Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/78032
Title: Deep learning convolutional network for image classification
Authors: Moektijono, Isselin
Keywords: DRNTU::Engineering::Mechanical engineering
Issue Date: 2019
Abstract: Deep learning architecture algorithms have been extensively developed and applied to various applications. The techniques have successfully improved the performance of difficult computer tasks such as computer vision, natural language processing, and speech recognition. This project aims to build and apply one of the well-known deep learning algorithms, Convolutional Neural Network to detect and classify different defects on manufacture parts, which categorized under image classification problem. The input data which is in the form of two-dimensional file of images which will be fed into various training models. The trained model reached a considered decent training accuracy result and could be used as foundation model to be applied for live prediction on video feed data.
URI: http://hdl.handle.net/10356/78032
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:MAE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
Final Report Complete.pdf
  Restricted Access
1.76 MBAdobe PDFView/Open

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.