Multi-Resolution and JND-Based Image Segmentation Algorithm
碩士 === 國立雲林科技大學 === 電機工程系碩士班 === 90 === Image segmentation is a basic step of image processing , such as computer vision , image analysis, medical image and the object-oriented compression standard : MPEG4. The complexity of image segmentation is a barrier of image real-time applications nowadays....
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2002
|
Online Access: | http://ndltd.ncl.edu.tw/handle/84233388135855627981 |
id |
ndltd-TW-090YUNTE441026 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-090YUNTE4410262016-06-24T04:15:30Z http://ndltd.ncl.edu.tw/handle/84233388135855627981 Multi-Resolution and JND-Based Image Segmentation Algorithm 多重解析度與應用視覺特性之影像分割演算法 Ming-Tzung Huang 洪銘聰 碩士 國立雲林科技大學 電機工程系碩士班 90 Image segmentation is a basic step of image processing , such as computer vision , image analysis, medical image and the object-oriented compression standard : MPEG4. The complexity of image segmentation is a barrier of image real-time applications nowadays. Because the segmentation results are judged by people, a good image segmentation algorithm should utilize human perception properties effectively. In the thesis , our algorithm utilizing the JND (Just Noticeable Different) and multi-resolution properties can reduce computation load effectively and get a concise result. Besides, we also proposed another image segmentation algorithm without watershed processing , we call it “the JND Pyramid Image Segmentation Algorithm”. It is a hybrid of edge detection and region growing techniques ,and it can produce the different segmentation levels to represent an image effectively. Day-Fann Shen 沈岱範 2002 學位論文 ; thesis 86 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立雲林科技大學 === 電機工程系碩士班 === 90 === Image segmentation is a basic step of image processing , such as computer vision , image analysis, medical image and the object-oriented compression standard : MPEG4. The complexity of image segmentation is a barrier of image real-time applications nowadays. Because the segmentation results are judged by people, a good image segmentation algorithm should utilize human perception properties effectively. In the thesis , our algorithm utilizing the JND (Just Noticeable Different) and multi-resolution properties can reduce computation load effectively and get a concise result.
Besides, we also proposed another image segmentation algorithm without watershed processing , we call it “the JND Pyramid Image Segmentation Algorithm”. It is a hybrid of edge detection and region growing techniques ,and it can produce the different segmentation levels to represent an image effectively.
|
author2 |
Day-Fann Shen |
author_facet |
Day-Fann Shen Ming-Tzung Huang 洪銘聰 |
author |
Ming-Tzung Huang 洪銘聰 |
spellingShingle |
Ming-Tzung Huang 洪銘聰 Multi-Resolution and JND-Based Image Segmentation Algorithm |
author_sort |
Ming-Tzung Huang |
title |
Multi-Resolution and JND-Based Image Segmentation Algorithm |
title_short |
Multi-Resolution and JND-Based Image Segmentation Algorithm |
title_full |
Multi-Resolution and JND-Based Image Segmentation Algorithm |
title_fullStr |
Multi-Resolution and JND-Based Image Segmentation Algorithm |
title_full_unstemmed |
Multi-Resolution and JND-Based Image Segmentation Algorithm |
title_sort |
multi-resolution and jnd-based image segmentation algorithm |
publishDate |
2002 |
url |
http://ndltd.ncl.edu.tw/handle/84233388135855627981 |
work_keys_str_mv |
AT mingtzunghuang multiresolutionandjndbasedimagesegmentationalgorithm AT hóngmíngcōng multiresolutionandjndbasedimagesegmentationalgorithm AT mingtzunghuang duōzhòngjiěxīdùyǔyīngyòngshìjuétèxìngzhīyǐngxiàngfēngēyǎnsuànfǎ AT hóngmíngcōng duōzhòngjiěxīdùyǔyīngyòngshìjuétèxìngzhīyǐngxiàngfēngēyǎnsuànfǎ |
_version_ |
1718322035564740608 |