Tactile identification of fruits using machine learning/deep learning
Object detection is becoming increasingly common due to the rise of automation. More autonomous robots are using object detection techniques to generate an appropriate output depending on their tasks. To perceive their surroundings and collect data, most autonomous robots use computer vision. How...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/167727 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Summary: | Object detection is becoming increasingly common due to the rise of automation. More
autonomous robots are using object detection techniques to generate an appropriate
output depending on their tasks. To perceive their surroundings and collect data, most
autonomous robots use computer vision. However, there are certain situations where
computer vision may not be the most optimal solution. For example, in situations where
haptic properties such as the height or width of an object need to be measured, computer
vision alone may not be sufficient. In such cases, other methods must be used to obtain
the necessary information.
Tactile identification can be used as an alternative method for autonomous robots to
perceive their surroundings. This approach has been extensively researched over the
years and involves using sensors to collect data, which is then trained with a machine
learning or deep learning algorithm.
Therefore, this project will use an in-house developed sensor together with machine
learning and deep learning algorithms to classify the fruits. The data will be collected
from five different types of fruit from the sensors. This data will then be used to train the
machine learning and deep learning algorithms. Finally, a new batch of fruits data will be
collected and tested to determine if the algorithms have successfully learned the features
of each fruit.
This project report will document the process of assembling the sensor, data collection,
data processing and analysis of the results. |
---|