Real-Time Object Detection For Wayang Punakawan Identification Using Deep Learning

Abstract

Indonesia is a country that has a variety of cultures, one of which is wayang kulit. This typical javanese performance art must continue to be preserved so that to be known by future generations. There are many wayang figures in Indonesia, and the most famous is punakawan. Wayang punakawan consists of four character namely semar, gareng petruk, and bagong. To preserve wayang punakawan to be known by the next generation, then in this study created a system that is able to identify real-time punakawan object using deep learning technology. The method that used is Single Shot Multiple Detector (SSD) as one of the models of deep learning that has a good ability in classifying data with three-dimensional structures such as real-time video. SSD model with MobileNet layer can work in slight computation, so that it can be run in real-time system. To classify object there are two steps that must be done such as training process and testing process. Training process takes 28 hours with 100.000 steps of iteration.The result of training process is a model which used to identify object. Based on the test result obtained an accuracy to detect object was 98,86%. This prove that the system has been able to optimize object in real-time accurately.

Deteksi Objek Menggunakan Metode Single Shot Multibox Detector Pada Alat Bantu Tongkat Tunanetra Berbasis Kamera

“…Pengolahan citra digital merupakan pemrosesan gambar maupun gambar bergerak berdimensi dua melalui komputer digital. Secara umum hal ini dibagi menjadi dua proses yaitu memperbaiki kualitas suatu gambar sehingga dapat lebih mudah diinterpretasi oleh manusia dan mengolah informasi yang terdapat pada suatu gambar untuk pengenalan objek secara otomatis [5].…”

“…Jarak yang digunakan adalah dalam rentang jarak efektif yang didapat pada uji fungsionalitas sebelumnya. Untuk masing-masing tempat dilakukan 30 kali pengujian, masing-masing 5…”

Object Detection to Identify Shapes of Swallow Nests Using a Deep Learning Algorithm

“…One of the deep learning architectures for creating object detection models with a learning process using data in the form of digital images is SSD MobileNet. SSD MobileNet is an SSD architecture (Single Shot Multibox Detector) with the MobileNet extractor feature, which architecture can work with little computation, so it is fit to run in real-time [5]. SSD itself is an object detection architecture that has high accuracy and is fast [6], while MobileNet is a lightweight feature extractor [7].…”