Title Of Paper:
GSFT-PSNR: Global Single Fuzzy Threshold Based on PSNR for OCR Systems
Author's Name :  Farshid PirahanSiah, Mohammad Shahverdy
KeyWords:  Single fuzzy Thresholding method, image segmentation, OCR, threshold algorithm, Adaptive Image Binarization, augmented reality. GSFT-PSNR: Global Single Fuzzy Threshold Based on PSNR for OCR Systems.
Pages:  1 -19
Volume: 4
Issue: 6
Year: 2016

Binarization or Thresholding is an important basic step in computer vision and image analysis applications and has a substantial influence such as, preprocessing step in camera calibration, documents image analysis (OCR) and augmented reality applications. Binarization use thresholding value to separate foreground from the background (convert color or grayscale image to binary image) and reduction the amount of data to be process and raise the computational speed. Recently, there has been an increased interest in multilevel Thresholding. However, as the number of levels increases, the computation time rises. In addition, single threshold methods are faster than multilevel methods because of reduced amount of data to process. Another category of thresholding methods is global and local thresholding. Moreover, for each new application, new methods need to develop due to different requirements of applications. The proposed method is Global Single Fuzzy Threshold based on PSNR called GSFT-PSNR. In this work, an algorithm that applies the peak signal-to-noise ratio method as an indicator to segment the image is proposed along with fuzzy. In this research proposed method for single thresholding compare with several thresholding methods by using DIBCO 2013 benchmark datasets.

Full Text: