In Optical Character Recognition [OCR], machine printed or handwritten characters/numerals are recognized. There are plentiful approaches that deal with problem of detection of numerals/character depending on the sort of feature extracted and different way of extracting them. This paper presents a novel method for handwritten Marathi (Devnagari) numerals; most popular in Indian subcontinent. The proposed work focuses on feature extraction i.e. the global features; namely, Fourier descriptors and chain code of the binary images representing isolated Marathi numerals are extracted as features. These feature vectors are fed to SVM classifier that has been trained to recognize Marathi numerals. The system has been tested on varieties of image of isolated handwritten Marathi numerals. Experimentation result shows the recognition rate of 98.1%.