The automatic recognition of ceramics from only one photo: The ArchAIDE app

Anichini, Francesca; Dershowitz, Nachum; Dubbini, Nevio; Gattiglia, Gabriele; Itkin, Barak; Wolf, Lior

doi:10.1016/j.jasrep.2020.102788

Cited by 16 publications

(14 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e hardware improvement method has great limitations in both technology and cost [9]. In addition, in the process of image transmission and storage, factors such as undersampling and noise introduction may also cause the image resolution to drop.…”

Section: Introductionmentioning

confidence: 99%

“…The hardware production technology has reached the bottleneck; it is more difficult to improve, the resolution improvement effect is not obvious, and the volume of the sensor may also become larger [ 8 ]. The hardware improvement method has great limitations in both technology and cost [ 9 ]. In addition, in the process of image transmission and storage, factors such as undersampling and noise introduction may also cause the image resolution to drop.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

[Retracted] Texture Image Classification Method of Porcelain Fragments Based on Convolutional Neural Network

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The texture image decomposition of porcelain fragments based on convolutional neural network is a functional algorithm based on energy minimization. It maps the image to a suitable space and can effectively decompose the image structure, texture, and noise. This paper conducts a systematic research on image decomposition based on variational method and compressed sensing reconstruction of convolutional neural network. This paper uses the layered variational image decomposition method to decompose the image into structural components and texture components and uses a compressed sensing algorithm based on hybrid basis to reconstruct the structure and texture components with large data. In compressed sensing, to further increase each feature component, the sparseness of tight framework wavelet-based shearlet transform is constructed and combined with wave atoms as a joint sparse dictionary big data. Under the condition of the same sampling rate, this algorithm can retain more image texture details and big data than the algorithm. The production of big data that meets the characteristics of the background text is actually an image-based normalization method. This method is not very sensitive to the relative position, density, spacing, and thickness of the text. A super-resolution model for certain texture features can improve the restoration effect of such texture images. And the dataset extracted by the classification method used in this paper accounts for 20% of the total dataset, and at the same time, the PSNR value of 0.1 is improved on average. Therefore, taking into account the requirements for future big data experimental training, this article mainly uses jpg/csv two standardized database datasets after segmentation. This dataset minimizes the difference between the same type of base text in the same period to lay the foundation for good big data recognition in the future.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

[Retracted] Texture Image Classification Method of Porcelain Fragments Based on Convolutional Neural Network

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Both these aspects are crucial to the potential application of machine learning to domains where there are no perfect datasets. As compared to some other solutions to the problem of classifying archaeological ceramics, such as the ArchAIDE project [ 16 , 55 , 56 ], we do not rely on the user’s input beyond the photograph. As such, we aim to include expert knowledge in training the classifier only, so that as little expertise as possible is required from any potential end user, making any eventual tool more widely usable.…”

Section: Discussionmentioning

confidence: 99%

“…The list of points is used by each procedure to draw an axial section, which is rotated to generate a 3D mesh of points that corresponds to the rotationally symmetric shape of each vessel. Figure 6 shows a diagram of this process (see [16,55,56] for comparable processes). As we have previously discussed, almost all photographed real pots have at least some degree of damage.…”

Section: Pot Simulationsmentioning

confidence: 99%

“…In this paper, we propose and empirically verify through extensive computational experiments that much-needed information for training advanced large-scale AI models, including deep neural networks, can be extracted from abundantly available published knowledge of experts (in our case Roman ceramic specialists) and fed into model training pipelines [ 16 ]. Not only will this enable us to address the issue of insufficient data but also this will allow us to properly calibrate and control bias in the training data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning from Scarce Information: Using Synthetic Data to Classify Roman Fine Ware Pottery

Jareño

Helden

Mirkes

et al. 2021

Entropy

View full text Add to dashboard Cite

In this article, we consider a version of the challenging problem of learning from datasets whose size is too limited to allow generalisation beyond the training set. To address the challenge, we propose to use a transfer learning approach whereby the model is first trained on a synthetic dataset replicating features of the original objects. In this study, the objects were smartphone photographs of near-complete Roman terra sigillata pottery vessels from the collection of the Museum of London. Taking the replicated features from published profile drawings of pottery forms allowed the integration of expert knowledge into the process through our synthetic data generator. After this first initial training the model was fine-tuned with data from photographs of real vessels. We show, through exhaustive experiments across several popular deep learning architectures, different test priors, and considering the impact of the photograph viewpoint and excessive damage to the vessels, that the proposed hybrid approach enables the creation of classifiers with appropriate generalisation performance. This performance is significantly better than that of classifiers trained exclusively on the original data, which shows the promise of the approach to alleviate the fundamental issue of learning from small datasets.

show abstract

Fuzzy Typological (Re)arrangement: a Prototype of Rethinking the Typology of Roman Tablewares from Sagalassos, Southwest Anatolia

Kafetzaki,

Poblome,

Aerts

2023

J Archaeol Method Theory

View full text Add to dashboard Cite

The automatic recognition of ceramics from only one photo: The ArchAIDE app

Cited by 16 publications

References 15 publications

[Retracted] Texture Image Classification Method of Porcelain Fragments Based on Convolutional Neural Network

[Retracted] Texture Image Classification Method of Porcelain Fragments Based on Convolutional Neural Network

Learning from Scarce Information: Using Synthetic Data to Classify Roman Fine Ware Pottery

Fuzzy Typological (Re)arrangement: a Prototype of Rethinking the Typology of Roman Tablewares from Sagalassos, Southwest Anatolia

Contact Info

Product

Resources

About