarding machine learning techniques for the identification of ancient artifacts.…”

Plant Disease Diagnosis in the Visible Spectrum

“…There are some papers that address general image segmentation by means of Gaussian mixture models (GMM) [11], other methods focus on the development of features of the image and models of features that get to be as informative as possible, some of those studies combine the intensity, shape, and texture in order to generate features that mimic the behavior of human beings [12]. Classic examples are those based on Gabor filters [13], based on wavelet transformations [14], on co-occurrence matrices [15], and derived features from Markov models for random fields of models of local textures [16,17]. The literature of the models that incorporate texture features is very vast, and a thorough summary is available in [18].…”