View Source

| *Title* | SO19 Recognize inaccurate graphical image files based on a pattern-set |
| *Detailed description* | A possible solution is to set up a training-set of inaccurate scanned image files (cropping, or other bad image quality) and then compare image files (e.g. new versions of scanned book pages) with the training-set to detect bad image quality. Based on the result, a decision on which version of a scan should be kept, can be taken programmatically.\\
Details will follow.\\
\\ |
| *[Solution Champion|SP:Responsibilities of the roles described on these pages]* \\ | _Who owns the Solution? Identify the owner with a link to their contact page on the SCAPE Sharepoint site, as well as identifying their institution in brackets. Eg:_ [Schlarb Sven|] (ONB) |
| *Corresponding Issue(s)* \\ | _A bulletted list of links to Issues to which this provides a Solution_ \\ |
| *myExperiment Link* \\ | _A link to a corresponding workflow on_ _[myExperiment|]_ \\ |
| *Tool Registry Link* \\ | _A link to information about the tool itself. Ideally this should point to an entry in_ _[the OPF Tool Registry|]_ [Click here if you need to create a new Tool Registry entry|]\\ |
| *Evaluation* \\ | _Any notes or links on how the solution performed. This will be developed and formalised by the Testbed SP._ \\ |