Video text extraction method based on clustering
A new method for video text extraction in order to overcome the weakness of existing methods was proposed.First,multi-scale text location and text region refinement in text location step were adopted.Then an improved K-means clustering method was used to segment text regions to obtain a binarized im...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2009-01-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/74652683/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841537556565458944 |
|---|---|
| author | SONG Yan1 LIU An-an1 ZHANG Yong-dong1 LIN Shou-xun1 |
| author_facet | SONG Yan1 LIU An-an1 ZHANG Yong-dong1 LIN Shou-xun1 |
| author_sort | SONG Yan1 |
| collection | DOAJ |
| description | A new method for video text extraction in order to overcome the weakness of existing methods was proposed.First,multi-scale text location and text region refinement in text location step were adopted.Then an improved K-means clustering method was used to segment text regions to obtain a binarized image in text segmentation step.Finally,OCR software was used to recognize text.The results of experiment show that the method can effctively used in sensitive words detection in videos from the Internet. |
| format | Article |
| id | doaj-art-91876f162df04175adb44ca97477fdc8 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2009-01-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-91876f162df04175adb44ca97477fdc82025-01-14T08:30:30ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2009-01-013013614074652683Video text extraction method based on clusteringSONG Yan1LIU An-an1ZHANG Yong-dong1LIN Shou-xun1A new method for video text extraction in order to overcome the weakness of existing methods was proposed.First,multi-scale text location and text region refinement in text location step were adopted.Then an improved K-means clustering method was used to segment text regions to obtain a binarized image in text segmentation step.Finally,OCR software was used to recognize text.The results of experiment show that the method can effctively used in sensitive words detection in videos from the Internet.http://www.joconline.com.cn/zh/article/74652683/text extractionOCRK-means clustering |
| spellingShingle | SONG Yan1 LIU An-an1 ZHANG Yong-dong1 LIN Shou-xun1 Video text extraction method based on clustering Tongxin xuebao text extraction OCR K-means clustering |
| title | Video text extraction method based on clustering |
| title_full | Video text extraction method based on clustering |
| title_fullStr | Video text extraction method based on clustering |
| title_full_unstemmed | Video text extraction method based on clustering |
| title_short | Video text extraction method based on clustering |
| title_sort | video text extraction method based on clustering |
| topic | text extraction OCR K-means clustering |
| url | http://www.joconline.com.cn/zh/article/74652683/ |
| work_keys_str_mv | AT songyan1 videotextextractionmethodbasedonclustering AT liuanan1 videotextextractionmethodbasedonclustering AT zhangyongdong1 videotextextractionmethodbasedonclustering AT linshouxun1 videotextextractionmethodbasedonclustering |