International Journal of Software Engineering and Its Applications Vol. 10, No. 11 (2016), pp. 131-142 http://dx.doi.org/10.14257/ijseia.2016.10.11.11 ISSN: 1738-9984 IJSEIA Copyright ⓒ 2016 SERSC Palmprint Recognition Systems based-on Backpropagation Neural Network and Euclidean Distance using Principal Components Analysis (PCA) Feature Extraction R. Rizal Isnanto 1 , Ajub Ajulian Zahra 2 , Adrian Khoirul Haq 2 and Fachrul Rozy 2 1 Computer Engineering Department, Diponegoro University, Semarang 2 Electrical Engineering Department, Diponegoro University, Semarang rizal_isnanto@yahoo.com Abstract Palmprint recognition system has been one promising biometric system used in Presence System. There are some methods to recognize the individual palmprint as well as to extract its feature. In this research, two recognition methods are compared, i.e., backpropagation neural network and similarity measure using Euclidean distance. While, for feature extraction, we implemented Principal Components Analysis (PCA) method. From the research, it can be concluded that from test results, the best recognition using backpropogation neural networks is 93.33% which is reached when parameters used are: 100 principal components, 1 hidden layer, and 75 neurons. While, implementation of similarity measure using Euclidean distance, the best recognition rate is 96.67% which is reached when 75 principal components are used. When considering the time consumed in recognition, the Euclidean distance gives the better result, i.e. 17.09 seconds, while using backpropagation neural network with 75 neurons, time consumed is 425 seconds. Therefore, from this research, recognition implementation combining both PCA and Euclidean distance are more suggested rather than using combination of PCA and backpropagation neural network. Keywords: Palmprint recognition, backpropagation neural network, Euclidean distance, Principal Component Analysis (PCA), feature extraction 1. Introduction Conventional personal identification techniques identity card are assumed that they cannot be implemented reliably. It happens because of possibilities of cards loss or used by unauthorized persons. Implementation of conventional identification techniques has been increasingly replaced by biometric technique-based identification. Biometrics systems are based on human natural characteristics, i.e., physiological as well as behavioral or chemical characteristics, e.g., face [2], fingerprint, voice, palmprint, iris, retina, DNA, fingerprint or even odor [5]. There are some research concerned in both palmprint identification as well as in palmprint verification system [4]. Considering the above reason, the authors would like to analyze the comparison between recognition systems based on the characteristics of human nature, i.e., palms. There are many algorithms to extract the palmprint features as well as many algorithms to identify or classify the features [1]. In this research, the Principal Components Analysis (PCA) is used to extract the palmprint features. While, the methods to identify the individual features are backpropagation neural networks and similarity measure using Euclidean distance. Both identification methods are then analyzed and compared, for which we can obtain which best identification method based on PCA feature extraction.