The proposed method is efficient where it is new, simple, fast, accurate so it is used in this research for recognizing Hindi numerals (0,1,2,3,4,5,6,7,8,9), that are usually used by Arabic population. The method is effective with handwritten numerals. This method is simply depends on determining number of terminal points and its positions for each digit in its different shapes, that represent the main feature for recognition. Only five features are added when there are similarity between digits (have the same number of terminals and position), the additional features was: less pixels number to recognize digit zero, intersection point position to recognize digit (2,3,6,7) that have three terminal points, image width to recognize digit one, curve number to recognize digit (2,4) that have two terminal points finally closed shape feature is added to recognize special cases of digit five and nine that have irregular shapes. Hence the proposed method is based on structural primitives such as curve, line, point type and etc. in a manner similar to that in which human beings describe characters geometrically. This work deals with noisy object by removed them from the original image to ensure that the noise pixels not merge with the original digit pixels. Encouraged recognition results are obtained for handwritten numerals samples written by different persons, different ages, different pens type, also different size, digits with rotation state are tested that gave an excellent recognition results. Some of problems with digit 9,5 are solved.