All Outputs (16)

Soft set-based MSER end-to-end system for occluded scene text detection, recognition and prediction (2024)
Journal Article
Das, A., Palaiahnakote, S., Banerjee, A., Antonacopoulos, A., & Pal, U. (2024). Soft set-based MSER end-to-end system for occluded scene text detection, recognition and prediction. Knowledge-Based Systems, https://doi.org/10.1016/j.knosys.2024.112593

The presence of unpredictable occlusions on natural scene text is a significant challenge, exacerbating the difficulties already posed on text detection and recognition by the variability of such images. Addressing the need for a robust, consistently... Read More about Soft set-based MSER end-to-end system for occluded scene text detection, recognition and prediction.

TTS: Hilbert Transform-based Generative Adversarial Network for Tattoo and Scene Text Spotting (2024)
Journal Article
Banerjee, A., Palaiahnakote, S., Antonacopoulos, A., Pal, U., Lu, T., & Canet, J. L. (2024). TTS: Hilbert Transform-based Generative Adversarial Network for Tattoo and Scene Text Spotting. IEEE Transactions on Multimedia, 1-15. https://doi.org/10.1109/tmm.2024.3378458

Text spotting in natural scenes is of increasing interest and significance due to its critical role in several applications, such as visual question answering, named entity recognition and event rumor detection on social media. One of the newly emerg... Read More about TTS: Hilbert Transform-based Generative Adversarial Network for Tattoo and Scene Text Spotting.

A new deep CNN for 3D text localization in the wild through shadow removal (2023)
Journal Article
Shivakumara, P., Banerjee, A., Nandanwar, L., Pal, U., Antonacopoulos, A., Lu, T., & Blumenstein, M. (2024). A new deep CNN for 3D text localization in the wild through shadow removal. Computer Vision and Image Understanding, 238, https://doi.org/10.1016/j.cviu.2023.103863

Text localization in the wild is challenging due to the presence of 2D and 3D texts, the presence of shadows, arbitrary orientated text with non-linear arrangements, varying lighting conditions as well as complex background. This paper proposes the f... Read More about A new deep CNN for 3D text localization in the wild through shadow removal.

Text line segmentation from struck-out handwritten document images (2022)
Journal Article
Shivakumara, P., Jain, T., Pal, U., Surana, N., Antonacopoulos, A., & Lu, T. (2022). Text line segmentation from struck-out handwritten document images. Expert systems with applications, 210, 118266. https://doi.org/10.1016/j.eswa.2022.118266

In the case of freestyle everyday handwritten documents, writing, erasing, striking out, and overwriting are common behaviors of the writers. This not cleanly-written text poses significant challenges for text line segmentation. Accurate text line se... Read More about Text line segmentation from struck-out handwritten document images.

A new deep wavefront based model for text localization in 3D video (2021)
Journal Article

With the evolution of electronic devices, such as 3D cameras, addressing the challenges of text localization in 3D video (e.g., for indexing) is increasingly drawing the attention of the multimedia and video processing community. Existing methods foc... Read More about A new deep wavefront based model for text localization in 3D video.

Flexible character accuracy measure for reading-order-independent evaluation (2020)
Journal Article

The extraction of textual information from scanned document pages is a fundamental stage in any digitisation effort and directly determines the success of the overall document analysis and understanding application scenarios. To evaluate and improve... Read More about Flexible character accuracy measure for reading-order-independent evaluation.

VISE : an interface for Visual Search and Exploration of museum collections (2019)
Journal Article
Usman, M., & Antonacopoulos, A. (2020). VISE : an interface for Visual Search and Exploration of museum collections. Journal on Computing and Cultural Heritage, 12(4), 1-9. https://doi.org/10.1145/3340936

This article presents VISE, an interface that enables VIsual Search and Exploration across collections of approximately 836,000 museum objects extracted from the websites of the National Museums Scotland and the Rijksmuseum in the Netherlands. VISE p... Read More about VISE : an interface for Visual Search and Exploration of museum collections.

