The field of scanned document image analysis has many challenges that lie in the diverse nature of document images and variations in their data representation. The aforementioned results in the fact that the field of document analysis still has a lot of room for improvement, especially by using newly developed techniques in the field of deep learning. In this paper, we will present an implementation of a solution for detecting and analyzing text data from scanned images of contracts written in Serbian language using Faster R-CNN Feature Pyramid networks from Detectron2. Further, we will explain the process that led to the creation of the tool, which includes the process of training the Detectron2 neural network, then the integration of the trained network with Layout Parser, and text extraction using Tesseract OCR for the Serbian language.