Transfer Learning Approach for Railway Technical Map (RTM) Component Identification
This work addresses the need for efficient railway management by digitizing existing technical maps, but it is incremental as it applies existing object detection and OCR methods to a new domain-specific dataset.
The paper tackles the problem of digitizing Railway Technical Maps (RTMs) from PDF images by proposing a system using deep learning and OCR to extract map components into formatted text files, with Faster-RCNN achieving the highest performance at 0.68 mAP and 0.76 F1 score.
The extreme popularity over the years for railway transportation urges the necessity to maintain efficient railway management systems around the globe. Even though, at present, there exist a large collection of Computer Aided Designed Railway Technical Maps (RTMs) but available only in the portable document format (PDF). Using Deep Learning and Optical Character Recognition techniques, this research work proposes a generic system to digitize the relevant map component data from a given input image and create a formatted text file per image. Out of YOLOv3, SSD and Faster-RCNN object detection models used, Faster-RCNN yields the highest mean Average Precision (mAP) and the highest F1 score values 0.68 and 0.76 respectively. Further it is proven from the results obtained that, one can improve the results with OCR when the text containing image is being sent through a sophisticated pre-processing pipeline to remove distortions.