Presentation is loading. Please wait.

Presentation is loading. Please wait.

Gili Werner. Motivation Detecting text in a natural scene is an important part of many Computer Vision tasks.

Similar presentations


Presentation on theme: "Gili Werner. Motivation Detecting text in a natural scene is an important part of many Computer Vision tasks."— Presentation transcript:

1 Gili Werner

2 Motivation Detecting text in a natural scene is an important part of many Computer Vision tasks

3 Motivation For example, the performance of optical character recognition (OCR) algorithms can be highly improved by first identifying the regions of text in the image

4 SWT Text Detector In this project I attempted to create a powerful and reliable tool for detecting text regions in an image, by using the Stroke Width Transform (SWT) grouping pixels together in an intelligent way, instead of looking for separating features of pixels

5 The Stroke Width Transform 3 major steps: 1. The stroke width transform A stroke in the image is a continuous band of a nearly constant width SWT is a local operator which calculates for each pixel the width of the most likely stroke containing the pixel

6 The Stroke Width Transform 2. Finding letter candidates Grouping the pixels into letter candidates based on their stroke width

7 The Stroke Width Transform 3. Grouping letter candidates into regions of text Group closely positioned letter candidates into regions of text Filters out many falsely-identified letter candidates, and improves the reliability of the algorithm results

8 Results

9

10 Strengths The SW Detector can detect letters of different languages (English, Hebrew, Arabic etc.) The text can be of varying sizes The text can be of different orientation Including curvy text Even handwriting can be detected

11 Weaknesses Appearance of noise Foliage resembles letters Does not handle round and curved letters as well Small and close letters tend to be grouped together in the SW labeling phase These groups may be dismissed in the ‘finding letter candidates’ phase

12 Questions?


Download ppt "Gili Werner. Motivation Detecting text in a natural scene is an important part of many Computer Vision tasks."

Similar presentations


Ads by Google