SCENE TEXT SEGMENTATION BY APPLYING TRIMMED MEDIAN FILTER USING ENERGETIC EDGE
This proposed method is an accurate and strong method for detecting texts in natural scene images. There are many cases that text regions are not clearly noTable.by background regions due to brightness or illumination variations. The proposed scene text finding process finds out the scene text conte...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
ICT Academy of Tamil Nadu
2017-11-01
|
Series: | ICTACT Journal on Image and Video Processing |
Subjects: | |
Online Access: | http://ictactjournals.in/ArticleDetails.aspx?id=3234 |
id |
doaj-8001664d84184538a3495ff2dcedd1b5 |
---|---|
record_format |
Article |
spelling |
doaj-8001664d84184538a3495ff2dcedd1b52020-11-25T03:34:46ZengICT Academy of Tamil NaduICTACT Journal on Image and Video Processing0976-90990976-91022017-11-01821626163210.21917/ijivp.2017.0228SCENE TEXT SEGMENTATION BY APPLYING TRIMMED MEDIAN FILTER USING ENERGETIC EDGET Beula Bell0BM K Jeya Kumar1Manomaniam Sundaranar University, IndiaNoorul Islam University, IndiaThis proposed method is an accurate and strong method for detecting texts in natural scene images. There are many cases that text regions are not clearly noTable.by background regions due to brightness or illumination variations. The proposed scene text finding process finds out the scene text contents from the natural scene images using the sophisticated edge revealing methods, the local directional number feature and linked map generation process. This proposed method takes natural scene image as input and detects the scene text regions. The detected scene text regions are marked for visual identification for human eyes.http://ictactjournals.in/ArticleDetails.aspx?id=3234Noise ReductionEnergetic Edge DetectionLocal Directional NumberLinked MapNon Seen Text Rejection |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
T Beula Bell BM K Jeya Kumar |
spellingShingle |
T Beula Bell BM K Jeya Kumar SCENE TEXT SEGMENTATION BY APPLYING TRIMMED MEDIAN FILTER USING ENERGETIC EDGE ICTACT Journal on Image and Video Processing Noise Reduction Energetic Edge Detection Local Directional Number Linked Map Non Seen Text Rejection |
author_facet |
T Beula Bell BM K Jeya Kumar |
author_sort |
T Beula Bell |
title |
SCENE TEXT SEGMENTATION BY APPLYING TRIMMED MEDIAN FILTER USING ENERGETIC EDGE |
title_short |
SCENE TEXT SEGMENTATION BY APPLYING TRIMMED MEDIAN FILTER USING ENERGETIC EDGE |
title_full |
SCENE TEXT SEGMENTATION BY APPLYING TRIMMED MEDIAN FILTER USING ENERGETIC EDGE |
title_fullStr |
SCENE TEXT SEGMENTATION BY APPLYING TRIMMED MEDIAN FILTER USING ENERGETIC EDGE |
title_full_unstemmed |
SCENE TEXT SEGMENTATION BY APPLYING TRIMMED MEDIAN FILTER USING ENERGETIC EDGE |
title_sort |
scene text segmentation by applying trimmed median filter using energetic edge |
publisher |
ICT Academy of Tamil Nadu |
series |
ICTACT Journal on Image and Video Processing |
issn |
0976-9099 0976-9102 |
publishDate |
2017-11-01 |
description |
This proposed method is an accurate and strong method for detecting texts in natural scene images. There are many cases that text regions are not clearly noTable.by background regions due to brightness or illumination variations. The proposed scene text finding process finds out the scene text contents from the natural scene images using the sophisticated edge revealing methods, the local directional number feature and linked map generation process. This proposed method takes natural scene image as input and detects the scene text regions. The detected scene text regions are marked for visual identification for human eyes. |
topic |
Noise Reduction Energetic Edge Detection Local Directional Number Linked Map Non Seen Text Rejection |
url |
http://ictactjournals.in/ArticleDetails.aspx?id=3234 |
work_keys_str_mv |
AT tbeulabell scenetextsegmentationbyapplyingtrimmedmedianfilterusingenergeticedge AT bmkjeyakumar scenetextsegmentationbyapplyingtrimmedmedianfilterusingenergeticedge |
_version_ |
1724557543327399936 |