Abstract:Abstract-The development of powerful 3D scanning hardware and reconstruction algorithms has strongly promoted the generation of 3D surface reconstructions in different domains. An area of special interest for such 3D reconstructions is the cultural heritage domain, where surface reconstructions are generated to digitally preserve historical artifacts. While reconstruction quality nowadays is sufficient in many cases, the robust analysis (e.g. segmentation, matching, and classification) of reconstructed 3D data… Show more
“…Using AI to analyse rock art is a newly emerging field in both data science and archaeology. In the course of the ERC funded 3D-Pitoti project, several methods have been proposed and tested on a relatively limited set of rock art images (Poier et al, 2016(Poier et al, , 2017Zeppelzauer et al, 2016;. 2D and 3D documentations were used to create an automatic segmentation algorithm.…”
Section: Previous Work and Research Questionmentioning
Rock art carvings, which are best described as petroglyphs, were produced by removing parts of the rock surface to create a negative relief. This tradition was particularly strong during the Nordic Bronze Age (1700–550 BC) in southern Scandinavia with over 20,000 boats and thousands of humans, animals, wagons, etc. This vivid and highly engaging material provides quantitative data of high potential to understand Bronze Age social structures and ideologies. The ability to provide the technically best possible documentation and to automate identification and classification of images would help to take full advantage of the research potential of petroglyphs in southern Scandinavia and elsewhere. We, therefore, attempted to train a model that locates and classifies image objects using faster region-based convolutional neural network (Faster-RCNN) based on data produced by a novel method to improve visualizing the content of 3D documentations. A newly created layer of 3D rock art documentation provides the best data currently available and has reduced inscribed bias compared to older methods. Several models were trained based on input images annotated with bounding boxes produced with different parameters to find the best solution. The data included 4305 individual images in 408 scans of rock art sites. To enhance the models and enrich the training data, we used data augmentation and transfer learning. The successful models perform exceptionally well on boats and circles, as well as with human figures and wheels. This work was an interdisciplinary undertaking which led to important reflections about archaeology, digital humanities, and artificial intelligence. The reflections and the success represented by the trained models open novel avenues for future research on rock art.
“…Using AI to analyse rock art is a newly emerging field in both data science and archaeology. In the course of the ERC funded 3D-Pitoti project, several methods have been proposed and tested on a relatively limited set of rock art images (Poier et al, 2016(Poier et al, , 2017Zeppelzauer et al, 2016;. 2D and 3D documentations were used to create an automatic segmentation algorithm.…”
Section: Previous Work and Research Questionmentioning
Rock art carvings, which are best described as petroglyphs, were produced by removing parts of the rock surface to create a negative relief. This tradition was particularly strong during the Nordic Bronze Age (1700–550 BC) in southern Scandinavia with over 20,000 boats and thousands of humans, animals, wagons, etc. This vivid and highly engaging material provides quantitative data of high potential to understand Bronze Age social structures and ideologies. The ability to provide the technically best possible documentation and to automate identification and classification of images would help to take full advantage of the research potential of petroglyphs in southern Scandinavia and elsewhere. We, therefore, attempted to train a model that locates and classifies image objects using faster region-based convolutional neural network (Faster-RCNN) based on data produced by a novel method to improve visualizing the content of 3D documentations. A newly created layer of 3D rock art documentation provides the best data currently available and has reduced inscribed bias compared to older methods. Several models were trained based on input images annotated with bounding boxes produced with different parameters to find the best solution. The data included 4305 individual images in 408 scans of rock art sites. To enhance the models and enrich the training data, we used data augmentation and transfer learning. The successful models perform exceptionally well on boats and circles, as well as with human figures and wheels. This work was an interdisciplinary undertaking which led to important reflections about archaeology, digital humanities, and artificial intelligence. The reflections and the success represented by the trained models open novel avenues for future research on rock art.
