Turning Pixels Into Data: Imaging for Accessibility

*** NEW – May 26, 2020

An attachment has been added. The document contains questions and answers related to the Challenge.*******************************************************

May 21, 2020

An attachment has been added. The document contains questions and answers related to the Challenge.*******************************************************

May 15, 2020

The closing date for this challenge has been extended to June 2, 2020 at 14:00 EDT. **************************************************** May 8, 2020 New attachment has been added. Please read the document as it provides important information pertaining to the submission of your proposal. ******************************** April 14 2020 Due to the issues surrounding COVID19, we have decided to extend the solicitation closing date until May 21, 2020. This Challenge Notice is issued under the Innovative Solutions Canada Program (ISC) Call for Proposals 003 (EN578-20ISC3). For general ISC information, Bidders can visit the ISC website. Please refer to the Solicitation Documents which contain the process for submitting a proposal. Steps to apply: Step 1: read this challenge Step 2: read the Call for Proposals Step 3: propose your solution here Challenge title: Turning pixels into data: Imaging for Accessibility CHALLENGE SPONSOR: Public Service and Procurement Canada Funding Mechanism: Contract MAXIMUM CONTRACT VALUE AND DURATION: Multiple contracts could result from this Challenge. The maximum funding available for any Phase 1 contract resulting from this Challenge is $150,000.00 CAD excluding applicable taxes, shipping, travel and living expenses, as required, for up to 6 months (excluding submission of the final report). Estimated number of Phase 1 contracts: 2 The maximum funding available for any Phase 2 contract resulting from this Challenge is $1,000,000.00 CAD excluding applicable taxes, shipping, travel and living expenses, as required, for up to 24 months (excluding submission of the final report). Only eligible businesses that have successfully completed Phase 1 will be considered for Phase 2. Estimated number of Phase 2 contracts: 1 This disclosure is made in good faith and does not commit Canada to contract for the total approximate funding. Final decisions on the number of Phase 1 and Phase 2 awards will be made by Canada on the basis of factors such as evaluation results, departmental priorities and availability of funds. TRAVEL:  For Phase 1 it is anticipated that two meetings will require the successful bidder(s) to travel to the location identified below: Kick-off meeting Matane, QC Progress Update Videoconference/Teleconference Final Review Meeting Matane, QC Challenge Summary Statement PSPC's Document Imaging Solutions Centre (DISC) is seeking to develop innovative capture solutions to improve accessibility of digitized documents and increase production capabilities, thus providing citizens and government organizations with more cost-effective, accessible and adapted digital information. Challenge Statement In light of the recently adopted Accessible Canada Act, DISC is facing technological challenges in providing digitized documents with improved readability for those with disabilities. Current imaging technologies for high-volume production are not designed to produce accessible documents that include proper tagging, image description and reading order. On the other hand, accessibility remediation solutions require significant user input and validation to produce accessible documents, and are therefore unfit for high-volume production environments. DISC is looking for technological solutions that make use of Artificial Intelligence (AI) and/or Robotic Process Automation (RPA) to integrate to our current imaging processes, with the objectives of producing documents in standard accessible formats (specifically HTML5 and ePub3) that respect all accessibility guidelines, while improving our accuracy rate and reducing costs associated with quality assurance. Essential Outcomes Proposed solutions must:

integrate to current Government of Canada imaging infrastructure (see Annex 1 for current workflow and technologies); allow for the secure processing of Protected B and Secret documents; make possible the conversion of both digitally created and scanned PDF documents into well-structured, properly tagged and fully compliant HTML5 or ePub3 files; make use of Optical Character Recognition (OCR), Artificial Intelligence (AI), Robotic Process Application (RPA) or any other relevant technology to extract pertinent and contextualized information from digitized documents, and produce accessible files that respect European Union Standard EN 301-549 (2018); integrate remediation console and revision tools to support validation of tagging, alternative text, tables, charts and other required descriptive entries; be scalable to provide high-volume imaging or conversion capacity; integrate solid reporting capacity and accessibility validation tools to provide feedback on automated processes.

Additional Outcomes Proposed solutions should:

provide basic quality control automations (page flipping, identification of scanning issues, rescan functionalities) while providing interactive interfaces to accelerate quality insurance operations and support data entry (when required); facilitate accessibility remediation for non-expert remediation agents through the use of a desktop application. This application should be designed to support manual actions such as tagging, alternate text integration, establishment of reading order as well as accessibility assessment. improve the overall accuracy of our capture processes and reduce the use of manual data entry, verification and corrections.

Background and Context As a service provider for a large number of federal organizations, DISC wants to respond to the recently-adopted Accessible Canada Act by offering value-added imaging services that include accessible file formats and adapted content in an environment of high-volume production and a 100% cost-recovery model. There are currently no integrated solutions to this task, other than highly labor-intensive data analysis and entry. Our current imaging workflow includes Optical Character Recognition (OCR) capacity and creates PDF files that are manually scanned for quality control and data entry, when required. PSPC is interested in a solution to make use of Artificial Intelligence (AI) (including deep learning and image recognition) and robotic automation to extract pertinent and contextualized information from digitized document and produce fully functional, well-structured and properly tagged accessible documents.  The three main difficulties encountered during conversion to an accessible format are: (a) the recognition and alt tagging for photos and images; (b) the identification and description of bar graphs, pie charts or any color-coded graph; and, (c) interactions with large tables and other non-regular content. The current market for our services is limited to federal organizations, but may expand in the near future to include other levels of government, notably provincial and municipal entities as well as foreign governments. Canada’s intention to gain leadership in areas of accessibility and open governance provide a unique opportunity to develop solutions that other entities will be requiring as regulations and policies are adopted. ENQUIRIES All enquiries must be submitted in writing to TPSGC.SIC-ISC.PWGSC@tpsgc-pwgsc.gc.ca no later than ten calendar days before the Challenge Notice closing date. Enquiries received after that time may not be answered.