An Efficient Method for Text Detection in Video Based on Stroke Width Similarity

Dinh, Viet Cuong; Chun, Seong Soo; Cha, Seungwook; Ryu, Hanjin; Sull, Sanghoon

doi:10.1007/978-3-540-76386-4_18

Cited by 20 publications

(11 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous previous works [4,9,10] employed the Canny operator to detect the distinct boundaries between foreground and background. However, threshold setting for Canny operator is not a straightforward work.…”

Section: Methodology a Edge Detectormentioning

confidence: 99%

“…In the last decade, a great number of impressive techniques [1][2][3][4][5][6][7][8][9][10][11][12] have been elaborately designed to narrow the gap between the limited capability of Optical Character Recognition (OCR) and the unconstrained appearances of scene characters. Among the existing techniques, edge-based methods have attracted extensive attention, since they utilize the essential and reliable contrast feature, and enable working free from an exhaustive scan of the original image.…”

Section: Introductionmentioning

confidence: 99%

“…To extract the stroke width, Subramanian et al [3] sought a set of dashes by analyzing a group of horizontal scanning lines. The method proposed by Dinh et al [4] traversed all horizontal lines to find stable valleys between double edge pixels. Then, a stroke width-based adaptive morphological dilation operator was exploited to connect edge pixels into candidate regions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Scene Character Detection by an Edge-Ray Filter

Shivakumara

Uchida

2013

2013 12th International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

Abstract-Edge is a type of valuable clues for scene character detection task. Generally, the existing edge-based methods rely on the assumption of straight text line to prune away the noncharacter candidates. This paper proposes a new edge-based method, called edge-ray filter, to detect the scene character. The main contribution of the proposed method lies in filtering out complex backgrounds by fully utilizing the essential spatial layout of edges instead of the assumption of straight text line. Edges are extracted by a combination of Canny and Edge Preserving Smoothing Filter (EPSF). To effectively boost the filtering strength of the designed edge-ray filter, we employ a new Edge Quasi-Connectivity Analysis (EQCA) to unify complex edges as well as contour of broken character. Label Histogram Analysis (LHA) then filters out non-character edges and redundant rays through setting proper thresholds. Finally, two frequentlyused heuristic rules, namely aspect ratio and occupation, are exploited to wipe off distinct false alarms. In addition to have the ability to handle special scenarios, the proposed method can accommodate dark-on-bright and bright-on-dark characters simultaneously, and provides accurate character segmentation masks. We perform experiments on the benchmark ICDAR 2011 Robust Reading Competition dataset as well as scene images with special scenarios. The experimental results demonstrate the validity of our proposal.

show abstract

Section: Methodology a Edge Detectormentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Scene Character Detection by an Edge-Ray Filter

Shivakumara

Uchida

2013

2013 12th International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

show abstract

“…Stroke width recently has emerged as a new feature that has shown to be extremely effective for text detection [3][4][5] and it has quickly been extended to the so-called Stroke Width Transform (SWT) and leads to a state-of-the-art text detection system [1]. However, one limitation of the algorithms in [3][4][5] is that they can only detect horizontal texts.…”

mentioning

confidence: 99%

“…However, one limitation of the algorithms in [3][4][5] is that they can only detect horizontal texts. The algorithm proposed in [1] can detect near-horizontal (within −15 • and 15 • ) and near-vertical (within 75 • and 105 • ) texts.…”

mentioning

confidence: 99%

Transform invariant text extraction

et al. 2013

View full text Add to dashboard Cite

Automatically extracting texts from natural images is very useful for many applications such as augmented reality. Most of the existing text detection systems require that the texts to be detected (and recognized) in an image are taken from a nearly frontal viewpoint. However, texts in most images taken naturally by a camera or a mobile phone can have a significant affine or perspective deformation, making the existing text detection and the subsequent OCR engines prone to failures. In this paper, based on stroke width transform and texture invariant low-rank transform, we propose a framework that can detect and rectify texts in arbitrary orientations in the image against complex backgrounds, so that the texts can be correctly recognized by common OCR engines. Extensive experiments show the advantage of our method when compared to the state of art text detection systems.

show abstract

Toward a computer vision-based wayfinding aid for blind persons to access unfamiliar indoor environments

Tian

Yang

et al. 2012

Machine Vision and Applications

View full text Add to dashboard Cite

Independent travel is a well known challenge for blind and visually impaired persons. In this paper, we propose a proof-of-concept computer vision-based wayfinding aid for blind people to independently access unfamiliar indoor environments. In order to find different rooms (e.g. an office, a lab, or a bathroom) and other building amenities (e.g. an exit or an elevator), we incorporate object detection with text recognition. First we develop a robust and efficient algorithm to detect doors, elevators, and cabinets based on their general geometric shape, by combining edges and corners. The algorithm is general enough to handle large intra-class variations of objects with different appearances among different indoor environments, as well as small inter-class differences between different objects such as doors and door-like cabinets. Next, in order to distinguish intra-class objects (e.g. an office door from a bathroom door), we extract and recognize text information associated with the detected objects. For text recognition, we first extract text regions from signs with multiple colors and possibly complex backgrounds, and then apply character localization and topological analysis to filter out background interference. The extracted text is recognized using off-the-shelf optical character recognition (OCR) software products. The object type, orientation, location, and text information are presented to the blind traveler as speech.

show abstract

An Efficient Method for Text Detection in Video Based on Stroke Width Similarity

Cited by 20 publications

References 10 publications

Scene Character Detection by an Edge-Ray Filter

Scene Character Detection by an Edge-Ray Filter

Transform invariant text extraction

Toward a computer vision-based wayfinding aid for blind persons to access unfamiliar indoor environments

Contact Info

Product

Resources

About