Discrimination of Ceramic Types Using Digital Image Processing by Means of Morphological Filters

López, Patricia Rodríguez; Lira, Jorge; Hein, Irmgard

doi:10.1111/arcm.12083

Cited by 5 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They achieve an accuracy of 90%. Several other notable examples of image-based classification of ceramics that do not fall under the use of CNNs include Lopez, Lira, and Hein (2015), Hein et al (2018), andTyukin et al (2018).…”

Section: Previous Work: Cnn Applications In Archaeology and Geologymentioning

confidence: 99%

Ceramic Fabric Classification of Petrographic Thin Sections with Deep Learning

Lyons

2021

Journal of Computer Applications in Archaeology

View full text Add to dashboard Cite

Classification of ceramic fabrics has long held a major role in archaeological pursuits. It helps answer research questions related to ceramic technology, provenance, and exchange and provides an overall deeper understanding of the ceramic material at hand. One of the most effective means of classification is through petrographic thin section analysis. However, ceramic petrography is a difficult and often tedious task that requires direct observation and sorting by domain experts. In this paper, a deep learning model is built to automatically recognize and classify ceramic fabrics, which expedites the process of classification and lessens the requirements on experts. The samples consist of images of petrographic thin sections under cross-polarized light originating from the Cocal-period (AD 1000-1525) archaeological site of Guadalupe on the northeast coast of Honduras. Two convolutional neural networks (CNNs), VGG19 and ResNet50, are compared against each other using two approaches to partitioning training, validation, and testing data. The technique employs a standard transfer learning process whereby the bottom layers of the CNNs are pre-trained on the ImageNet dataset and frozen, while a single pooling layer and three dense layers are added to 'tune' the model to the thin section dataset. After selecting fabric groups with at least three example sherds each, the technique can classify thin section images into one of five fabric groups with over 93% accuracy in each of four tests. The current results indicate that deep learning with CNNs is a highly accessible and effective method for classifying ceramic fabrics based on images of petrographic thin sections and that it can likely be applied on a larger scale.

show abstract

Section: Previous Work: Cnn Applications In Archaeology and Geologymentioning

confidence: 99%

Ceramic Fabric Classification of Petrographic Thin Sections with Deep Learning

Lyons

2021

Journal of Computer Applications in Archaeology

View full text Add to dashboard Cite

show abstract

“…The method can give the satisfactory results on alumina ceramic images and ceramic tile images. Ananyev et al (2014) and Lopez et al (2015) both applied the morphological filter in the segmentation and quantification of microstructures in the ceramic images. Haha et al (2007) segmented the SEM (scanning electron microscopy) images of motar with a threshold segmentation method, extracted the microstructures under different grayscale range.…”

Section: Introductionmentioning

confidence: 99%

SEGMENTATION AND ANALYSIS METHOD FOR TWO-PHASE CERAMIC (HfB2-B4C) BASED ON THE DETECTION OF VIRTUAL BOUNDARIES

et al. 2019

View full text Add to dashboard Cite

Microstructure of a material stores the genesis of the material and shows various properties of the material. To efficiently analyse the microstructure of a material, the segmentation of different phases or constituents is an important step. However, in general, due to the microstructure’s complexity, most of segmentation is manually done by human experts. It is challenging to automatically segment the material phases and the microstructure. In this work, we propose a method which combines the the dilation operator, GLCM (gray-level co-occurrence matrix), Hough transform and DBSCAN (density-based spatial clustering of applications with noise) for phases segmentation in the examples of certain material of eutectic HfB2-B4C ceramics. In the segmented regions, the further analysis for the microstructural elements is done with DBSCAN. The experimental results show that the proposed method achieves 95.75% segmentation accuracy for segmenting phases and 86.64% correct classification rate for the microstructure in the segmented phases. These experimental results show that our method is effective for the difficult task of the both segmentation and classification of the microstructural characteristics.

show abstract

“…In the last years, even more works considered routinely digital image analysis to study archeological ceramic materials (e.g. Knappett et al, 2011;Aprile et al, 2014;Dal Sasso et al, 2014;Eramo et al 2014;Lopez et al, 2015;Thér, 2016). However, to our knowledge, at present no work is known in the field which is aimed to evaluate the possibilities of OM image analysis for classification and modal analysis, knowing its advantages and drawbacks, as compared to SEM image processing.…”

Section: Introductionmentioning

confidence: 99%

Classification of mineral inclusions in ancient ceramics: comparing different modal analysis strategies

Aprile

Castellano

Eramo

2018

Archaeol Anthropol Sci

View full text Add to dashboard Cite

Digital image analysis has recently emerged as a powerful tool for the analysis of the ceramic thin sections. By producing quantitative data, it increases the usefulness of ceramic petrography to address archaeological questions.Despite several works considering digital image analysis to study archaeological ceramic materials, so far no work has been proposed to evaluate the possibilities of optical microscopy (OM) image analysis for classification and modal analysis, knowing its advantages and drawbacks, as compared to scanning electron microscopy (SEM) image processing. In this work we propose an algorithm to count the mineral inclusions correctly classified by OM image analysis with respect to SEM images. The proposed algorithm is based on a matching mechanism applied to the regions of interest (ROIs) detected in the OM images according to the corresponding ROIs as detected in the SEM images.Moreover, a comparison with point counting on the same OM images is also provided to evaluate the pros and cons of each method. Two Holocene potsherds (8900-4200 BP) are considered as case study for modal analysis to identify and classify quartz, feldspars and carbonate aggregates as mineral inclusions.

show abstract

Discrimination of Ceramic Types Using Digital Image Processing by Means of Morphological Filters

Cited by 5 publications

References 11 publications

Ceramic Fabric Classification of Petrographic Thin Sections with Deep Learning

Ceramic Fabric Classification of Petrographic Thin Sections with Deep Learning

SEGMENTATION AND ANALYSIS METHOD FOR TWO-PHASE CERAMIC (HfB2-B4C) BASED ON THE DETECTION OF VIRTUAL BOUNDARIES

Classification of mineral inclusions in ancient ceramics: comparing different modal analysis strategies

Contact Info

Product

Resources

About