Text localization, enhancement and binarization in multimedia documents
By Christian Wolf, J. Jolion, F. Chassaing. Object recognition supported by user interaction for service robots, 2002
297 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/6b4f762d9a5acd964411d8c737073c24ce16a3c8
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Xiang Bai
- Cong Yao
- Andrew Zisserman
- David S. Doermann
- Jiri Matas
- Yingli Tian
- Lukás Neumann
- Andrea Vedaldi
Citations in the corpus
- ICDAR 2003 robust reading competitions (2003, background): “In recent years there has been some significant research into these general reading systems that are able to locate and/or read text in scene images [11, 2, 3, 4, 1, 10].”
- Camera-based analysis of text and documents: a survey (2005, methodology): “In both [90] and [100], Niblack’s method is found to be the most effective to extract text.”
- A framework for improved video text detection and recognition (2012, methodology): “[23], which apply a single threshold for the entire document, and adapted local thresholding algorithms [21, 27, 34], which assign a threshold for each pre-defined local region of the document.”
- Action Classification in Soccer Videos with Long Short-Term Memory Recurrent Neural Networks (2010, methodology): “Thus, we perform a pre-processing step, inspired by the work in [6], which consists in detecting and blurring these logos.”
- Handwritten Optical Character Recognition (OCR): A Comprehensive Systematic Literature Review (SLR) (2020, background): “In the early 2000s, binarization techniques were introduced to preserve historical documents in digital form and provide researchers with access to these documents [13]–[16].”
- Text String Detection from Natural Scenes by Structure-based Partition and Grouping (2011, methodology): “[37] improved Otsu’s method to binarize text regions from background, followed by a sequence of morphological processing to reduce noise and correct classification errors.”
- ICDAR 2005 text locating competition results (2005, methodology): “For this we used the same data as the ICDAR 2003 competition, which has been kept private until now.”