This repository contains the source code for the Pattern Entity Selection tool, presented in the paper:
S. Lengauer, I. Sipiran, R. Preiner, T. Schreck, B. Bustos: A Benchmark Dataset for Repetitive Pattern Recognition on Textured 3D Surfaces. Computer Graphics Forum, 40(5), Proc. Eurographics Symposium on Geometry Processing. 2021.
This tool was used (in conjunction with a Sample Pattern Selection tool) to generate a benchmark dataset of patterns exhibited by ancient Peruvian pottery, which can be found here.
The code was written and built on a Linux system with qtcreator, relying on Qt 5.12.
It can be built via qmake <pro_file> && make.
The UI is tripartite. The left-hand side features a list of the pattern archetypes to annotate. They can be loaded from images via File > Load Sampe Patterns. The middle view shows the loaded mesh in a flattened 2D representation. This surface is used for the annotation. The right-hand side shows the 3D model with the colorized annotations.
A mesh can be loaded via File > Load Mesh.
Annotation can be created by pressing Shift and clicking into the selection view.
In this manner a polygon can be drawn around the outline of a pattern entity.
After confirming the selection an overlay appears which can then be used to indicate its size and orientation w.r.t. the provided archetype.
If you use our tool in a scientific context, please cite us as:
@article{LENGAUER2020111,
title = {A sketch-aided retrieval approach for incomplete 3D objects},
journal = {Computers & Graphics},
volume = {87},
pages = {111-122},
year = {2020},
issn = {0097-8493},
doi = {https://doi.org/10.1016/j.cag.2020.02.001},
url = {https://www.sciencedirect.com/science/article/pii/S0097849320300182},
author = {Stefan Lengauer and Alexander Komar and Arniel Labrada and Stephan Karl and Elisabeth Trinkl and Reinhold Preiner and Benjamin Bustos and Tobias Schreck},
keywords = {Image processing, Shapes, Information storage and retrieval, Information systems},
abstract = {With the growing amount of digital collections of visual CH data being available across different repositories, it becomes increasingly important to provide archaeologists with means to find relations and cross-correspondences between different digital records. In principle, existing shape- and image-based similarity search methods can aid such domain analysis tasks. However, in practice, visual object data are given in different modalities, and often only in incomplete or fragmented state, posing a particular challenge for conventional similarity search approaches. In this paper we introduce a methodology and system for cross-modal visual search in CH object data that addresses these challenges. Specifically, we propose a new query modality based on 3D views enhanced by user sketches (3D+sketch). This allows for adding new context to the search, which is useful e.g., for searching based on incomplete query objects, or for testing hypotheses on existence of certain shapes in a collection. We present an appropriately designed workflow for constructing query views from incomplete 3D objects enhanced by a user sketch, based on shape completion and texture inpainting. Visual cues additionally help users compare retrieved objects with the query. The proposed approach extends on a previously presented retrieval system by introducing improved retrieval methods, an extended evaluation including retrieval in a larger and richer data collection, and enhanced interactive search weight specification. We demonstrate the feasibility and potential of our approach to support analysis of domain experts in Archaeology and the field of CH in general.}
}