Periodic Reporting for period 2 - ArchAIDE (Archaeological Automatic Interpretation and Documentation of cEramics)
Periodo di rendicontazione: 2017-06-01 al 2019-05-31
Pottery classification is of fundamental importance for the comprehension and dating of the archaeological contexts, and for understanding production, trade flows and social interactions, but it requires complex skills and it is a very time consuming activity, both for researchers and professionals. The objectives of ArchAIDE are to support the work of archaeologists with innovative computer-based tools, able to provide the user with features for the semi-automatic description and matching of potsherds over the huge existing ceramic catalogues. This tool would revolutionise archaeologists habits, behaviours and expectations, would meet real user needs and generate economic benefits, reducing time and costs, would create societal benefits from cultural heritage, improving access, re-use and exploitation of the digital cultural heritage in a sustainable way.
These objectives will be achieved through the development of:
- an as-automatic-as-possible procedure to transform the paper catalogues in a digital description, to be used as a data pool for search and retrieval process;
- a tool that will support archaeologists in recognising potsherds during excavation and post excavation analysis, through an easy-to-use interface and efficient algorithms for search and retrieval of the visual/geometrical correspondences;
- an automatic procedure to derive a complete potsherd’s identity card by transforming the data collected into a formatted electronic document, printable or visual;
- a web-based real-time data visualization to improve access to archaeological heritage and generate new understanding;
- an open archive to allow the archival and re-use of archaeological data, transforming them into common heritage and permitting economic sustainability.
These objectives will be achieved through the development of:
- an as-automatic-as-possible procedure to transform the paper catalogues in a digital description, to be used as a data pool for search and retrieval process;
- a tool that will support archaeologists in recognising potsherds during excavation and post excavation analysis, through an easy-to-use interface and efficient algorithms for search and retrieval of the visual/geometrical correspondences;
- an automatic procedure to derive a complete potsherd’s identity card by transforming the data collected into a formatted electronic document, printable or visual;
- a web-based real-time data visualization to improve access to archaeological heritage and generate new understanding;
- an open archive to allow the archival and re-use of archaeological data, transforming them into common heritage and permitting economic sustainability.
Currently, the project has ended its first year. Work Packages 1, 3, 4, 5, 6, 7, 9, and 10 are active. WP2 is ended on M8, whereas WP8 (Test and assessment of the overall system on application scenarios) will begin on M22. The project began on 1st June 2016 with WPs 1 Management, 9 Communication/Public engagement/Innovation, 10 Archiving and Dissemination, and 2 Methodologies, specification and design. WP2 was dedicated to define the working scenario in archaeological investigation and pottery processing, the database structure, the selection of the pottery catalogues and of test bed cases. The achievement of MS1 Preliminary report about the archaeological and technical specification of the system on M4 gave the start to WPs 3, 4 and 6. Using the ADS Roman Amphorae database as a point of departure, WP3 Creation of the Application Database has completed the database design and has begun on incorporating multilingual vocabularies of pottery characteristics. WP4 Technologies for digitisation of catalogues evaluated different solutions for OCR, in order to analyse flexibility, amount of languages supported, extendibility. The advanced OCR implementation (that aims at automatically filling the database structure) is currently under finalisation. An automatic application that is able to analyse a scanned version of the drawing has been implemented. In addition, a 3D representation of the drawing is created automatically. The achievement of Milestones 2 First Version of the database ready for being populated and 3 First validated version of the technologies for the digitization of paper catalogues ready to be used for starting DB population on M8 permitted to start WP5 Population of the Database. Once defined the workflow for populating the database, WP 5 began to digitise catalogues and photograph potsherds for training the algorithms. After a first manual population of database to see functionality and bugs, the database was automatically populated with the data from the ADS Roman Amphorae digital resource. WP6 Shape and image-based similarity search and retrieval has focused on building synthetic training data of 3D vessels as well as simulating breaking them and obtaining matching sherds. This data will be used in order to develop the algorithms necessary for matching sherds with catalogue-based drawings of vessels. While the database of ceramics was populated, an initial overview of the data was done to identify the sort of similarity to be detected. When doing so, it was discovered that there are some problems with appearance based similarity. Consequently, the maximum effort was allocated on shape-based similarity, which allows much more freedom in gaining the data. WP7 The mobile tool and Front end Desktop Application achieved the Reference Database API for the retrieval of the ceramic types from the mobile tool through the search engine produced in WP6, started the implementation of the core components of the mobile tool, and of the “Result database” (server database supporting the mobile tool). WPs 1, 9, and 10 will last during all the project lifetime. WP1 guarantees the correct implementation of the overall management, the monitoring of the project and its activities, and the achievement of the project objectives. WP9 defined the communication strategies in order to engage a large audience supported by a strong social media communication. The logo and the visual identity of the project have been designed , as well as a line of products to promote the project to a wider public. WP10 started the dissemination and promotion of the results of the project, and worked to make the project collaborative and transparent to researchers in the archaeological domain and beyond.
The project expects impacts on archaeological professional labour market, archaeological research, and training and education in archaeology.
As for the archaeological professional labour market, it is estimated that approximately 33,000 archaeologists now work across Europe, 11,350 in the USA, 6,255 in Japan, and between 500 and 600 in Australia. This information underlines the world-wide potential market of ArchAIDE. ArchAIDE will give to private companies the possibility to reduce time and costs, or to redistribute and optimize the activity of professionals, bringing positive effect on the whole sector.
As for archaeological research, ArchAIDE will move archaeologists from spending time on routine tasks like drawing and classification to create background knowledge and enable new knowledge generation, permitting to develop new research field in archaeology. ArchAIDE allows the creation of new archaeological data that will be made available both through the interactive app (supporting data access and visualization) and published as open data. In this way, ArchAIDE will help to broaden the horizons of archaeological research (new typological studies about archaeological pottery, trade flows and their economic impact, geographical diffusion, etc).
As for education and training, students complete their studies with training activities leaded by Universities or Archaeological companies. In such a context, ArchAIDE will become an extra training tool.
Besides, we have to consider also the millions of global citizens that approach archaeology in a non-professional manner and in all those related areas (educational, touristic, entrepreneurial, etc) that draw on open archaeological data to produce derivatives content such as storytelling, educational tools, etc. Supporting ordinary people will increase awareness and cultural interest in the population.
As for the archaeological professional labour market, it is estimated that approximately 33,000 archaeologists now work across Europe, 11,350 in the USA, 6,255 in Japan, and between 500 and 600 in Australia. This information underlines the world-wide potential market of ArchAIDE. ArchAIDE will give to private companies the possibility to reduce time and costs, or to redistribute and optimize the activity of professionals, bringing positive effect on the whole sector.
As for archaeological research, ArchAIDE will move archaeologists from spending time on routine tasks like drawing and classification to create background knowledge and enable new knowledge generation, permitting to develop new research field in archaeology. ArchAIDE allows the creation of new archaeological data that will be made available both through the interactive app (supporting data access and visualization) and published as open data. In this way, ArchAIDE will help to broaden the horizons of archaeological research (new typological studies about archaeological pottery, trade flows and their economic impact, geographical diffusion, etc).
As for education and training, students complete their studies with training activities leaded by Universities or Archaeological companies. In such a context, ArchAIDE will become an extra training tool.
Besides, we have to consider also the millions of global citizens that approach archaeology in a non-professional manner and in all those related areas (educational, touristic, entrepreneurial, etc) that draw on open archaeological data to produce derivatives content such as storytelling, educational tools, etc. Supporting ordinary people will increase awareness and cultural interest in the population.