This paper presents the zone based feature extraction and statistical classification technique for Kannada handwritten numeral recognition. The Kannada handwritten numeral database required for the experimentation is collected from the different individuals and are preprocessed for feature extraction. The binary images fitted in a particular window size are partitioned into a number of regions and a real value is computed by the density of one’s to represent the image. The statistical classifier build for the experimentation and on Kannada handwritten numeral database found better classification and recognition rate.