20
Image reconstruction its individual pieces By : Prashant Agrawal Hitesh Meghani

Image reconstruction from its individual pieces

Embed Size (px)

Citation preview

Page 1: Image reconstruction from its individual pieces

Image reconstruction its individual pieces

By : Prashant Agrawal Hitesh Meghani

Page 2: Image reconstruction from its individual pieces

Input Specifications:The images pieces may be

With Straight Edges(Rectangular)

Non-uniformly Cut

Rotated by Multiples of 90 degrees

Page 3: Image reconstruction from its individual pieces

Basic Steps :1)Extraction of the individual images2)Selection of the base image

3)Formation of the boundary array

Page 4: Image reconstruction from its individual pieces

Basic Steps :

4)Search for a matching piece

5)Addition of matched piece

6)Repeat Iteratively

Page 5: Image reconstruction from its individual pieces

Step 1: Image Extraction

CROP the image to fit into a rectangular bounding box. Blacken the remaining part.

Page 6: Image reconstruction from its individual pieces

Step 2: Selection of Base

Select the base image – to add other images on it.

Page 7: Image reconstruction from its individual pieces

Step 3:Formation of the boundary arrayBoundary Array consists of

Distance of the boundary pixel from the side of the bounding box.

The red, green and blue color coordinates

Page 8: Image reconstruction from its individual pieces

Step 3:Formation of the boundary array

Page 9: Image reconstruction from its individual pieces

Step 3:Formation of the boundary array

Page 10: Image reconstruction from its individual pieces

Step 4 :Search for Matching piece

Extraction of Boundaries of two pieces

Page 11: Image reconstruction from its individual pieces

Sum is not constant

Sum =356+-1Now Check for RGB values

MATCHING POINTS

Step 4 :Search for Matching piece

Page 12: Image reconstruction from its individual pieces

Step 4:Search for Matching piece Right boundary of base image is

comparedwith: 1)Left boundary of first piece

2)Next boundary of the same piece.3)Next piece is taken.

Next boundary of the base piece is repeated until match is found.

Page 13: Image reconstruction from its individual pieces

Step 5: Addition of Matched Piece

Piece is rotated if required.The size of the base image is

increased to accommodate both the images.

The image is added on the basis of match points.

Page 14: Image reconstruction from its individual pieces

Step 5: Addition of Matched Piece

Page 15: Image reconstruction from its individual pieces

Step 6: Iterative RepetitionThe added

image is made the base image

Identify the image to

add to base

Add the image to

base

Page 16: Image reconstruction from its individual pieces

Demo :On C ( Open CV)On MATLAB

Page 17: Image reconstruction from its individual pieces

Implementation And ComparisonsOn MATLAB- User friendly

programming but takes larger time.On C- Very quick execution

Page 18: Image reconstruction from its individual pieces

ShortcomingsImages with uniform backgroundImage piece cut entirely from

another.

Page 19: Image reconstruction from its individual pieces

ApplicationsForensic sciencesPattern matching

Page 20: Image reconstruction from its individual pieces

Thank You

Questions ????