Reptile Recognition based on Convolutional Neural Network
Condro Kartiko1, Agi Prasetiadi2, Elisa Usada3

1Condro Kartiko, Department of Software Engineering, Institut Teknologi Telkom Purwokerto, Indonesia. 

2Agi Prasetiadi, Department of Informatics, Institut Teknologi Telkom Purwokerto, Indonesia. 

3Elisa Usada, Department of Informatics, Institut Teknologi Telkom Purwokerto, Indonesia. 

Manuscript received on 09 January 2020 | Revised Manuscript received on 05 February 2020 | Manuscript Published on 20 February 2020 | PP: 112-115 | Volume-9 Issue-3S January 2020 | Retrieval Number: C10260193S20/2020©BEIESP | DOI: 10.35940/ijitee.C1026.0193S20

Open Access | Editorial and Publishing Policies | Cite | Zenodo | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (

Abstract: Indonesian people are less interested in reptile animals. These are because most Indonesian people have the mindset that reptiles are difficult to tame and are focused on things about the ferocity of these animals in their natural habitat. Therefore it is necessary to have the means to identify reptile objects as one of the educational tools for introducing reptiles to the public. This research aims to produce a specialized Convolutional Neural Network model for recognizing reptile species. We also expand the model for recognizing another reptile species such as Snake, Crocodile, Turtle, and Gecko. Thousands of reptile images are being trained inside our model in order to obtain a kernel that can be used to automate reptile species recognition based on ordinary camera images. Our model currently reaches 64.3% accuracy for detecting 14 different species. Finally, as a suggestion for the next research, further enrichment especially from the background extraction process is needed to increase the accuracy of reptile detection.

Keywords: Reptile; Species Recognition; Automatic Detection; Convolutional Neural Network.
Scope of the Article: Neural Information Processing