2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) (2017)
Nov. 9, 2017 to Nov. 15, 2017
Text detection in natural scenes holds great importance in the field of research and still remains a challenge and an important task because of size, various fonts, line orientation, different illumination conditions, weak characters and complex backgrounds in image. The contribution of our proposed method is to filtering out complex backgrounds by combining three strategies. These are enhancing the edge candidate detection in HSV space color using the fractal dimension (FD) to transform the image intensities, then using MSER candidate detection to get different masks applied in HSV space color as well as gray color. After that, we opt for the Stroke Width Transform (SWT) and heuristic filtering. Such strategies are followed so as to maximize the capacity of zones text pixels candidates and distinguish between text boxes and the rest of the image. The components selected non text are filtered by classifying the characters candidates using Support Vector Machines (SVM) exploring Convolutional Neural Networks (CNN) features and Histogram of Oriented Gradients (HOG) vector features. We use the technique of word grouping who the boundary box localization select different words in the image where false positives text blocks are eliminated by geometrical properties. The evaluation of the proposed method demonstrate the effectiveness of our method for complex foreground through the experimental results tested on three benchmarks ICDAR2013, ICDAR2015 and MSRA-TD500.
edge detection, feature extraction, image classification, image colour analysis, image filtering, natural scenes, neural nets, support vector machines, text detection, transforms
H. Turki, M. Ben Halima and A. M. Alimi, "Text Detection Based on MSER and CNN Features," 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, Japan, 2018, pp. 949-954.