“…Petroglyph, in other words rock-art, analysis [8,28,[31][32][33]46] is another related topic to our glyph recognition task. For petroglyph segmentation that can be considered as foreground/background classification of pixels, Seidl et al [31] studied various combinations of traditional textural features.…”
Section: Related Workmentioning
confidence: 99%
“…Specifically, third order Gray-Level Co-occurrence Matrix (GLCM) and Local Binary Patterns (LBP) were shown to outperform color or dense-SIFT features in a late classification fusion setting [31]. In a recent 3D petroglyph segmentation study, Poier et al [28] reported that fully-connected CNNs produced better segmentation results thanks to capturing the spatial context better than random forests. Poier et al [28] also noted that the contribution of traditional color and textural features to final segmentation maps was negligible, therefore only depth maps and orthophotos generated from the point clouds were used as input to the classifiers.…”
Thanks to the digital preservation of cultural heritage material, multimedia tools, e.g. based on automatic visual processing, enable to considerably ease the work of scholars in the humanities and help them to perform quantitative analysis of their data. In this context, this paper assesses three different Convolutional Neural Network (CNN) architectures along with three learning approaches to train them for hieroglyph classification, which is a very challenging task due to the limited availability of segmented ancient Maya glyphs. More precisely, the first approach, the baseline, relies on pretrained networks as feature extractor. The second one investigates a transfer learning method by fine-tuning a pretrained network for our glyph classification task. The third approach considers directly training networks from scratch with our glyph data. The merits of three different network architectures are compared: a generic sequential model (i.e. LeNet), a sketch-specific sequential network (i.e. Sketch-a-Net), and the recent Residual Networks. The sketch-specific model trained from scratch outperforms other models and training strategies. Even for a challenging 150-class classification task, this model achieves 70.3% average accuracy and proves itself promising in case of small amount of cultural heritage shape data. Furthermore, we visualize the discriminative parts of glyphs with the recent Grad-CAM method, and demonstrate that the discriminative parts learned by the model agrees in general with the expert annotation of the glyph specificity (diagnostic features). Finally, as a step towards systematic evaluation of these visualizations, we conduct a perceptual crowdsourcing study. Specifically, we analyze the interpretability of the representations from Sketch-a-Net and ResNet-50. Overall, our paper takes two important steps towards providing tools to scholars in the digital humanities: increased performance for automation, and improved interpretability of algorithms. CCS Concepts: • Computing methodologies → Shape representations; Neural networks; Object identification; • Applied computing → Arts and humanities;
“…SfM is well-suited for identifying petroglyphs on uneven surfaces, such as those often found in caves (Caninas et al 2016; Fritz et al 2016), and SfM models give spatial context to petroglyphs that is helpful for interpretation (Alexander et al 2015; Janik et al 2007). Because of the value of SfM for the interpretation of rock art, archaeologists have recently explored methods of digitally enhancing model visualization (e.g., Carrero-Pazos et al 2016; Vilas-Estevez et al 2016), have developed specialized tools for efficiently collecting rock art photographs (e.g., Höll et al 2014), and have segmented rock art models to effectively store and query models in databases (e.g., Poier et al 2016; Zeppelzauer et al 2015; Zeppelzauer et al 2016). Significantly, SfM mapping has a substantially lower impact on rock art than tracing, and monitoring of archaeological features through SfM mapping can be used to identify conservation priorities (Plets et al 2012).…”
Section: Photogrammetry and Structure From Motion (Sfm)mentioning
Structure from motion (SfM) mapping is a photogrammetric technique that offers a cost-effective means of creating three-dimensional (3-D) visual representations from overlapping digital photographs. The technique is now used more frequently to document the archaeological record. We demonstrate the utility of SfM by studying red scoria bodies known aspukaofrom Rapa Nui (Easter Island, Chile). We created 3-D images of 50pukaothat once adorned the massive statues (moai) of Rapa Nui and compare them to 13 additionalpukaolocated in Puna Pau, the island's red scoriapukaoquarry. Through SfM, we demonstrate that the majority of these bodies have petroglyphs and other surface features that are relevant to archaeological explanation and are currently at risk of continued degradation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.