Projection Profile method

In Image Processing, projection profile refers to projection of sum of hits/positives along an axis from bi-dimensional image. Projection profile method is majorly used for segmentation of text objects present inside text documents.

Solution:

Note: Projection profile is calculated for a thresholded image or binarized image where a thresholded image is a grayscale image with pixel values as 0 or 255. Image pixels are replaced by 1 and 0 for pixel values 0 and 255 respectively.

Projection profile is calculated separately for different axis. Projection profile along vertical axis is called Vertical Projection profile. Vertical projection profile is calculated for every column as sum of all row pixel values inside the column. Horizontal Projection profile is the projection profile of a image along horizontal axis. Horizontal Projection profile is calculated for every row as sum of all column pixel values inside the row.

Code Implementation for Horizontal Projection Profile:

C++

 #include using namespace std;    // Function to generate horizontal projection profile vector getHorizontalProjectionProfile(     vector > image, int rows, int cols) {        for (int i = 0; i < rows; i++)     {         for (int j = 0; j < cols; j++)         {             // Convert black spots to ones             if (image[i][j] == 0)             {                 image[i][j] = 1;             }             // Convert white spots to zeros             else if (image[i][j] == 255)             {                 image[i][j] = 0;             }         }     }        vector horizontal_projection(rows, 0);        // Calculate sum of 1's for every row     for (int i = 0; i < rows; i++)     {         // Sum all 1's         for (int j = 0; j < cols; j++)         {             horizontal_projection[i] += image[i][j];         }     }        return horizontal_projection; } // Driver Function int main() {     int rows = 5, cols = 3;     vector > image = { { 0, 0, 0 },         { 0, 255, 255 },         { 0, 0, 0 },         { 0, 255, 255 },         { 0, 0, 0 }     };        vector horizontal_projection = getHorizontalProjectionProfile(                                             image, rows, cols);    for (auto it : horizontal_projection)     {         cout << it << " ";     }     return 0; }

Python3

 import numpy as np    # Function to generate horizontal projection profile def getHorizontalProjectionProfile(image):        # Convert black spots to ones     image[image == 0]   = 1     # Convert white spots to zeros     image[image == 255] = 0        horizontal_projection = np.sum(image, axis = 1)         return horizontal_projection       # Driver Function if __name__ == '__main__':        rows = 5     cols = 3     image = np.array([[0, 0, 0],             [0, 255, 255],             [0, 0, 0],             [0, 255, 255],             [0, 0, 0]])            horizontal_projection = getHorizontalProjectionProfile(image.copy())        print(*horizontal_projection)

Output:

3 1 3 1 3

Code Implementation for Vertical Projection Profile:

C++

 #include using namespace std;    // Function to generate vertical projection profile vector getVerticalProjectionProfile(     vector > image, int rows, int cols) {        for (int i = 0; i < rows; i++)     {         for (int j = 0; j < cols; j++)         {             // Convert black spots to ones             if (image[i][j] == 0)             {                 image[i][j] = 1;             }             // Convert white spots to zeros             else if (image[i][j] == 255)             {                 image[i][j] = 0;             }         }     }        vector vertical_projection(cols, 0);        // Calculate sum of 1's for every column     for (int j = 0; j < cols; j++)     {         // Sum all 1's         for (int i = 0; i < rows; i++)         {             vertical_projection[j] += image[i][j];         }     }        return vertical_projection; }    // Driver Function int main() {     int rows = 5, cols = 3;     vector > image = { { 0, 0, 0 },         { 0, 255, 255 },         { 0, 0, 0 },         { 0, 255, 255 },         { 0, 0, 0 }     };        vector vertical_projection = getVerticalProjectionProfile(                                           image, rows, cols);    for (auto it : vertical_projection)     {         cout << it << " ";     }     return 0; }

Python3

 import numpy as np    # Function to generate vertical projection profile def getVerticalProjectionProfile(image):        # Convert black spots to ones      image[image == 0]   = 1     # Convert white spots to zeros      image[image == 255] = 0        vertical_projection = np.sum(image, axis = 0)        return vertical_projection    # Driver Function if __name__ == '__main__':        rows = 5     cols = 3     image = np.array([[0, 0, 0],             [0, 255, 255],             [0, 0, 0],             [0, 255, 255],             [0, 0, 0]])        vertical_projection = getVerticalProjectionProfile(image.copy())        print(*vertical_projection)

Output:

5 3 3

Time Complexity: O(rows*columns)
Space Complexity: O(rows*columns)

My Personal Notes arrow_drop_up Check out this Author's contributed articles.

If you like GeeksforGeeks and would like to contribute, you can also write an article using contribute.geeksforgeeks.org or mail your article to contribute@geeksforgeeks.org. See your article appearing on the GeeksforGeeks main page and help other Geeks.

Please Improve this article if you find anything incorrect by clicking on the "Improve Article" button below.

Article Tags :

Be the First to upvote.

Please write to us at contribute@geeksforgeeks.org to report any issue with the above content.