Jurnal Elektronik Ilmu Komputer Udayana p-ISSN: 2301-5373 Volume 8, No 4. May 2020 e-ISSN: 2654-5101 393 Alphabet Writing Game Application using Template Matching Cross-correlation I Made Pegi Kurnia Amerta a1 , I Gede Arta Wibawa a2 a Program Studi Teknik Informatika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universtas Udayana Jalan Kampus Bukit Jimbaran, Jimbaran, Badung, Bali 1 amertakurnia@gmail.com 2 gede.arta@unud.ac.id Abstract The game of writing letters is an attractive learning media. Each person's handwriting is different. So that it requires a data classification method to match the test data with the template that is the alphabet letter. In this journal using a template matching cross-correlation for data classification. Before data classification, preprocessing is done in the form of resize and threshold to produce binary images. Thinning process is also carried out to thin the letters. The thinning algorithm used is stentiford. From the accuracy testing obtained an average value of 70.38%. With the number of letters that continue to experience errors namely the characters H, K, M, and Y. Keywords: Template Matching, Cross-Correlation, Handwriting 1. Introduction Learning letters that exist in formal schools, usually using the demonstration method. While the learning objectives so that students can apply them to the surrounding environment. Then we need a new method that is practice by doing. The game application acts as a virtual assistant that helps students in assessing the practice of writing alphabet letters. The game application in this journal identifies alphabet letters consisting of 26 letters. Pre-processing is done by changing the size of the image, changing the color of the image to binary. Before data classification, thinning is performed on the image. Algorithms that can be used in the thinning process are zhang-suen and stentiford. The accuracy of the stentiford algorithm is higher than that of zhang-Suen, although the stentiford algorithm has a longer processing time compared to zhang-Suen [1]. The length of the process is due to the algorithm of stentiford which is done by matching several template images with a size of 3x3 pixels [2]. Whereas in the zhang-Suen algorithm, thinning is done on a pixel based on the surrounding pixels and if the surrounding area is not part of the skeleton of the image [2]. Template matching is part of the data classification method. The step of this algorithm is to match the image with one or more templa