The absence of large scale datasets with pixel–level supervisions is a significant obstacle for the training of deep convolutional networks for scene text segmentation. For this reason, synthetic data generation is normally employed to enlarge the training dataset. Nonetheless, synthetic data cannot reproduce the complexity and variability of natural images. In this paper, a weakly supervised learning approach is used to reduce the shift between training on real and synthetic data. Pixel–level supervisions for a text detection dataset (i.e. where only bounding–box annotations are available) are generated. In particular, the COCO–Text–Segmentation (COCO_TS) dataset, which provides pixel–level supervisions for the COCO–Text dataset, is created and released. The generated annotations are used to train a deep convolutional neural network for semantic segmentation. Experiments show that the proposed dataset can be used instead of synthetic data, allowing us to use only a fraction of the training samples and significantly improving the performances.

Bonechi, S., Andreini, P., Bianchini, M., Scarselli, F. (2019). COCO_TS Dataset: Pixel–Level Annotations Based on Weak Supervision for Scene Text Segmentation. In K.P. Tetko I.V. (a cura di), Artificial Neural Networks and Machine Learning – ICANN 2019: Image Processing. ICANN 2019 (pp. 238-250). Springer-Verlag [10.1007/978-3-030-30508-6_20].

COCO_TS Dataset: Pixel–Level Annotations Based on Weak Supervision for Scene Text Segmentation

Bonechi, Simone;Andreini, Paolo;Bianchini, Monica;Scarselli, Franco
2019-01-01

Abstract

The absence of large scale datasets with pixel–level supervisions is a significant obstacle for the training of deep convolutional networks for scene text segmentation. For this reason, synthetic data generation is normally employed to enlarge the training dataset. Nonetheless, synthetic data cannot reproduce the complexity and variability of natural images. In this paper, a weakly supervised learning approach is used to reduce the shift between training on real and synthetic data. Pixel–level supervisions for a text detection dataset (i.e. where only bounding–box annotations are available) are generated. In particular, the COCO–Text–Segmentation (COCO_TS) dataset, which provides pixel–level supervisions for the COCO–Text dataset, is created and released. The generated annotations are used to train a deep convolutional neural network for semantic segmentation. Experiments show that the proposed dataset can be used instead of synthetic data, allowing us to use only a fraction of the training samples and significantly improving the performances.
978-3-030-30507-9
978-3-030-30508-6
Bonechi, S., Andreini, P., Bianchini, M., Scarselli, F. (2019). COCO_TS Dataset: Pixel–Level Annotations Based on Weak Supervision for Scene Text Segmentation. In K.P. Tetko I.V. (a cura di), Artificial Neural Networks and Machine Learning – ICANN 2019: Image Processing. ICANN 2019 (pp. 238-250). Springer-Verlag [10.1007/978-3-030-30508-6_20].
File in questo prodotto:
File Dimensione Formato  
COCO_TS_Dataset_Pixel-level_Annotations_Based_on_Weak_Supervision_for_Scene_Text_Segmentation.pdf

non disponibili

Tipologia: Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 4.98 MB
Formato Adobe PDF
4.98 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11365/1080152