Pelee-Text plus plus : A Tiny Neural Network for Scene Text Detection

Author(s)

Cordova, Manuel ^[1] ; Pinto, Allan ^[1] ; Pedrini, Helio ^[1] ; Torres, Ricardo da Silva ^[2]

Affiliation

^[1] Univ Estadual Campinas, Inst Comp, BR-13083852 Campinas - Brazil

^[2] NTNU Norwegian Univ Sci & Technol, Fac Informat Technol & Elect Engn, Dept ICT & Nat Sci, N-6009 Alesund - Norway

• Document type: Journal article
• Source: IEEE ACCESS; v. 8, p. 223172-223188, 2020.
• Web of Science Citations: 0

Abstract

Scene text detection has become an important field in the computer vision area due to the increasing number of applications. This is a very challenging problem as textual elements are commonly found in ``noisy{''} and complex natural scenes. Another issue refers to the presence of texts encoded into different languages within the same image. State-of-the-art solutions rely on the use of deep neural network approaches or even ensembles of them. However, such solutions are associated with ``heavy{''} models, which are computationally expensive in terms of memory and storage footprints, which hampers their use in real-time mobile applications. In this work, we introduce Pelee-Text++, a lightweight neural network architecture for multi-lingual multi-oriented scene text detection, especially tailored to running on devices with computational restrictions. Additionally, to the best of our knowledge, this is the first work to evaluate the performance of text detection methods in commercial smartphones. Over this scenario, Pelee-Text++ processes 2.94 frames per second and it is the only evaluated approach that did not cause memory issues on smartphones, even using an input image of 1024 x 1024 pixels. Our proposal achieves a promising trade-off between efficiency and effectiveness, with a model size of 27 Megabytes and F-measure of 91.20%, 85.78%, 81.72%, 80.30%, 82.53% and 66.51% on ICDAR 2011, ICDAR 2013, ICDAR 2015, MSRA-TD500, ReCTS 2019 and Multi-lingual 2019 datasets, respectively. (AU)

• FAPESP's process: 17/20945-0 - Multi-user equipment approved in great 16/50250-1: local positioning system
• Grantee: Sergio Augusto Cunha
• Support Opportunities: Multi-user Equipment Program
• FAPESP's process: 19/17729-0 - Data-driven approaches for soccer match analysis: an e-Science perspective
• Grantee: Paulo Roberto Pereira Santiago
• Support Opportunities: Regular Research Grants
• FAPESP's process: 16/50250-1 - The secret of playing football: Brazil versus the Netherlands
• Grantee: Sergio Augusto Cunha
• Support Opportunities: Research Projects - Thematic Grants
• FAPESP's process: 19/22262-3 - Large volume reconstruction: high precision system for position detection in sports
• Grantee: Paulo Roberto Pereira Santiago
• Support Opportunities: Organization Grants - Scientific Meeting
• FAPESP's process: 19/16253-1 - Unraveling the secret of Brazilian and Dutch soccer by capturing successful elements of playing style and playing strategies
• Grantee: Allan da Silva Pinto
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• FAPESP's process: 14/12236-1 - AnImaLS: Annotation of Images in Large Scale: what can machines and specialists learn from interaction?
• Grantee: Alexandre Xavier Falcão
• Support Opportunities: Research Projects - Thematic Grants
• FAPESP's process: 15/24494-8 - Communications and processing of big data in cloud and fog computing
• Grantee: Nelson Luis Saldanha da Fonseca
• Support Opportunities: Research Projects - Thematic Grants