Replacing paper with photo collection

June 25, 2018

For a famous company responsible for the management and development of 95% of the network of electricity distribution in France, the Paris Digital Lab students worked on a project that aimed to replace paper collection with a photo collection of its heritage data.

The objective of the project was therefore to determine whether the Artificial Intelligence was able to identify specific hardware specifications from pictures. Thus, we were led to use Tesseract to perform the Optical Character Recognition on label photos. In parallel, research methods of field in a text, pre-image processing and result analysis were developed to operate and optimize the performance of the algorithm.