Contract notice: Optical-character-recognition Tender - 40627852

Object of the contract
Optical-character-recognition (OCR) software development services
Description: Contract notice: Optical-character-recognition (OCR) software development services
Authority Type: Other
Contact Nature: Services
Procedure: Open procedure
Document: Contract notice
Regulation: European Economic Area (EEA), with participation by GPA countries
Award criteria: The most economic tender
CPV code: 72212313, 72222300, 72300000, 72311000, 72312200, 79999100, 72212313, 72222300, 72300000, 72311000, 72312200, 79999100
CPV Description: Optical-character-recognition (OCR) software development services.
Information technology services.
Data services.
Computer tabulation services.
Optical character recognition services.
Scanning services.
Microfilm Digitalisation, including OCR Processing and Structure Analysis
Reference Number : 2019/581
The National Library of Norway would like to keep the content of the physical collections for the future through the digitalisation programme. At the same time it would like to form the basis for future digital services on nb.no
The National Library of Norway`s microfilm collection consists of more than 70 000 microfilm rolls. The material is 35 mm, unperforated, black and white polyester microfilm.
The microfilms were produced in the period 1950-2009. The condition and quality will vary somewhat, depending on when and where the films were produced. Tenderers must describe in the tender how they can digitalise microfilm of varying quality. It is particularly important to get clarify any limitations that the National Library of Norway must include in their calculations when large parts of the microfilm collection is to be digitalised. As far as we know, there can be challenges with the physical condition or the contract of the films for approx. 5 % of the materials.
A microfilm roll normally includes between 500 and 1400 pictures, each one of a single newspaper page. The microfilm format is unperforated 35 mm film, which is normally not longer than 30 m.
The contracting authority estimates that the digitalisation service will include approx. 2 000 000-4 000 000 pages per annum, depending on the available budget.
Digitalisation test:
Tenderers who want to submit offers related to microfilm digitisation must, together with the tender, deliver a digitised image of an equivalent quality to their offer. The sample image must be digitised from a target film (test target microfilm), that the National Library will provide to the tenderer on request. The request for test target microfilm must be directed to the contact person for the competition.
The digitised test target microfilm must reproduce the target (the test target) as good as possible. It must be correctly exposed and have a good level of focus in order to ensure readability.
The targets (the test targets) must be returned to the National Library as quickly as possible after the test scannings have been implemented.
The digitised images will be assessed in regard to quality through the help of Golden Thread analysis software and the evaluation will be part of the tender evaluation.
For the OCR process, the sample image of newspaper pages digitised from microfilm will be made available.
For the entire collection, there will be newspaper pages with both Latin and Gothic fonts, or a combination of both parts, depending on when the newspaper was published. Most of the newspapers were published in Norwegian, in one of the official Norwegian written languages, Nynorsk or Bokmal. The oldest newspapers from before 1907 were most likely published in Danish. There may be the occasional newspaper in English. However, these are rare.
The OCR process must safeguard word accuracy of at least 90 % in regard to Latin letters and 80 % when concerning Gothic letters.
Metadata: OCR metadata must contain relevant information from OCR processing and must contain information about:
— the OCR technology,
— the degree of accuracy for each character, work and page,
— the position of each work on the page.
The OCR processed newspaper pages will be assessed qualitatively and the assessment will be part of the tender evaluation.
Internet address (URL): https://permalink.mercell.com/118426363.aspx