University Name: SIT740 Image Recognition and Machine Learning Project

This project explores image recognition using machine learning, specifically focusing on the implementation of TensorFlow to address challenges in AI and robotics. The study aims to develop a simulation program to recognize images, enhancing the capabilities of intelligent systems. The project highlights the benefits of this solution, such as improved security and reduced workload in forensic investigations. The solution's limitations, such as dependency on a database, are also acknowledged. The project demonstrates the practical application of TensorFlow and its potential for commercial purposes, providing a valuable resource for students studying AI and related fields. Screenshots of the simulation are included to illustrate the practical application and functionality of the solution.

Running head: DISTINCTION TASK 8.3
SIT740 Research and Development in Information Technology
Distinction Task 8.3: Investigation of the tool for given problem
Student Name:
University Name:

1DISTINCTION TASK 8.3
Recognition of Image and Machine Learning
The recognition of images is an important task to develop and test approaches of machine
learning. The vision is a powerful sense which is available in humans naturally but the question
remains in context to robotics on how to teach the robots to recognize images with accuracy.
Hence, this project has been chosen to identify a tool that will help to solve the issue.
TensorFlow, an open source programming tool for dataflow has been chosen so that the concept
behind recognition of images by robots can be easily implemented in the real world. The
objective of this study is solve the concern regarding image recognition by robots. In this study, a
simulation program has been developed for implementing a prototype of the real life scenario.
The advantage of this solution is that it will add as a security measure for household as well as
commercial intelligent systems. The solution will also help to reduce the workload on humans to
identify objects within an image during forensic investigations. The disadvantage of this solution
is that it can operate properly only with the images that are stored in the database. The feature of
the proposed solution is that it can be embedded with intelligent systems such that those can be
used for commercial purposes.

2DISTINCTION TASK 8.3
Screenshots of the simulation running related to the issue
Figure 1: Operation of TensorFlow
(Source: Created by Author)
Figure 2: Execution of the designed program
(Source: Created by Author)

3DISTINCTION TASK 8.3
Bibliography
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving,
G., Isard, M. and Kudlur, M., 2016, November. TensorFlow: A System for Large-Scale Machine
Learning. In OSDI (Vol. 16, pp. 265-283).
Dean, J., 2015. Large-scale deep learning for intelligent computer systems. BayLearn keynote
speech.