A New Genetic Algorithm‐Based Network for Text Localization in Degraded Social Media Images

Palaiahnakote, Shivakumara; Kumar, Chandrahas Pavan; Aggarwal, Pranjal; Sharma, Shubham; Chandana, Pasupuleti; Basavanna, Mahadveppa; Pal, Umapada

Abstract

ABSTRACTThis paper presents a novel model for understanding social image content through text localization. For text localization, we explore maximally stable extremal regions (MSER) for detecting components that work by clustering pixels with similar properties. The output of component detection includes several non‐text components due to the degradations of social media images. To select the best components among many, we explore the genetic algorithm by convolving different kernels with components, which results in a feature matrix that is further fed to EfficientNet for choosing actual text components. Therefore, the proposed model is called genetic algorithm based network for text localization in degraded social media images (TLDSMI). For evaluating text localization, we consider the images of the standard dataset of natural scenes by uploading and downloading from different social media platforms, namely, WhatsApp, Telegram, and Instagram. The effectiveness of our method is shown by testing on original and degraded standard datasets. For example, for the degraded images of different complexities including degradations caused by social media platforms, the proposed method performs well in almost all situations. In addition, the proposed model achieves the best F1‐Score, 0.76, 0.77, 0.70, and 0.78 for the degraded images of CUTE, ICDAR 2013, Total‐Text, and CTW1500, respectively, compared to the state‐of‐the‐art methods.

• Journal Article Type: Article
• Acceptance Date: Feb 11, 2025
• Online Publication Date: Feb 24, 2025
• Publication Date: 2025-01
• Deposit Date: Feb 28, 2025
• Publicly Available Date: Mar 3, 2025
• Journal: IET Image Processing
• Print ISSN: 1751-9659
• Electronic ISSN: 1751-9667
• Publisher: Institution of Engineering and Technology (IET)
• Peer Reviewed: Peer Reviewed
• Volume: 19
• Issue: 1
• DOI: https://doi.org/10.1049/ipr2.70030