Digital Libraries Without Databases: The Bleek and Lloyd Collection

The Outreach of Digital Libraries: A Globalized Resource Network

Robinson

et al. 2012

Self Cite

Abstract. There is an ever-increasing amount of digital content being generated that needs to be well-organised, preserved and made accessible. The majority of generic repository software tools that currently exist are, arguably, overly complex, thus making collections difficult to manage and maintain in resource constrained environments. A possible solution to this problem would, in part, require designing digital library tools and services that are simple and easy to manage. This paper describes a digital library system that is based on a set of design decisions aimed at simplifying repository software architectures. The proposed system makes use of a hierarchical file-store for storage of digital objects. Evaluation of the system by means of a user experience study was conducted to investigate the usefulness of the system, its relative ease of use and what effect, if any, the architecture would have on the user experience. Experimental results showed that users found the system useful, effective and easy to use and that the architecture did not appear to negatively influence the user experience.

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Bonolo: A General Digital Library System for File-Based Collections

Phiri

The Outreach of Digital Libraries: A Globalized Resource Network

Robinson

et al. 2012

Self Cite

“…These stories, along with art and dictionaries were preserved and have come to be known as the Bleek and Lloyd collection. The collection consists of 157 notebooks containing 14128 pages, 752 drawings and over 14000 dictionary pages for the |xam dictionary [15]. There are three types of objects in the |xam dictionary: envelopes, slips and entries.…”

Section: Bleek and Lloyd Collectionmentioning

confidence: 99%

“…In 2007, Suleman [15] built a digital library system for the notebooks and the art in the Bleek and Lloyd collection using an XML-centric solution. An XML-centric solution was chosen for this archive because it: required no installation from the end user; was platform independent; allowed for easier processing; and had long term preservation benefits.…”

Section: Bleek and Lloyd Collectionmentioning

confidence: 99%

Translating handwritten bushman texts

Proceedings of the 10th Annual Joint Conference on Digital Libraries

Suleman

2010

Self Cite

The Bleek and Lloyd Collection is a collection of artefacts documenting the life and language of the Bushman people of southern Africa in the 19th century. Included in this collection is a handwritten dictionary that contains English words and their corresponding |xam Bushman language translations. This dictionary allows for the manual translation of |xam words that appear in the notebooks of the Bleek and Lloyd collection. This, however, is not practical due to the size of the dictionary, which contains over 14000 entries. To solve this problem a content-based image retrieval system was built that allows for the selection of a |xam word from a notebook and returns matching words from the dictionary. The system shows promise with some search keys returning relevant results.

“…The Bleek and Lloyd Collection [22] is a collection of notebooks that document the language and culture of the |Xam and !Kun people who lived in Southern Africa in the late 19th century. The collection has been digitised and digital library systems have been created for preserving this collection and providing access to it via the Web [22,26].…”

Section: Introductionmentioning

confidence: 99%

A comparison of machine learning techniques for handwritten |Xam word recognition

Proceedings of the South African Institute for Computer Scientists and Information Technologists Conference

Suleman

Paihama

2013

Self Cite

The Bleek and Lloyd collection contains 19th century handwritten notebooks that document the language and culture of the |Xam-speaking people who lived in Southern Africa. Access to this rich data could be enhanced by transcriptions of the text; however, the complex diacritics used in the notebooks complicate the process of transcription. Machine learning techniques could be used to perform this transcription, but it is not known which techniques would produce the best results. This paper thus reports on a comparison of 3 popular techniques applied to this problem: artificial neural networks (ANN); hidden Markov models (HMM); and support vector machines (SVM). It was found that an SVM-based classifier using histograms of oriented gradients as features resulted in the best word recognition accuracy of 58.4%. Furthermore, it was found that most feature extraction parameters did not have a large effect on recognition accuracy and that the SVM-based recognisers outperform both ANN-and HMM-based recognisers.