Handwriting Detection refers to the process by which a computer is able to recognise and make sense of handwritten input from various media, including paper documents, touch screens, photographs, and so on. To recognise handwritten text is an example of pattern recognition. The goal of pattern recognition is to assign information or an object to one of several predetermined classes. or groups. Handwriting recognition systems have historically made use of handcrafted features and extensive training data. It is difficult to train an Optical Character Recognition (OCR) system with these requirements in mind. In the last few years, deep learning-based research in the field of handwriting recognition has led to groundbreaking performance. Still, the availability of massive processing power and the exponential increase in the volume of handwritten data calls for advancements in recognition accuracy and warrants additional study. Convolutional neural networks (CNNs) are the best method for solving handwriting recognition problems because they are able to accurately perceive the structure of handwritten characters/words, which in turn aids in the automatic extraction of distinct features. The purpose of this system is to identify documents in a variety of formats. The evolution of handwriting has led to the appearance of many different types of handwritten characters, such as digits, numerals, cursive script, symbols, and scripts in languages other than English.