Abstract
The vehicle logo is one of the features that can be used to identify a vehicle. Even so, a lot of Intelligent Transport System which are developed nowadays has yet to use a vehicle logo recognition system as one of its vehicle identification tools. Hence there are still cases of traffic crimes that haven't been able to be examined by the system, such as cases of counterfeiting vehicle license plates. Vehicle logo recognition itself could be done by using various feature extraction and classification methods. This research project uses the Local Binary Pattern feature extraction method which is often used for many kinds of image recognition systems. Then, the classification method used is Random Forest which is known to be effective and accurate for various classification problems. The data used for this study were as many as 2000 vehicle logo images consisting of 5 brand classes, namely Honda, Kia, Mazda, Mitsubishi, and Toyota. The results of the tests carried out obtained the best accuracy value of 88.89% for the front view logo image dataset, 77.03% for the side view logo image dataset, and 83% for the dataset with both types of images.
Highlights
The vehicle logo is one of the features that can be used to identify a vehicle
able to be examined by the system
Vehicle logo recognition itself could be done by using various feature extraction and classification methods
Summary
Oleh karena itu melanjutkan dari kasus untuk dataset kedua di penelitian sebelumnya [2], pada penelitian ini dibangun sistem pengenalan logo kendaraan menggunakan metode ekstraksi ciri LBP dan klasifikasi. Penelitian [7] pada tahun 2017 menyatakan Dari 2000 citra pada dataset, di antaranya terdapat dua bahwa penggunaan metode RF menghasilkan akurasi jenis citra logo kendaraan berdasarkan sisi pengambilan yang lebih baik dibandingkan K-NN untuk klasifikasi gambarnya yaitu 1255 citra logo kendaraan yang multi kelas benih dan daun tanaman dengan metode diambil dari sisi depan dan 745 citra logo kendaraan ekstraksi ciri LBP. Tahapan yang dilakukan pada proses LBP dimulai dari Random Forest (RF) adalah metode klasifikasi ensemble melakukan penghitungan selisih nilai keabuan antara learning yang terdiri dari kumpulan pohon keputusan setiap piksel pada citra dengan titik-titik sampel yang yang setiap hasil pohonnya bernilai satu unit suara untuk diambil dari piksel-piksel tetangganya.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
