The presence of mixed type texts in a document image is an important obstacle towards the automation of the optical character recognition procedure. Machine printed character recognition and handwritten character recognition techniques

In many documents such as admission form, bank cheques, memorandums, letters and application forms machine printed and handwritten characters are mixed. Since the algorithms for recognition of machine-printed texts and handwritten texts are different, it is necessary to distinguish between these two types of texts before giving it to respective OCR systems to process it. This separation will definitely increase the performance and overall system quality. The paper discusses some observations about characteristics of these two types of texts and various techniques of separation of machine printed and handwritten text into three categories (Structural and statistical features, Gradient features and Geometric features) based on feature extraction method. Keywords-Feature Extraction, Handwritten Text, Machine Printed Text, OCR.