CHASSIS PLATE NUMBER RECOGNITION USING FUZZY ALGORITHM

Wijaya, I Wayan Ari (2020) CHASSIS PLATE NUMBER RECOGNITION USING FUZZY ALGORITHM. Other thesis, UNIKA SOEGIJAPRANATA SEMARANG.

[img]
Preview
Text (COVER)
16.K1.0027 I WAYAN ARI WIJAYA_COVER_a.pdf

Download (816kB) | Preview
[img]
Preview
Text (BAB I)
16.K1.0027 I WAYAN ARI WIJAYA_BAB I_a.pdf

Download (257kB) | Preview
[img] Text (BAB II)
16.K1.0027 I WAYAN ARI WIJAYA_BAB II_a.pdf
Restricted to Registered users only

Download (260kB)
[img] Text (BAB III)
16.K1.0027 I WAYAN ARI WIJAYA_BAB III_a.pdf
Restricted to Registered users only

Download (427kB)
[img]
Preview
Text (BAB IV)
16.K1.0027 I WAYAN ARI WIJAYA_BAB IV_a.pdf

Download (1MB) | Preview
[img]
Preview
Text (BAB V)
16.K1.0027 I WAYAN ARI WIJAYA_BAB V_a.pdf

Download (1MB) | Preview
[img]
Preview
Text (BAB VI)
16.K1.0027 I WAYAN ARI WIJAYA_BAB VI_a.pdf

Download (352kB) | Preview
[img]
Preview
Text (DAFTAR PUSTAKA)
16.K1.0027 I WAYAN ARI WIJAYA_DAPUS_a.pdf

Download (314kB) | Preview
[img]
Preview
Text (LAMPIRAN)
16.K1.0027 I WAYAN ARI WIJAYA_LAMPIRAN_a.pdf

Download (1MB) | Preview

Abstract

Number plate detection and recognition systems are widely used in various systems for detecting characters and numbers in vehicle license plates. This research will try the similar approach on chassis number plates instead of its common use in vehicle license plates. The data used in this research consists of 92 chassis number images that are taken from google and various websites. And from the 92 data, the features of 55 image data are successfully extracted. There are 2 approaches in processing the image. The approach will start from extracting the fuzzy edge detection features from the images by using the fuzzy algorithm. And the results will be segmented and divided into training and testing datasets for the neural network. After which the neural network will be used to recognize the characters and numbers inside the plates. The result of this approach are as follows, the neural network gained a higher percentage of accuracy with different samples: 48/94 or 51% for numbers and 22/49 or 44% for alphabet sample images. This shows that detections in chassis plates have various difficulties compared to the usual license plate detection and recognition system.

Item Type: Thesis (Other)
Subjects: 000 Computer Science, Information and General Works > 005 Computer programming, programs & data
Divisions: Faculty of Computer Science > Department of Informatics Engineering
Depositing User: Ms Agustin Hesti Pertiwi
Date Deposited: 23 Jun 2020 04:16
Last Modified: 23 Sep 2020 02:05
URI: http://repository.unika.ac.id/id/eprint/21439

Actions (login required)

View Item View Item