Feature Extraction Method Algorithms1. Intersection pointsPrinciple:• The number and position of intersections between the character and the straight lines have been retained as elements.• 1st horizontal (1/3)th of height.;• 2nd horizontal (2/3)th of height .; • The vertical straight line passes through the center of gravity of the character Algorithm: INPUT: Image of the character OUTPUT: Number and position of intersections between the character and the straight lines begin Step 1: Transform the input image into a thinned image Step 2 : Draw two straight horizontal lines at the first third and the second third of the character's heightStep 3: The vertical straight line passes through the center of gravity of the characterStep 4: Find the position X of the point of intersection of the horizontal line at 1/ 3 of the character height with the character. Step 5: Find the X position of the point of intersection of the horizontal line at 2/3 of the height of the character with the character. Step 6: Find the Y position of the point of intersection of the vertical line at the character's centroid with the character.Step 7: Store the above features in a file. end • Number of horizontal intersection points 2• Number of vertical intersection points 1• Total number. intersection points 32. Characteristics of the zone centroidPrinciple:• The major advantage of this approach comes from its robustness to small variations, its ease of implementation and its good recognition rate.• The extraction method Area-based feature extraction provides good results even when some pre-processing steps like filtering, smoothing and skew removal are not taken into account. Algorithm 1: Extraction of distance metric features based on image centroid and area (ICZ)...... middle of paper ......Horizontal profile =(left side view)/(right side view)3) Bottom view: sum white pixels when scanning an input image vertically from bottom (y2) to top (y3) until it touches a black pixel. 3) Top view: the sum of white pixels when scanning an input image vertically from top (y0) to bottom (y1) until it touches a black pixel. Vertical profile = (top view)/(bottom view) Image size d input (128 X 128) left = 0 right = 582HP= 0Image size (256 left profile value equal to 0The horizontal profile values ​​are invariant to scale8. Zone density (ZD) characteristics: The density of each zone is obtained by dividing the number of foreground pixels in each zone by the total number of pixels in each zone. 16 zones of 32*32 standardized Devnagari digits „3‟.