Transfer Learning Approach for Railway Technical Map (RTM) Component Identification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rumalshan, Obadage Rochana, Weerasinghe, Pramuka, Shaheer, Mohamed, Gunathilake, Prabhath, Dayaratna, Erunika
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909208203493376
author Rumalshan, Obadage Rochana
Weerasinghe, Pramuka
Shaheer, Mohamed
Gunathilake, Prabhath
Dayaratna, Erunika
author_facet Rumalshan, Obadage Rochana
Weerasinghe, Pramuka
Shaheer, Mohamed
Gunathilake, Prabhath
Dayaratna, Erunika
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13229
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Transfer Learning Approach for Railway Technical Map (RTM) Component Identification
Rumalshan, Obadage Rochana
Weerasinghe, Pramuka
Shaheer, Mohamed
Gunathilake, Prabhath
Dayaratna, Erunika
Computer Vision and Pattern Recognition
Artificial Intelligence
Digital Libraries
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.
title Transfer Learning Approach for Railway Technical Map (RTM) Component Identification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Digital Libraries
url https://arxiv.org/abs/2405.13229