Deep Features for Text Spotting

Jaderberg, Max; Vedaldi, Andrea; Zisserman, Andrew

doi:10.1007/978-3-319-10593-2_34

Cited by 519 publications

(468 citation statements)

References 30 publications

Supporting

Mentioning

466

Contrasting

Unclassified

Order By: Relevance

“…Generally, text detection methods are based on either connected components or sliding windows [4]. Connected component based methods, like Maximally Stable Extremal Regions (MSER) [10][11][12], enjoy their computational efficiency and high recall rates, but suffer from a large number of false detections.…”

Section: Image Text Detectionmentioning

confidence: 99%

“…Similar to Section 2.1 where the importance of features is addressed, existing image text recognition methods are also classified into those based on hand-engineered features [14,18,[24][25][26][27] and those based on feature learning [3,4,6,13,17,[28][29][30][31][32][33][34] …”

Section: Image Text Recognitionmentioning

confidence: 99%

“…CNNs have most recently proven their mettle handling image text detection and recognition [3,4]. By virtue of their special bio-inspired structures (i.e.…”

mentioning

confidence: 99%

“…features extracted from hidden layers of a CNN character classifier can also be used for text detection [4]. Additionally, the fixed input size of typical CNNs makes them especially suitable for recognizing East Asian characters whose SCW is consistent.…”

mentioning

confidence: 99%

See 3 more Smart Citations

End-to-end subtitle detection and recognition for videos in East Asian languages via CNN ensemble

Shan

Qiu

et al. 2018

Signal Processing: Image Communication

View full text Add to dashboard Cite

In this paper, we propose an innovative end-to-end subtitle detection and recognition system for videos in East Asian languages. Our end-to-end system consists of multiple stages. Subtitles are firstly detected by a novel image operator based on the sequence information of consecutive video frames.Then, an ensemble of Convolutional Neural Networks (CNNs) trained on synthetic data is adopted for detecting and recognizing East Asian characters. Finally, a dynamic programming approach leveraging language models * Corresponding author tively, which is a significant outperformance of other existing methods. The near-perfect accuracy of our system dramatically narrows the gap between human cognitive ability and state-of-the-art algorithms used for such a task.

show abstract

Section: Image Text Detectionmentioning

confidence: 99%

Section: Image Text Recognitionmentioning

confidence: 99%

“…CNNs have most recently proven their mettle handling image text detection and recognition [3,4]. By virtue of their special bio-inspired structures (i.e.…”

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

End-to-end subtitle detection and recognition for videos in East Asian languages via CNN ensemble

Shan

Qiu

et al. 2018

Signal Processing: Image Communication

View full text Add to dashboard Cite

show abstract

“…Text-line region detection Our system detects text-line regions based on a pretrained CNN model from Oxford [11] and Hough line detection. A text saliency map, shown in figure 2 (b), is generated by evaluating the text/background CNN model, which is trained on cropped 24 × 24 pixel case-insensitive characters, in a sliding window fashion across the image.…”

Section: Indexingmentioning

confidence: 99%

A Text Recognition and Retrieval System for e-Business Image Management

Zhou

McGuinness

O’Connor

2018

MultiMedia Modeling

View full text Add to dashboard Cite

Abstract. The on-going growth of e-business has resulted in companies having to manage an ever increasing number of product, packaging and promotional images. Systems for indexing and retrieving such images are required in order to ensure image libraries can be managed and fully exploited as valuable business resources. In this paper, we explore the power of text recognition for e-business image management and propose an innovative system based on photo OCR. Photo OCR has been actively studied for scene text recognition but has not been exploited for e-business digital image management. Besides the well known difficulties in scene text recognition such as various size, location, orientation in text and cluttered background, e-business images typically feature text with extremely diverse fonts, and the characters are often artistically modified in shape, colour and arrangement. To address these challenges, our system takes advantage of the combinatorial power of deep neural networks and MSER processing. The cosine distance and n-gram vectors are used during retrieval for matching detected text to queries to provide tolerance to the inevitable transcription errors in text recognition. To evaluate our proposed system, we prepared a novel dataset designed specifically to reflect the challenges associated with text in e-business images. We compared our system with two other approaches for scene text recognition, and the results show our system outperforms other state-ofthe-art on the new challenging dataset. Our system demonstrates that recognizing text embedded in images can be hugely beneficial for digital asset management.

show abstract

Quantum Machine Learning

2022

Artificial Intelligence and Quantum Computing for Advanced Wireless Networks

View full text Add to dashboard Cite

Deep Features for Text Spotting

Cited by 519 publications

References 30 publications

End-to-end subtitle detection and recognition for videos in East Asian languages via CNN ensemble

End-to-end subtitle detection and recognition for videos in East Asian languages via CNN ensemble

A Text Recognition and Retrieval System for e-Business Image Management

Quantum Machine Learning

Contact Info

Product

Resources

About