DocumentCode :
594711
Title :
Scene text detection using sparse stroke information and MLP
Author :
Chowdhury, A.R. ; Bhattacharya, Ujjwal ; Parui, Swapan K.
Author_Institution :
Dept. of Inf. Technol., Heritage Inst. of Technol., Kolkata, India
fYear :
2012
fDate :
11-15 Nov. 2012
Firstpage :
294
Lastpage :
297
Abstract :
In this article, we present a novel set of features for detection of text in images of natural scenes using a multi-layer perceptron (MLP) classifier. An estimate of the uniformity in stroke thickness is one of our features and we obtain the same using only a subset of the distance transform values of the concerned region. Estimation of the uniformity in stroke thickness on the basis of sparse sampling of the distance transform values is a novel approach. Another feature is the distance between the foreground and background colors computed in a perceptually uniform and illumination-invariant color space. Remaining features include two ratios of anti-parallel edge gradient orientations, a regularity measure between the skeletal representation and Canny edgemap of the object, average edge gradient magnitude, variation in the foreground gray levels and five others. Here, we present the results of the proposed approach on the ICDAR 2003 database and another database of scene images consisting of text of Indian scripts.
Keywords :
compressed sensing; edge detection; feature extraction; gradient methods; image classification; image colour analysis; image representation; multilayer perceptrons; natural scenes; text detection; visual databases; Canny edgemap; ICDAR 2003 database; Indian scripts; MLP classifier; antiparallel edge gradient orientations; average edge gradient magnitude; background colors; distance transform values; foreground colors; foreground gray level variation; illumination-invariant color space; multilayer perceptron; natural scenes; perceptually uniform color space; regularity measure; scene image database; scene text detection; skeletal representation; sparse sampling; sparse stroke information; stroke thickness uniformity estimation; Databases; Feature extraction; Image color analysis; Image edge detection; Pattern recognition; Robustness; Transforms;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition (ICPR), 2012 21st International Conference on
Conference_Location :
Tsukuba
ISSN :
1051-4651
Print_ISBN :
978-1-4673-2216-4
Type :
conf
Filename :
6460130
Link To Document :
بازگشت