Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : ComEngApp : Computer Engineering and Applications Journal

An Analysis of Adaptive Approach for Document Binarization Malik, Reza Firsandaya; Saparudin; Septyliana, Intan
Computer Engineering and Applications Journal (ComEngApp) Vol. 2 No. 2 (2013)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Abstract Binarization is an initial step in document image analysis for differentiate text area from background. Determination of binarization technique is really important to retrieve all the text information especially from degraded document image. This paper explains about adaptive binarization using Gatos’s method. Gatos’s method is doing preprocessing, foreground estimation using Sauvola’s method, background estimation, upsampling, final thresholding and postprocessing. In this paper, Sauvola’s method is final thresholding from Wiener filter image result and source image, and count F-Measure from both of these binary image results. By using optimum constant value on k value, n local window, Ksw and Ksw1, Gatos’s method can produced binary image better than Sauvola’s method based on F-Measure value. Sauvola’s method produces average value F=84,62%, Sauvola’s method with Wiener filter produces average value F=99.06% and Gatos’s method produces average value F=99,43%. Keyword : Degraded Document Image, Adaptive Approcah for Binarization, Gatos’s  Method, Sauvola’s MethodDOI: 10.18495/comengapp.22.185194
Weighting Facial Features Extraction using Geometric Average Saparudin
Computer Engineering and Applications Journal (ComEngApp) Vol. 6 No. 1 (2017)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Human facial feature extraction is an important process in the face recognition system. The quality of the results from the extraction of human facial features is determined by the degree of accuracy. The weighting of human facial features is used to test the accuracy of the methods used. This research produces the process of weighting the facial features automatically. The results obtained are the same as those seen by the human eyes. Â