Efficient and effective OCR engine training (2019)
Journal Article
Clausner, C., Antonacopoulos, A., & Pletschacher, S. (2020). Efficient and effective OCR engine training. International Journal on Document Analysis and Recognition, 23(1), 73-78. https://doi.org/10.1007/s10032-019-00347-8

We present an efficient and effective approach to train OCR engines using the Aletheia document analysis system. All components required for training are seamlessly integrated into Aletheia: training data preparation, the OCR engine’s training proces... Read More about Efficient and effective OCR engine training.

Highlights of the novel dewaterability estimation test (DET) device (2019)
Journal Article
Scholz, M., Almuktar, S., Clausner, C., & Antonacopoulos, A. (2020). Highlights of the novel dewaterability estimation test (DET) device. Environmental Technology, 41(20), 2594-2602. https://doi.org/10.1080/09593330.2019.1575916

Many industries, which are producing sludge in large quantities, depend on sludge dewatering technology to reduce the corresponding water content. A key design parameter for dewatering equipment is the capillary suction time (CST) test, which has, ho... Read More about Highlights of the novel dewaterability estimation test (DET) device.

Study protocol : responding to the needs of patients with IgA nephropathy, a social media approach (2017)
Journal Article

Background
IgA nephropathy is the most common cause of glomerulonephritis in the Western world and predominantly affects young adults. Demographically these patients are the biggest users of social media. With increasing numbers of patients turning... Read More about Study protocol : responding to the needs of patients with IgA nephropathy, a social media approach.

Effective geometric restoration of distorted historical documents for large-scale digitization (2017)
Journal Article
Yang, P., Antonacopoulos, A., Clausner, C., Pletschacher, S., & Qi, J. (2017). Effective geometric restoration of distorted historical documents for large-scale digitization. IET Image Processing, 11(10), 841-853. https://doi.org/10.1049/iet-ipr.2016.0973

Due to storage conditions and material’s non-planar shape, geometric distortion of the 2-D content is widely present in scanned document images. Effective geometric restoration of these distorted document images considerably increases character recog... Read More about Effective geometric restoration of distorted historical documents for large-scale digitization.

Making Europe’s historical newspapers searchable (2016)
Journal Article
Neudecker, C., & Antonacopoulos, A. (2016). Making Europe’s historical newspapers searchable. https://doi.org/10.1109/DAS.2016.83

This paper provides a rare glimpse into the overall approach for the refinement, i.e. the enrichment of scanned historical newspapers with text and layout recognition, in the Europeana Newspapers project. Within three years, the project processed mor... Read More about Making Europe’s historical newspapers searchable.

Navigating the storm : IMPACT, eMOP, and Agile Steering Standards (2015)
Journal Article

This article discusses two major initiatives tasked with developing tools to im- prove optical character recognition (OCR) or the mechanical keying of texts that are digitally available only as page images. The two initiatives are the IMProving ACces... Read More about Navigating the storm : IMPACT, eMOP, and Agile Steering Standards.

Distinction between handwritten and machine-printed text based on the bag of visual words model (2014)
Journal Article
Zagoris, K., Pratikakis, I., Antonacopoulos, A., Gatos, B., & Papamarkos, N. (2014). Distinction between handwritten and machine-printed text based on the bag of visual words model. Pattern recognition, 47(3), 1051-1062. https://doi.org/10.1016/j.patcog.2013.09.005

In a variety of documents, ranging from forms to archive documents and books with annotations, machine printed and handwritten text may coexist in the same document image, raising significant issues within the recognition pipeline. It is, therefore,... Read More about Distinction between handwritten and machine-printed text based on the bag of visual words model.

Colour text segmentation in web images based on human perception (2007)
Journal Article
Antonacopoulos, A., & Karatzas, D. (2007). Colour text segmentation in web images based on human perception. Image and Vision Computing, 25(5), 564-577. https://doi.org/10.1016/j.imavis.2006.05.003

Page segmentation using the description of the background (1998)
Journal Article
Antonacopoulos, A. (1998). Page segmentation using the description of the background. Computer Vision and Image Understanding, 70(3), 350-369. https://doi.org/10.1006/cviu.1998.0691

There is an ever increasing number of publications which do not have the “traditional” layout where printed regions are rectangu- lar. Text paragraphs and areas of graphic type may be of any shape, individually rotated and in any arrangement. Previou... Read More about Page segmentation using the description of the background.