**Important Note:** This article is part of the series in which TechReport.us discuss theory of Video Stream Matching.

Basically Algo is one but here using its two possible approaches.

- Edge Map
- Edge Angles

**4.4.2.1 Algorithm 3**

Input:

BMP Image

Output:

Array Of Numerical values define the Edge Map.

Working:

It takes an Image and converts it into gray scale if it is not already in gray scale. Then apply Canny Algorithm 6 Steps define in chapter 2 and return the image edges.

Step 0 : Start

Step 1 : Takes input an Image (im).

Step 2 : If (im) in gray scale

If not

then

convert (im) into gray scale.

Step 3 : (im1) = Apply Gaussian to remove noise (im)

Step 4 : (im2) = Apply Sobel operator in Horizontal direction (im1)

Step 5 : (im3) = Apply Sobel operator in Vertical direction (im1)

Step 6 : AddIm = Im2 + Im3

Step 7 : Loop1: for I =rows of (AddIm) //calculate 4 angles according to define

Step 8 : Loop2: for J = columns of (AddIm)

Step 9 : Calculate angle for each AddIm(I,J)

Store in AngelMat(I,J)

Step 10 : end Loop1

Step 11 : end Loop2

Step 12 : t1 = Threshold(AddIm)

Step 13 : t1= t1 + t1* 0.5 // for non maxima suppression

Step 14 : Loop1 : for i=rows of AddIm

Step 15 : Loop2 : for j=columns of AddIm

If AddIm( i,j) >t1 and AngleMat(i,j) is according to rules

Set AddIm( i,j) =1

else

Set AddIm( i,j) =0

Step 16: end Loop2

Step 17: end Loop1

Step 18 : t1 = Threshold(AddIm)

Step 19 : t2 = t1 + t1* 0.5 // for Double Threshold

Step 20 : Loop1 : for i=rows of AddIm

Step 21 : Loop2 : for j=columns of AddIm

If AddIm( i,j) >t1

Set AddIm( i,j) =1

else

Set AddIm( i,j) =0

Step 22 : Cheak 8-N of ( i,j)

If AddIm( i,j) Neighbours > t2

then

Set to 1

Else

Set to 0

Step 23: end Loop2

Step 24: end Loop1

Step 25 : Return (AddIm)

Step 26 : Stop

**4.4.2.2 Algorithm 4**

Input:

BMP Image

Output:

Array Of Numerical values define the Edge Angles.

Working:

It takes an Image and converts it into gray scale if it is not already in gray scale. Then apply Canny Algorithm 6 Steps define in chapter 2 and return the image angles.

Step 0 : Start

Step 1 : Takes input an Image (im).

Step 2 : If (im) in gray scale

If not

then

convert (im) into gray scale.

Step 3 : (im1) = Apply Gaussian to remove noise (im)

Step 4 : (im2) = Apply Sobel operator in Horizontal direction (im1)

Step 5 : (im3) = Apply Sobel operator in Vertical direction (im1)

Step 6 : AddIm = Im2 + Im3

Step 7 : Loop1: for I =rows of (AddIm) //calculate 4 angles according to define

Step 8 : Loop2: for J = columns of (AddIm)

Step 9 : Calculate angle for each AddIm(I,J)

Store in AngelMat(I,J)

Step 10 : end Loop1

Step 11 : end Loop2

Step 12 : Row =1 , Col =1

Step 13 : Loop1 : for i=rows of AddIm // make tiles of image

Step 14 : Col = Col + 1 , Row = 1 ;

Step 15 : Loop2 : for j=columns of AddIm

Calculate number of times each angle occuers in each tile

And store it in ResAng(Row,Col)

Row = Row + 1

Step 16: end Loop2

Step 17: end Loop1

Step 18 : Return (ResAng)

Step 19 : Stop