Status: taken
Supervisor: Sebastian Zambanini

Problem Statement

The INDIGO project aims to document and analyze the graffiti along Vienna’s Donaukanal. However, indexing graffiti images by written text is a time-consuming task. Hence, a system which provides automatic guesses for written text would be highly beneficial.

Goal

The goal of this work is to explore and examine methods that can be used to recognize text in graffiti images.

Workflow

Literature Review – getting to know the methods
Data Preparation
Implementation
Evaluation
Written Report/Thesis and final presentation

Literature

[1] Xiaoxue Chen, Lianwen Jin, Yuanzhi Zhu, Canjie Luo, and Tianwei Wang.  “Text Recognition in the Wild: A Survey” ACM Comput. Surv. 54, 2, Article 42, 2022, https://doi.org/10.1145/3440756

[2] Ruijie Yan, Liangrui Peng, Shanyu Xiao, Gang Yao, “Primitive Representation Learning for Scene Text Recognition” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 284-293, https://doi.ieeecomputersociety.org/10.1109/CVPR46437.2021.00035