| Paper Details: | Downloads: 415 |
| Serial Number: | P1151052920
|
| Title: | Text/Image separation in multistructured documents
|
| Authors: | Fattah Zirari and M’Bark Iggane and Driss Mammass and S. NICOLAS and Abdellatif Ennaji and F. Nouboud
|
| Abstract: | The separation of text / image is a major step in the processing of multi-structured documents. It consists of separating the document into two classes: text and image. In this context, it is important to implement approaches that can handle such documents. This paper presents a new method of separating text / image into a multi-structured document. The method developed is based on statistical analysis of texture coupled with a classification method of k-means. This is, initially, to browse the document by a sliding window, and calculate the texture parameters for each pixel, using a method to extract features such as co-occurrence matrix to obtain the characteristic vectors of the document. The distribution of these vectors using the k-means algorithm into two classes used to classify the pixels of the document as part of the text or image. Examples within the issue of separating text / image on newspapers illustrate this article
|
| Keywords: | co-occurrence matrix, texture, segmentation, K-means, document image
|
| Journal/Conference: | International Journal of Graphics, Vision and Image Processing
|
| Volume: | 10
|
| Issue: | 6
|
| Submission Date: | 9/1/2010 12:00:00 AM
|
| Review Date: | 10/1/2010 12:00:00 AM
|
| Publishing Date: | 12/31/2010 12:00:00 AM
|
| Article Downloads: | 415
|
| Download: |
|