Open Access Journal

ISSN : 2394-2320 (Online)

International Journal of Engineering Research in Computer Science and Engineering (IJERCSE)

Monthly Journal for Computer Science and Engineering

Open Access Journal

International Journal of Engineering Research in Computer Science and Engineering (IJERCSE)

Monthly Journal for Computer Science and Engineering

ISSN : 2394-2320 (Online)

An Artificial Intelligence-Based Approach to Detect the Quality of Wooden Panels using Convolutional Neural Networks

Author : Tom Tuunainen 1 Olli Isohanni 2 Mitha Rachel Jose 3

Date of Publication :25th September 2023

Abstract: Convolutional Neural Network (CNN) is a network architecture for deep learning that learns directly from data [10]. CNN are used to obtain patterns from images to recognize objects, classes, and categories. These are used to classify audio, time series, and signal data. MobileNet is a CNN architecture that is developed to build light-weight deep neural networks. Image classification categorizes the input images into pre-defined labels or categories. This study is performed to detect the quality of Medium Density Fiberboard (MDF) wooden panels. This model learns from the image dataset of wooden panels and produces accurate results. The panels are suitable for many kinds of interior styles. The panels can be made of MDF or woods such as high-quality spruce or pine. This experiment focuses on the quality of the MDF panels and the wooden panels of various sizes, which might differ in length, depth and thickness. The analysis aims to detect the quality of wooden panels using a CNN architecture called MobileNet. The CNN is trained with three categories; PASS, FAIL, and empty, with each category containing 1000 samples. The samples containing high-quality panels were categorized as PASS, and broken or defective panels were categorized as FAIL. If there are no panels, then the CNN defaults to the empty category.

Reference :

Will Updated soon

Recent Article