PENGENAL PLAT NOMOR KENDARAAN BERBASIS TEMPLATE MATCHING DAN COSINE SIMILARITY

IRFAN, MUHAMMAD GHANI (2019) PENGENAL PLAT NOMOR KENDARAAN BERBASIS TEMPLATE MATCHING DAN COSINE SIMILARITY. Undergraduate Thesis thesis, Institut Telkom Purwokerto.

	Text Cover.pdf - Accepted Version Download (29MB)
Preview	Text Abstract.pdf - Accepted Version Download (8kB) | Preview
Preview	Text Abstrak.pdf - Accepted Version Download (7kB) | Preview
Preview	Text BAB I.pdf - Accepted Version Download (82kB) | Preview
Preview	Text BAB II.pdf - Accepted Version Download (232kB) | Preview
Preview	Text BAB III.pdf - Accepted Version Download (387kB) | Preview
	Text BAB IV.pdf - Accepted Version Restricted to Registered users only Download (315kB)
Preview	Text BAB V.pdf - Accepted Version Download (8kB) | Preview
Preview	Text Daftar Pustaka.pdf - Accepted Version Download (76kB) | Preview

Abstract

ABSTRACT The increased of number of vehicles made the availability of parking lot is needed. But unfortunately the parking lot is one of the places that are prone to theft. To improve its security, identification of vehicles is very important. This can be obtained with its plate number. ANPR (Automatic Number Plate Recognition) is the solution. In this study, vehicle's plate number is recognized automatically by using template matching and cosine similarity. This system consists of 3 main components, which are plate detection, character segmentation, and character recognition cosine similarity. From the test results, the accuracy of character recognition 87.16% with 387 characters recognized from 444 characters. Accuracy of full plate recognition 37.10% with 23 plates that can be recognized from 62 plates. Keyword: ANPR, template matching, number plate detection, character segmentation, cosine similarity

Actions (login required)

View Item