Panda recognition app

• Main Author: Woo, Alvin
• Other Authors: Kong Wai-Kin Adams
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2021
• Subjects: Engineering::Computer science and engineering
• Online Access: https://hdl.handle.net/10356/148314
• Institution: Nanyang Technological University

Pandas are known to be highly endangered animals [1]. The project aims to implement a deep learning algorithm that recognises panda faces into a mobile app to allow users to recognise the pandas easily and accurately. The panda recognition app’s purpose is to be able to scan a panda image and recognise the exact panda in the image. The project focuses on designing an android mobile app through Android studio software using Java. The algorithm of the panda image recognition and the trained model was provided. The panda recognition algorithm was coded in python. Therefore, the approach of this project is to use a server and client programming. The Android mobile app is the client that sends the image of the panda to the python server which is the panda recognition program. The python server will run the image recognition with the trained models and send its output to the android client. The mobile app manages to establish successful connections with the python server via the ip address of the server. The app is able to send the image path of the image to the python server and the algorithm retrieves the image using the image path given. The python server then runs the panda image recognition model and successful returns the result. In conclusion, the panda recognition mobile app is achieved through the client-server architecture and is able to display accurate results with the trained model in the python server.