Paper Details: Downloads: 2577
Serial Number: P1151747592
Title: Rotational invariant Real Time Text Recognition
Authors: M. Anyayahan and M. Balinas and A. La Madrid and M. Laurel and C. Lopez and R. Tolentino
Abstract: In everyday life, people always encounter different text images. These text images are in a style of linear or multi-oriented texts in either printed or written form. Due to different orientations of texts in an image, it is a challenge in Optical Character Recognition to recognize this kind of text. In this paper, real time recognition of text in different rotational variations is presented. The performance is done from acquisition of image by a camera and processed by Microsoft Visual Studio. The detection and recognition of text with different rotational variations are achieved by detecting and computing the direction and angle of tilt respectively through the use of geometric and trigonometric principles then recognized by Tesseract optical character recognition engine after counter rotation.
Keywords: : multi orientation angle, rotational variation, tilt angle, tilt direction, Optical Character Recognition.
Journal/Conference: International Journal of Graphics, Vision and Image Processing
Volume: 17
Issue: 2
Submission Date: 11/28/2017 12:00:00 AM
Review Date: 12/21/2017 12:00:00 AM
Publishing Date: 1/9/2018 12:00:00 AM
Article Downloads: 2577
Download:

Facebook