a laplacian method for video text detection n.
Download
Skip this Video
Download Presentation
A Laplacian Method for Video Text Detection

Loading in 2 Seconds...

play fullscreen
1 / 40

A Laplacian Method for Video Text Detection - PowerPoint PPT Presentation


  • 152 Views
  • Uploaded on

A Laplacian Method for Video Text Detection. Trung Quy Phan, Palaiahnakote Shivakumara and Chew Lim Tan. Agenda . Introduction Previous Methods Laplacian Method Experimental Results Conclusion and Future Work. Agenda . Introduction Previous Methods Laplacian Method Experimental Results

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'A Laplacian Method for Video Text Detection' - avalon


Download Now An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
a laplacian method for video text detection

A Laplacian Methodfor Video Text Detection

Trung Quy Phan, Palaiahnakote Shivakumara and Chew Lim Tan

agenda
Agenda
  • Introduction
  • Previous Methods
  • Laplacian Method
  • Experimental Results
  • Conclusion and Future Work
agenda1
Agenda
  • Introduction
  • Previous Methods
  • Laplacian Method
  • Experimental Results
  • Conclusion and Future Work
introduction
Introduction
  • Motivation: video indexing
    • Generates keywords from text
    • Able to retrieve a particular event or image
  • Graphic & scene text
  • Different from camera-based images
    • Low resolution
    • Complex background
    • Text movement & distortion
agenda2
Agenda
  • Introduction
  • Previous Methods
  • Laplacian Method
  • Experimental Results
  • Conclusion and Future Work
previous methods
Previous Methods
  • Connected component-based
    • Assumes text pixels have the same colors or grayscale intensities
  • Edge-based
    • Works well for high contrast text
    • Produces false positives for complex backgrounds
  • Texture-based
    • Trainable
    • Computationally expensive
agenda3
Agenda
  • Introduction
  • Previous Methods
  • Laplacian Method
  • Experimental Results
  • Conclusion and Future Work
laplacian method
Laplacian Method
  • Step 1: Text Detection
    • Identifies candidate text regions
  • Step 2: Boundary Refinement
    • Refines the text block boundaries
  • Step 3: False Positive Elimination
agenda4
Agenda
  • Introduction
  • Previous Methods
  • Laplacian Method
    • Text Detection
    • Boundary Refinement
    • False Positive Elimination
  • Experimental Results
  • Conclusion and Future Work
text detection
Text Detection
  • Text regions have a large number of discontinuities
  • Input  grayscale  Laplacian-filtered to detect the discontinuities in four directions
text detection1
Text Detection
  • Text regions typically have many positive and negative peaks of large magnitudes
text detection2
Text Detection
  • Maximum gradient difference (MGD) [1]
    • For each 1 × N window, MGD is the difference between the maximum and minimum values
  • Text regions have larger MGD values because of the peaks of large magnitudes
text detection3
Text Detection
  • K-means clustering on the MGD map
    • K = 2, Euclidean distance
agenda5
Agenda
  • Introduction
  • Previous Methods
  • Laplacian Method
    • Text Detection
    • Boundary Refinement
    • False Positive Elimination
  • Experimental Results
  • Conclusion and Future Work
boundary refinement
Boundary Refinement
  • Binary Sobel edge map SM of the input image (only for text regions)
  • Horizontal and vertical projection profiles
boundary refinement1
Boundary Refinement
  • Horizontal
  • Vertical
agenda6
Agenda
  • Introduction
  • Previous Methods
  • Laplacian Method
    • Text Detection
    • Boundary Refinement
    • False Positive Elimination
  • Experimental Results
  • Conclusion and Future Work
false positive elimination
False Positive Elimination
  • Text block: (1) aspect_ratio ≥ T1 and (2) edge_area / area ≥ T2
    • edge_area = number of edge pixels
  • Otherwise, false positive
  • T1 = 0.5 and T2 = 0.1
false positive elimination2
False Positive Elimination
  • 1st false positive removed due to the aspect ratio rule
false positive elimination3
False Positive Elimination
  • Sobel edge map
  • 2nd false positive removed due to the edge density rule
agenda7
Agenda
  • Introduction
  • Previous Methods
  • Laplacian Method
  • Experimental Results
  • Conclusion and Future Work
experimental results
Experimental Results
  • 101 images: news, sports, movies, etc.
  • Sizes from 320 × 240 to 816 × 448
  • English, Chinese and Korean text
  • Three implemented methods: edge-based method [1], gradient-based method [2] and uniform-colored method [3]
agenda8
Agenda
  • Introduction
  • Previous Methods
  • Laplacian Method
  • Experimental Results
    • Sample Results
    • Performance Measures
    • Evaluation
  • Conclusion and Future Work
sample results
Sample Results
  • Low contrast text

Input Edge-based Gradient-based

Uniform-colored Proposed

sample results1
Sample Results
  • Scene text

Input (from [4]) Edge-based Gradient-based

Uniform-colored Proposed

sample results2
Sample Results
  • The proposed method fails if the contrastis too low

Input Proposed

Edge-based Gradient-based Uniform-colored

sample results3
Different font sizes

Different languages

Sample Results

(from [4])

sample results4
Sample Results
  • Different window sizes
  • N = 5 in our experiment

Input

N = 5 N = 21

agenda9
Agenda
  • Introduction
  • Previous Methods
  • Laplacian Method
  • Experimental Results
    • Sample Results
    • Performance Measures
    • Evaluation
  • Conclusion and Future Work
performance measures
Performance Measures
  • Detection Rate (DR)
    • number of localized text / number of text
  • False Positive Rate (FPR)
    • number of non-text /number of localized blocks
  • Misdetection Rate (MDR)
    • number of text with missing characters / number of localized text

DR = 100%

FPR = 25%

MDR = 67%

agenda10
Agenda
  • Introduction
  • Previous Methods
  • Laplacian Method
  • Experimental Results
    • Sample Results
    • Performance Measures
    • Evaluation
  • Conclusion and Future Work
evaluation1
Evaluation
  • The proposed method outperforms the edge-based and gradient-based methods in all performance measures
evaluation2
Evaluation
  • Compared to the gradient-based method, the proposed method has a slightly worse MDR but a significantly higher DR
agenda11
Agenda
  • Introduction
  • Previous Methods
  • Laplacian Method
  • Experimental Results
  • Conclusion and Future Work
conclusion and future work
Conclusion and Future Work
  • The proposed method performs well on the dataset
    • Gradient information  candidate text regions
    • Edge information  localized text blocks
  • May fail if the contrast is too low
  • Can be extended for non-horizontal text
references
References
  • C. Liu, C. Wang and R. Dai, “Text Detection in Images Based on Unsupervised Classification of Edge-based Features”, ICDAR 2005, pp. 610-614.
  • E. K. Wong and M. Chen, “A new robust algorithm for video text extraction”, Pattern Recognition 36, 2003, pp. 1397-1406.
  • V. Y. Mariano and R. Kasturi, “Locating Uniform-Colored Text in Video Frames”, 15th ICPR, Volume 4, 2000, pp 539-542.
  • X. S. Hua, W. Liu and H. J. Zhang, “Automatic Performance Evaluation for Video Text Detection”, ICDAR, 2001, pp 545-550.