New Search

Advanced search
Open Access

Model CNN LeNet dalam Rekognisi Angka Tahun pada Prasasti Peninggalan Kerajaan Majapahit

Tri Septianto, Endang Setyati, Joan Santoso
Jurnal Teknologi dan Sistem Komputer , Volume 6, pp 106-109; doi:10.14710/jtsiskom.6.3.2018.106-109

Abstract: The object of the inscription has a feature that is difficult to recognize because it is generally eroded and faded. This study analyzed the performance of CNN using LeNet model to recognize the object of year digit found on the relic inscriptions of Majapahit Kingdom. Object recognition with LeNet model had a maximum accuracy of 85.08% at 10 epoch in 6069 seconds. This LeNet's performance was better than the VGG as the comparison model with a maximum accuracy of 11.39% at 10 epoch in 40223 seconds.
Keywords: model / CNN / Relic / Faded / Pada / kerajaan / Lenet / Majapahit / Angka / rekognisi

Share this article

Click here to see the statistics on "Jurnal Teknologi dan Sistem Komputer" .