Identifying Wood Types Using Convolutional Neural Network

ROSTINA

Informasi Dasar

20.04.4252
006.31
Karya Ilmiah - Skripsi (S1) - Reference

Abstract. This paper explains about identifying wood types using a macroscopic image on wood surfaces which have speci?c characteristics, such as cross-section, radial, and tangential. Generally, on the identi?cation process of wood types, traders and carpenters only do the checking which focuses on the cross-section part, it happened because of the dif?culty of identifying the radial and the tangential wood surfaces. By using the convolutional neural network method, it can extract images with several layers, so that it is possible to do an identi?cation process on all three wood surfaces. There are approximately 3,000 images which consist of 3 species of wood with each cross-section, radial and tangential surfaces. Identi?cation results showed great potential even though there was a small amount of misclassi?cation caused by similarities in di?erent species and di?erences in similar species. Within the process, classi?cation results obtained by the amount training accuracy 89% and testing accuracy 96% for the cross-section, 79% for the radial and 88% for the tangential planes. Thus, the identi?cation of wood surfaces with high accuracy result was at the cross-section surface. abstract environment.

Subjek

Machine - learning
 

Katalog

Identifying Wood Types Using Convolutional Neural Network
 
-
Indonesia

Sirkulasi

Rp. 0
Rp. 0
Tidak

Pengarang

ROSTINA
Perorangan
Putu Harry Gunawan, Esa Prakasa
 

Penerbit

Universitas Telkom, S1 Informatika
Bandung
2020

Koleksi

Kompetensi

 

Download / Flippingbook

 

Ulasan

Belum ada ulasan yang diberikan
anda harus sign-in untuk memberikan ulasan ke katalog ini