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

Slides:



Advertisements
Similar presentations
By: Mani Baghaei Fard.  During recent years number of moving vehicles in roads and highways has been considerably increased.
Advertisements

High-level Component Filtering for Robust Scene Text Detection
Terrain reconstruction through the contour lines of the scanned topographic maps Meir Tseitlin 2007.
1Ellen L. Walker Edges Humans easily understand “line drawings” as pictures.
Edge detection Goal: Identify sudden changes (discontinuities) in an image Intuitively, most semantic and shape information from the image can be encoded.
Lecture 5 Template matching
Text Detection in Video Min Cai Background  Video OCR: Text detection, extraction and recognition  Detection Target: Artificial text  Text.
Textual Information Access for the Visually Impaired Ramani Duraiswami.
EE663 Image Processing Edge Detection 2 Dr. Samir H. Abdul-Jauwad Electrical Engineering Department King Fahd University of Petroleum & Minerals.
Processing Digital Images. Filtering Analysis –Recognition Transmission.
1 Learning to Detect Natural Image Boundaries David Martin, Charless Fowlkes, Jitendra Malik Computer Science Division University of California at Berkeley.
Computer Vision Introduction to Image formats, reading and writing images, and image environments Image filtering.
Quadtrees, Octrees and their Applications in Digital Image Processing
Object Recognition Using Distinctive Image Feature From Scale-Invariant Key point D. Lowe, IJCV 2004 Presenting – Anat Kaspi.
Lecture 4: Edge Based Vision Dr Carole Twining Thursday 18th March 2:00pm – 2:50pm.
1/25 Writing Character sets Unicode Input methods.
1 Chapter 21 Machine Vision. 2 Chapter 21 Contents (1) l Human Vision l Image Processing l Edge Detection l Convolution and the Canny Edge Detector l.
Edge detection Goal: Identify sudden changes (discontinuities) in an image Intuitively, most semantic and shape information from the image can be encoded.
Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.
Classification with Hyperplanes Defines a boundary between various points of data which represent examples plotted in multidimensional space according.
FEATURE EXTRACTION FOR JAVA CHARACTER RECOGNITION Rudy Adipranata, Liliana, Meiliana Indrawijaya, Gregorius Satia Budhi Informatics Department, Petra Christian.
Computer vision.
Edit by Dalton Lin Copyright © 2012 Elsevier Inc. All rights reserved.. Chapter 1 Vision, the Challenge.
An efficient method of license plate location Pattern Recognition Letters 26 (2005) Journal of Electronic Imaging 11(4), (October 2002)
S EGMENTATION FOR H ANDWRITTEN D OCUMENTS Omar Alaql Fab. 20, 2014.
CS 6825: Binary Image Processing – binary blob metrics
Development of an OCR System Nathan Harmata TJHSST Computer Systems Lab
September 23, 2014Computer Vision Lecture 5: Binary Image Processing 1 Binary Images Binary images are grayscale images with only two possible levels of.
Institute for Visualization and Perception Research 1 © Copyright 2000 Haim Levkowitz Introduction (Foley & Van Dam Ch 1) Uses of computer graphics … Some.
Quadtrees, Octrees and their Applications in Digital Image Processing.
Chapter 4: Pattern Recognition. Classification is a process that assigns a label to an object according to some representation of the object’s properties.
1 Research Question  Can a vision-based mobile robot  with limited computation and memory,  and rapidly varying camera positions,  operate autonomously.
Object Recognition in ROS Using Feature Extractors and Feature Matchers By Dolev Shapira.
1 Eye Detection in Images Introduction To Computational and biological Vision Lecturer : Ohad Ben Shahar Written by : Itai Bechor.
Presented By Lingzhou Lu & Ziliang Jiao. Domain ● Optical Character Recogntion (OCR) ● Upper-case letters only.
Learning low-level vision Computer Examples by Michael Ross.
APECE-505 Intelligent System Engineering Basics of Digital Image Processing! Md. Atiqur Rahman Ahad Reference books: – Digital Image Processing, Gonzalez.
FACE DETECTION : AMIT BHAMARE. WHAT IS FACE DETECTION ? Face detection is computer based technology which detect the face in digital image. Trivial task.
October 1, 2013Computer Vision Lecture 9: From Edges to Contours 1 Canny Edge Detector However, usually there will still be noise in the array E[i, j],
Lukáš Neumann and Jiří Matas Centre for Machine Perception, Department of Cybernetics Czech Technical University, Prague 1.
Lecture 04 Edge Detection Lecture 04 Edge Detection Mata kuliah: T Computer Vision Tahun: 2010.
Edge Segmentation in Computer Images CSE350/ Sep 03.
Preliminary Transformations Presented By: -Mona Saudagar Under Guidance of: - Prof. S. V. Jain Multi Oriented Text Recognition In Digital Images.
Wrapping Snakes For Improved Lip Segmentation Matthew Ramage Dr Euan Lindsay (Supervisor) Department of Mechanical Engineering.
Instructor: Mircea Nicolescu Lecture 5 CS 485 / 685 Computer Vision.
Digital Image Processing
Image Features (I) Dr. Chang Shu COMP 4900C Winter 2008.
Arabic Handwriting Recognition Thomas Taylor. Roadmap  Introduction to Handwriting Recognition  Introduction to Arabic Language  Challenges of Recognition.
1 Edge Operators a kind of filtering that leads to useful features.
Portable Camera-Based Assistive Text and Product Label Reading From Hand-Held Objects for Blind Persons.
Automatic License Plate Recognition for Electronic Payment system Chiu Wing Cheung d.
OCR Reading.
2. Skin - color filtering.
- photometric aspects of image formation gray level images
S.Rajeswari Head , Scientific Information Resource Division
Face detection in complex images
Advanced Higher Computing Based on Heriot-Watt University Scholar Materials Applications of AI – Vision and Languages 1.
Introduction Computer vision is the analysis of digital images
Machine Learning & Digital Humanities
Fourier Transform: Real-World Images
Text Detection in Images and Video
Introduction Computer vision is the analysis of digital images
ECE 692 – Advanced Topics in Computer Vision
a kind of filtering that leads to useful features
a kind of filtering that leads to useful features
First Homework One week
Introduction Computer vision is the analysis of digital images
Introduction to Artificial Intelligence Lecture 22: Computer Vision II
Presentation transcript:

Gili Werner

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

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

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

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

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

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

Results

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

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

Questions?