| Geologists involved in exploration and mining are tasked with capturing geological data from rock samples and data about the drilling and exploration activities undertaken to obtain these samples. Some measurements they take involve using simple devices and readers such as scales, hardness testers, GPS, thermometers etc. Many of these measuring instruments have LCD displays and the geologists typically transcribe readings manually into software on a tablet or laptop. |
|
Our hypothesis is that a system can be developed where a camera can be used to take an image of the LCD screen of a measuring instrument, and the visual cues, such as the edges of the display, can be used to orientate and extract a value or values from the image. These values can then be used directly by the software, making the manual transcription no longer necessary. Just as a human observer can accurately read and record values from a display, a system could be developed to do the same.
The objective of the project is to determine whether the technology that exists today can be used to develop a system that accurately extracts values from images of LCD displays. At its simplest, as a proof of concept, the project should demonstrate the feasibility of value recognition for known instruments, at its most complex we envisage an AI solution capable of learning and accurately extracting values from new instrument displays. This stretch goal is unlikely for the project, but the project may provide the foundation for the development of such as system.