Retrieving color patterns on surface meshes using edgeLBP descriptors

Thompson, Elia Moscoso; Biasotti, Silvia

doi:10.1016/j.cag.2018.12.009

Cited by 5 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[AHP04] used LBP for face recognition. LBPs, which do not directly handle 3D models, have been incorporated into point clouds in other studies by voxelizing point clouds or projecting point clouds from different views [ZWZ*18, MTB19, MTBDC20].…”

Section: Related Workmentioning

confidence: 99%

SGLBP: Subgraph‐based Local Binary Patterns for Feature Extraction on Point Clouds

Zhang

Jin

et al. 2022

Computer Graphics Forum

View full text Add to dashboard Cite

Extraction for points that can outline the shape of a point cloud is an important task for point cloud processing in various applications. The topology information of the neighbourhood of a point usually contains sufficient information for detecting features, which is fully considered in this study. Therefore, a novel method for extracting feature points based on the topology information is proposed. First, an improved α-shape technique is introduced, generating two graphs for potential feature detection and neighbourhood description, respectively. Local binary pattern (LBP) is then applied to the subgraphs, thus subgraph-based local binary patterns (SGLBPs) are generated for encoding the topology of the neighbourhoods of points, which helps to remove non-feature points from potential feature points. The proposed method can directly process raw point clouds and needs no prior surface reconstruction or geometric invariants computation; furthermore, the proposed method detects feature points by analysing the topologies of the neighbourhoods of points, consequently promoting the effectiveness for tiny features and the robustness to noises and non-uniformly sampling patterns. The experimental results demonstrate that the proposed method is robust and achieves state-of-the-art performance.

show abstract

Section: Related Workmentioning

confidence: 99%

SGLBP: Subgraph‐based Local Binary Patterns for Feature Extraction on Point Clouds

Zhang

Jin

et al. 2022

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…The experimentation allows to identify the ceramic fragments, through the combination of semantic and geometric elements, and to assemble them in a semi-automatic way, simplifying the work of the archaeologist and giving the possibility to virtually reunify a spread archaeological heritage. [Moscoso Thompson, Biasotti 2019]. The third field aims to develop systems for the management of large amounts of data and informations, analog or digital, contained in libraries, archives, museums, and to provide the user with easier and more immediate access to information.…”

Section: Ai and Big Data: Order Complexitymentioning

confidence: 99%

Artificial Intelligency, Big Data and Cultural Heritage

Buratti¹,

Conte²,

Rossi³

2021

Representation Challenges. Augmented Reality and Artificial Intelligence in Cultural Heritage and Innovative Design Domain

View full text Add to dashboard Cite

In recent decades, the cultural heritage sector has benefited from solutions offered by ICT for the conservation, management, enhancement and communication of cultural heritage; today this specific sector benefits from the infinite potential of application of AI. The proposed research identifies the three main lines of research that operate in the cultural heritage exploiting the synergy between machine learning, big data and AI, starting from the analysis of the state of the art and a subsequent first taxonomic approximation of artificial intelligence systems. The analysis of some case studies developed in the field of recovery and restoration of cultural heritage, monitoring and prevention of damage, data acquisition and analysis of the same, confirm the real potential of AI: trigger knowledge from knowledge.

show abstract