00000caa a22000003i 4500 UP-1685594773862388635 Buklod 20210322215112.0 m | | ta 210322s2019 xx r |||| u|eng d (iLib)UPBAG-00039569063 STII-DOST BAG rda eng ARTICLE-2820 Recio, Kristine Rey O. author. Three-step approach to edge detection of texts by Kristine Rey O. Recio and Renier G. Mendoza. 2019. pages 193-211 illustrations, map 26 cm text rdacontent unmediated rdamedia volume rdacarrier Includes bibliographical references (pages 209-211) We proposed a three-step image segmentation approach to determine the edges of images containing old texts. In general, texts from old books and articles tend to be very noisy. Thus, we first employed a suitable denoising method to obtain a smooth approximation ð??°ð??? of a given image ð??° Ì?. Then, the fuzzy edge map ð??¬ Ì? was obtained using the gradient of ð??°ð???. This gradient map gave an estimate of the edges of the texts. For the second step, the method of ð??? −means++ with two clusters was employed to separate the edges from rest of the image. Because a smooth approximation of the image was used, the edges obtained are "thick." And so, in the last step of the our method, the binary image generated from the previous step was post-processed using a thinning algorithm. We implemented our method to images containing Baybayin texts from the National Museum of the Philippines. (Author's abstract) Edge detection. Image denoising. Method of k - means++. Thinning algorithm. Library and information science. Mendoza, Renier G. author. The Philippine Journal of Science Vol. 148, no. 1, March 2019. Request full-text access via UPB University Library through https://forms.gle/KZjBv7aRtY6jiL5E9 (viewed 22 March 2021) FI UPBAG UPBAG-MAIN ARTICLE-2820 Analytics