深度學習型影像分割方法探討

A Study of Image Segmentation Based on Deep Learning Method

孟祥浩(Shiang-Hao Meng)

指導教授 ： 汪柏

淡江大學/工學院/資訊工程學系碩士在職專班/碩士(2022年)

https://doi.org/10.6846/TKU.2022.00778

摘要

在本論文中，我們將針對具有防偽浮水印的紙本發票轉換後產生的數位資料做自動化的防偽浮水印去除並且優化數字部份的辨識度。希望能取代傳統的影像分割方式並且能夠達到一定程度的防偽浮水印消除率與提昇數字部份的辨識度。
本論文主要研究重點在於如何使用深度學習去除防偽浮水印，透過建立訓練組及驗証組的資料集訓練U-NET模型，再藉由訓練好的U-NET模型去除防偽浮水印，提高資料的辨識度。

關鍵字

深度學習 ； 影像分割 ； U-NET

並列摘要

In this paper, we introduce a method to do image segmentation in documents with anti-counterfeiting watermarks. We proposed a method based on the Deep Learning algorithm to remove the noise of anti-counterfeiting watermarks. The main research purpose of this paper is how to use deep learning U-NET model to remove anti-counterfeiting watermarks. The U-NET model is trained by establishing the data set of the training images and the validation images, and then the anti-counterfeiting watermark will be removed by the trained U-NET model to improve the identification of data.

並列關鍵字

Image Segmentation ； Deep Learning ； U-NET

參考文獻

[1] Thresholding (4, April, 2022) Retrieved 9, April, 2022 from https://en.wikipedia.org/wiki/Thresholding_(image_processing)

[2] Ulfat Imdad, Muhammad Asif, Mirza Tahir Ahmad, Osama Sohaib, Muhammad Kashif Hanif, Muhammad Hasanain Chaudary” Three Dimensional Point Cloud Compression and

Decompression Using Polynomials of Degree One” , Symmetry, Vol 11 , Issue 2, February 2019

[3] Edge detection (22, March, 2022‎) Retrieved 9, April, 2022 from

https://en.wikipedia.org/wiki/Edge_detection