An Efficient Edge Based Technique for Text Detection in Video Frames

Palaiahnakote, Shivakumara; Huang, Wei‐Hua; Tan, Chew Lim

doi:10.1109/das.2008.17

Cited by 46 publications

(12 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, detection rate and false positive rate of the proposed approach are higher than the existing approaches. However when we compare the results of the proposed approach with our existing approaches [7,9] the proposed approach gives low detection rate because the existing approaches are tested on small dataset (101) but the proposed approach is tested on large dataset (800) frames. The main contribution of the proposed work is the use of eigen value analysis for text detection.…”

Section: Misdetection Rate (Mdr) = Number Of Mdb/ Number Of Tdbmentioning

confidence: 91%

“…They can be broadly classified as connected component based [5][6], gradient and edge based [7][8][9][10][11] and texture based approaches [12][13]. It is known that performance of the first category is poor for frames with small font and cluttered background due to its assumptions that text characters should have the same intensity values and geometrical properties.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An eigen value based approach for text detection in video

Guru

Manjunath

Shivakumara

et al. 2010

Proceedings of the 9th IAPR International Workshop on Document Analysis Systems

View full text Add to dashboard Cite

In this paper, a novel approach for detection of text and non-text regions in video frames is proposed. The proposed approach performs block wise eigen analysis on the gradient image of the video frame. For each block of the gradient frame, the dominant eigen value is computed to decide if the block could be a candidate text block. The K-means clustering is then applied to further identify text blocks among the candidate blocks. From each of the identified candidate text blocks edges are extracted using the sobel operator, and then by the use of horizontal and vertical profiles a bounding rectangle is fixed up. Further, geometric properties of the identified text regions are studied to eliminate false text regions. In order to validate the efficacy of the proposed approach, experimentation on a dataset containing 800 video frames has been carried out. The obtained results ensure that the proposed approach is with increased text detection rate with very low false and misdetection rates when compared to the other existing state of the art techniques.

show abstract

Section: Misdetection Rate (Mdr) = Number Of Mdb/ Number Of Tdbmentioning

confidence: 91%

Section: Introductionmentioning

confidence: 99%

An eigen value based approach for text detection in video

Guru

Manjunath

Shivakumara

et al. 2010

Proceedings of the 9th IAPR International Workshop on Document Analysis Systems

View full text Add to dashboard Cite

show abstract

“…Jain et al [14] perform a color space reduction followed by color segmentation and spatial regrouping to detect text. Although processing of touching characters is considered by the authors, the segmentation phase presents major problems in the case of low quality documents, especially video sequences.…”

Section: Review Of Literaturementioning

confidence: 99%

Text Detection and Recognition Using Camera Based Images

Darshan

Gopalkrishna

Hanumantharaju³

2015

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Abstract. The increase in availability of high performance, low-priced, portable digital imaging devices has created an opportunity for supplementing traditional scanning for document image acquisition. Cameras attached to cellular phones, wearable computers, and standalone image or video devices are highly mobile and easy to use; they can capture images making them much more versatile than desktop scanners. Should gain solutions to the analysis of documents captured with such devices become available, there will clearly be a demand in many domains. Images captured from images can suffer from low resolution, perspective distortion, and blur, as well as a complex layout and interaction of the content and background.In this paper, we propose an efficient text detection method based on Maximally Stable Exterme Region (MSER) detector, saying that how to detect regions containing text in an image. It is a common task performed on unstructured scenes, for example when capturing video from a moving vehicle for the purpose of alerting a driver about a road sign . Segmenting out the text from a clutterd scene greatly helps with additional tasks such as optical charater recognition (OCR). The efficiency of any service or product, especially those related to medical field depends upon its applicability. The applicability for any service or products can b achieved by applying thr basic principles of Software Engineering.

show abstract

“…Our system focuses on finding and extracting text from signage. Many efforts have been made to extract text regions from the scene image [4,6,8,10]. We propose a robust algorithm to extract text from complex background with multiple colors.…”

Section: Algorithm Of Text Extraction Localization and Recognitionmentioning

confidence: 99%

Context-based indoor object detection as an aid to blind persons accessing unfamiliar environments

Yang

Tian

et al. 2010

Proceedings of the 18th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Independent travel is a well known challenge for blind or visually impaired persons. In this paper, we propose a computer visionbased indoor wayfinding system for assisting blind people to independently access unfamiliar buildings. In order to find different rooms (i.e. an office, a lab, or a bathroom) and other building amenities (i.e. an exit or an elevator), we incorporate door detection with text recognition. First we develop a robust and efficient algorithm to detect doors and elevators based on general geometric shape, by combining edges and corners. The algorithm is generic enough to handle large intra-class variations of the object model among different indoor environments, as well as small inter-class differences between different objects such as doors and elevators. Next, to distinguish an office door from a bathroom door, we extract and recognize the text information associated with the detected objects. We first extract text regions from indoor signs with multiple colors. Then text character localization and layout analysis of text strings are applied to filter out background interference. The extracted text is recognized by using off-the-shelf optical character recognition (OCR) software products. The object type, orientation, and location can be displayed as speech for blind travelers.

show abstract

An Efficient Edge Based Technique for Text Detection in Video Frames

Cited by 46 publications

References 10 publications

An eigen value based approach for text detection in video

An eigen value based approach for text detection in video

Text Detection and Recognition Using Camera Based Images

Context-based indoor object detection as an aid to blind persons accessing unfamiliar environments

Contact Info

Product

Resources

About