Nondestructive characterization and artificial intelligence recognition of acoustic identifiers of ancient ceramics

In order to ensure the sustainability of cultural, historical and architectural heritage, preserving and restoring historical buildings and transferring them to future generations is one of the important issues of today. Restoration decisions regarding the repairs of historical buildings are of great importance in this context. Developing correct intervention decisions requires the thorough analysis of the structure, the determination of the structural and material properties meticulously, and the use the most appropriate materials for repairing it. However, only physical and chemical analyses are not sufficient to determine material properties of historical buildings; therefore, archaeometric analyses are needed to determine them more appropriately. In this study, it is aimed to determine the components and characteristics of the filling mortars of Oshki (Öşvank) Church, one of the most magnificent structures of the Eastern Anatolia region, in order to preserve the masonry structure and guide the restoration studies in the light of archaeometric analyses. The raw material properties of the samples taken from the filling mortars of the church were determined by the physical, chemical and petrographic analyses. As a result of the analyses, the aggregate-binding properties of Oshki Church filler mortars were determined. It was revealed that the aggregate content was determined as petrographic, lime was used as a binder and all samples contained pozzolan whereas no cement was used in any of the samples, and the samples did not contain marble rice/powder and organic additives like oil, protein etc. It has also been observed that the aggregate in the mortar content is compatible with the geological formations of near surrounding of the church. In this context, this study emphasizes the importance of archaeometric analysis in restoration of historical buildings. Moreover, differing from other studies in the literature, this study proposes mortar recipe to be used in the restoration of the church, which can pioneer to future studies in the field of architectural restoration.

show abstract

Incomplete handwritten Dongba character image recognition by multiscale feature restoration

Bi,

Luo

2024

Herit Sci

View full text Add to dashboard Cite

Incomplete handwritten Dongba character often appears in heritage documents and its recognition is significant for heritage and philology. However, all previous methods always suppose that a complete Dongba character is used as input, and thus fail to achieve satisfactory performance when applied to incomplete Dongba character recognition. In this paper, an end-to-end network (DB2RNet) is proposed for incomplete handwritten Dongba character image recognition by multiscale feature restoration. Specifically, we first develop datasets that contain different levels of incomplete Dongba characters. A restoration module is proposed to restore the input incomplete Dongba character, and then a recognition module is employed to recognize Dongba character. By introducing an inter-module residual connection between the restoration module and recognition module, the DB2RNet can strengthen feature information transmission and boost the recognition performance. In addition, novel multiscale feature blocks are introduced, which can provide more effective texture and contextual information transmission for Dongba character image restoration, and thus yielding better restoration effects and better recognition results. Extensive experiments are conducted on Dongba character, Chinese character and Oracle character datasets and validate the effectiveness, superiority and robustness of our methods. Experiments results demonstrate that our proposed DB2RNet achieves competitive Dongba character restoration and recognition performance and outperforms the current state-of-the-art methods.

show abstract

Nondestructive characterization and artificial intelligence recognition of acoustic identifiers of ancient ceramics

Cited by 6 publications

References 26 publications

Nondestructive Testing Technologies of Cultural Relics by Using Audible Sound and Ultrasonic Wave

Nondestructive Testing Technologies of Cultural Relics by Using Audible Sound and Ultrasonic Wave

Archaeometric characterization and restoration proposal for filling mortars of Oshki (Öşvank) church

Incomplete handwritten Dongba character image recognition by multiscale feature restoration

Contact Info

Product

Resources

About