Linear Time Maximally Stable Extremal Regions

By David Nistér, Henrik Stewénius. European Conference on Computer Vision, 2008

351 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/c79a502b49f24597f818b08a3c67ec3100a36bcb

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

1. Xiang Bai
2. Andrew Zisserman
3. Yu Qiao
4. Andrea Vedaldi
5. Cong Yao
6. Luc Van Gool
7. Dacheng Tao
8. Xiaogang Wang

In Electrical and Electronic Engineering

1. Yu Qiao
2. Lianwen Jin
3. Joelle Pineau
4. Jiri Matas
5. Qixiang Ye
6. Bernd Girod
7. Yuliang Liu
8. Ouais Alsharif

Citations in the corpus

• Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees (2014, background): “First, the MSERs detector is computationally fast and can be computed in linear time of the number of pixels in a image [25].”
• End-to-End Text Recognition with Hybrid HMM Maxout Models (2013, methodology): “While being highly imprecise text detectors, they can be computed very quickly (Nist´er & Stew´enius, 2008).”
• A Method for Text Localization and Recognition in Real-World Images (2010, background): “Assuming that individual characters are detected as Extremal Regions (ER) and taking computation complexity into consideration, the search space was limited to the setM of Maximally Stable Extremal Regions (MSER) [15], which can be computed in linear time in number of pixels [17].”
• A Big Data Analytics Method for Tourist Behaviour Analysis (2017, neutral): “is extracted using Maximally Stable Extremal Regions detectors [52] and SURF [3] descriptors.”
• Text Detection and Recognition in Imagery: A Survey (2015, background): “MSERs-based text localization has been widely explored [78], [112], [122], [137], [164], [182], [195].”
• Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection (2017, methodology): “s and the relationships between characters [40], e.g. connected component based methods [38,27,22]. These methods often use stroke width transform (SWT) [9] or maximally stable extremal region (MSER) [20,24] to first extract character candidates, and using a series of subsequence steps to eliminate n”
• Robust text detection in natural images with edge-enhanced Maximally Stable Extremal Regions (2011, background): “While MSER has been identified as one of the best region detectors [19] due to its robustness against view point, scale, and lighting changes, it is sensitive to image blur.”
• OpenMVG: Open Multiple View Geometry (2016, background): “• Affine invariant regions: Tree-Based Morse Regions (TBMR) [23], Maximally Stable Extremal Regions (MSER) [24].”