Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Jurnal ULTIMA Computing

Pengenalan Tulisan Tangan Offline Dengan Algoritma Generalized Hough Transform dan Backpropagation Farica Perdana Putri; Adhi Kusnadi
Ultima Computing : Jurnal Sistem Komputer Vol 10 No 1 (2018): Ultima Computing : Jurnal Sistem Komputer
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2376.779 KB) | DOI: 10.31937/sk.v10i1.890

Abstract

Offline handwriting recognition is a technique used to recognize handwriting in paper document which converting it to digital form. Each handwriting has a unique style and shape that can be used to identify the owner. This research aims to develop a method to recognize the digital data handwriting. The method combines two algorithms; the first is Generalized Hough Transform in feature extraction process to detect arbitrary objects on the image; the second algorithm is Backpropagation to train the neural network based on feature values from feature extraction process. Artificial Neural Network (ANN) is used to improve the accuracy of the recognition system. The experiments are performed by using 100 handwriting images of 10 different people. The number of hidden units is defined through experiment to obtain optimal neural network. The experiment result shows that the recognition accuracy is up to 80%. Index Terms—Artificial Neural Network, Backrpopagation, Generalized Hough Transform, Offline handwiritng recognition
Algoritma Fisher-Yates Shuffle dan Flood Fill sebagai Maze Generator pada Game Labirin D.J. Owen Hoetama; Farica Perdana Putri; P.M. Winarno
Ultima Computing : Jurnal Sistem Komputer Vol 10 No 2 (2018): Ultima Computing : Jurnal Sistem Komputer
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1592.456 KB) | DOI: 10.31937/sk.v10i2.1064

Abstract

Maze game is an interesting game and used to spend time. However, in the maze game, the level used forthis game still uses static levels. Static levels make the maze shape stay the same if we play the same level. Thus, players will quickly feel bored because it finds the same complexity. Maze generator is a static level problem solution on the maze game. This research uses Fisher-Yates Shuffle algorithm and Flood Fill algorithm to make maze generator. Fisher-Yates Shuffle algorithm is used for wall position randomization and Flood Fill algorithm to keep the maze results to remain resolved. The results of the application implementation yielded 30 mazes and were tested using the Hamming Distance algorithm, yielding that the result of the maze formed is always different. The average percentage rate difference produced 48% each time the maze was formed. The results of the maze that was formed performed perfect maze checking with the result of 83.33% percentage. Index Terms— Fisher-Yates Shuffle, Flood Fill, MazeGenerator, Hamming Distance