Naslov
Review of chart image detection and classification

Autori
Bajić, Filip ; Job, Josip

Izvornik
International journal on document analysis and recognition (1433-2833) 1 (2023); 1, 22

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Chart classification ; Chart image processing ; Image processing and computer vision ; Information visualization ; Review and evaluation

Sažetak
This paper presents a complete review of different approaches across all components of the chart image detection and classification up to date. A set of 89 scientific papers is collected, analyzed, and enlisted into four categories: chart-type classification, chart text processing, chart data extraction, and chart description generation. Detailed information about problem formulation and a research field is provided, and an overview of used methods in each category. Each paper's contribution is noted, including the essential information for authors in this research field. In the end, a comparison is made between the reported results. The state-of-the-art methods in each category are described, and a research direction is given. We have also analyzed the open challenges that still exist and require the author's attention.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA