Indonesian Vehicles Number Plates Recognition System Using Multi Layer Perceptron Neural Network and Connected Component Labelling

International Journal on Information and Communication Technology (IJoICT) Vol 1, No 1 (2015): December 2015
Publisher : School of Computing, Telkom University

Show Abstract | Original Source | Check in Google Scholar | Full PDF (668.771 KB)


In recent years, the amount of vehicle in Indonesia has been increasing rapidly. This surely, if it is conducted conventionally, challenges the upholder in recognizing and detecting the lawbreakers vehicle. The objective of this research aims to create the system which can automatically recognize vehicles number plates. This is also expected to be able to assist the upholder to take an action against the lawbreaker. The method used are sliding concentric windows and connected component for detecting and segmenting each of character on vehicles number plates. Further, multi-layer perceptron neural network classification model is used to identify each of character on it.The system has been tested using variety of vehicles number plate images and succesfully recognize 180 of 224 characters images (80.35%). Based on the computation of each character, the accuracy of the system, throughout tested vehicles number plate images, can reach 95.69% (1509 of 1577 characters can be identified).The tested system has shown prospective results, thus the technique used on this research can be implemented through vehicles number plate recognition system in Indonesia.

A Two Microphone-Based Approach for Detecting and Identifying Speech Sounds in Hearing Support System

Data Science: Journal of Computing and Applied Informatics Vol 2 No 2 (2018): Data Science: Journal of Computing and Applied Informatics (JoCAI)
Publisher : Talenta Publisher

Show Abstract | Original Source | Check in Google Scholar


For people with hearing disabilities, not only would give them difficulties in going through their everyday lives but also sometimes could be life threatening. In this research we proposed a simple, yet robust approach for helping the hearing-impaired people in identifying the important sounds around them by using two microphones as input channel that could be worn around the person’s head as a substitute for their ears. This device then could be used to record the situation of the surroundings, and then the system would estimate the Direction of Arrival (DOA) of the sound sources, then detect and classify them using Support Vector Machine (SVM) into target speech or noise category. As the results, system’s classifier could produce FAR and FRR as low as 2%, in which 274 out of 280 samples were successfully classified as target speeches and 22 from the total of 27 noise samples were successfully classified as noise