Automatic Shadow Detection from a Single Image

碩士 === 國立臺灣大學 === 資訊工程學研究所 === 101 === Shadow detection is one of major topics in computer vision. Shadow usually causes interference when preforming image segmentation, tracking, face detection, and object recognition. Thus, detecting shadow region is an important step before shadow removal process...

Full description

Bibliographic Details
Main Authors: Shun-Wen Cheng, 鄭舜文
Other Authors: 李明穗
Format: Others
Language:en_US
Published: 2013
Online Access:http://ndltd.ncl.edu.tw/handle/72901432280737229354
id ndltd-TW-101NTU05392038
record_format oai_dc
spelling ndltd-TW-101NTU053920382016-03-16T04:15:06Z http://ndltd.ncl.edu.tw/handle/72901432280737229354 Automatic Shadow Detection from a Single Image 基於單張影像之自動偵測影子方法 Shun-Wen Cheng 鄭舜文 碩士 國立臺灣大學 資訊工程學研究所 101 Shadow detection is one of major topics in computer vision. Shadow usually causes interference when preforming image segmentation, tracking, face detection, and object recognition. Thus, detecting shadow region is an important step before shadow removal process. It is a challenging task that most of method need users to provide strokes to indicate location of shadow and only few of methods can automatically detect shadow region. This thesis proposed a method that can detect shadow automatically. The pairwise classification is performed to classify the relationship between all the pair of patches in the input image, and Gaussian Mixture Model (GMM) is applied to obtain main color statistic of the shadow patches and enhance accuracy of the detection, then the input image is upsampled to find the small area of shadow. Finally, the detected shadow region is refined by mean-shift segmentation. The experimental result shows the proposed method can generate accurate shadow map without any user assistance. 李明穗 2013 學位論文 ; thesis 45 en_US
collection NDLTD
language en_US
format Others
sources NDLTD
description 碩士 === 國立臺灣大學 === 資訊工程學研究所 === 101 === Shadow detection is one of major topics in computer vision. Shadow usually causes interference when preforming image segmentation, tracking, face detection, and object recognition. Thus, detecting shadow region is an important step before shadow removal process. It is a challenging task that most of method need users to provide strokes to indicate location of shadow and only few of methods can automatically detect shadow region. This thesis proposed a method that can detect shadow automatically. The pairwise classification is performed to classify the relationship between all the pair of patches in the input image, and Gaussian Mixture Model (GMM) is applied to obtain main color statistic of the shadow patches and enhance accuracy of the detection, then the input image is upsampled to find the small area of shadow. Finally, the detected shadow region is refined by mean-shift segmentation. The experimental result shows the proposed method can generate accurate shadow map without any user assistance.
author2 李明穗
author_facet 李明穗
Shun-Wen Cheng
鄭舜文
author Shun-Wen Cheng
鄭舜文
spellingShingle Shun-Wen Cheng
鄭舜文
Automatic Shadow Detection from a Single Image
author_sort Shun-Wen Cheng
title Automatic Shadow Detection from a Single Image
title_short Automatic Shadow Detection from a Single Image
title_full Automatic Shadow Detection from a Single Image
title_fullStr Automatic Shadow Detection from a Single Image
title_full_unstemmed Automatic Shadow Detection from a Single Image
title_sort automatic shadow detection from a single image
publishDate 2013
url http://ndltd.ncl.edu.tw/handle/72901432280737229354
work_keys_str_mv AT shunwencheng automaticshadowdetectionfromasingleimage
AT zhèngshùnwén automaticshadowdetectionfromasingleimage
AT shunwencheng jīyúdānzhāngyǐngxiàngzhīzìdòngzhēncèyǐngzifāngfǎ
AT zhèngshùnwén jīyúdānzhāngyǐngxiàngzhīzìdòngzhēncèyǐngzifāngfǎ
_version_ 1718206394225655808