Background: A novel method to detect the text region from the natural image using the
discriminative deep feature of text regions is presented with deep learning concept in this manuscript.
Objectives: Curve Text Detection (CTD) from the natural image is generally based on two different
tasks: learning of text data and text region detection. In the learning of text data, the goal is to
train the system with a sample of letters and natural images, while, in the text region detection, the
aim is to confirm whether the detected regions are text region or not. The emphasis of this research
is on the development of deep learning algorithm.
Methods: A novel approach has been proposed to detect the text region from natural images
which simultaneously tackles three combined challenges: 1) pre-processing of the image without
losing text region; 2) appropriate segmentation of text region using their strokes, and 3) training of
data. In pre-processing, image enhancement and binarization are done then morphological operations
are defined with the Maximally Stable Extremal Region (MSER) based segmentation technique
which operates on the basis of stroke region of text and then finds out the (Speed Up Robust
Feature) SURF key point from those regions.
Results: Based on the SURF feature, text region is detected from the images using a trained structure
of Artificial Neural Network (ANN) which is based on deep learning mechanism.
Conclusion: CTW-1500 dataset is used to simulate the proposed work and the parameters like
Precision, Recall, F-Measure (H-mean), Execution time, Accuracy and Error Rate are computed
and are compared with the existing work to depict the effectiveness of the work.