Date of Award

May 2020

Degree Type

Thesis

Degree Name

Master of Science

Department

Engineering

First Advisor

Yi Hu

Committee Members

Yin Wang, Jun Zhang

Keywords

machine learning, object detection, SPL meter

Abstract

Sound pressure level (SPL) meter is one of the useful devices used for measuring the sound level pressure. The measurement device displays the SPL value in decibels (dB) on a standard LCD screen (no backlight). We could base on the digit number shown on the LCD screen to do some adjustments or evaluations. Thus, SPL has been widely used in several fields to quantify different noise, such as industrial, environmental, and aircraft noise. However, in my basic knowledge, there is no previous study used machine learning to auto-recognize the digit on the SPL meter. This thesis presents a novel system that recognizes the digit number on the SPL meter automatically.

In this thesis, we present a novel approach to preprocess the image of SPL meter. This approach could help us to reduce the noise and amplify the number. Then, we train two machine learning models to auto-recognize the multi-digit on the SPL meter. In our experiment result, it could be efficient to detect the SPL meter under high accuracy. There are two main claims to our thesis. First, this is the original research that utilized the ML to auto-recognize the SPL meter. Second, we are the only researchers to set up the SPL meter dataset which includes one-digit and multi-digit images.

Download

Share

COinS