The purpose of this research is to create a system that takes handwritten as well as printed English characters and numerals as input, process the character, train the k space nearest neighbor algorithm, recognize the pattern and modify the character to a beautified version of the input. This research is aimed at developing software, which will be helpful in recognizing characters of English language. This research is restricted to English characters and numerals only. It is also helpful in recognizing special characters. It can be further developed to recognize the characters of different languages. One of the primary means by which computers are endowed with humanlike abilities is through the use of Machine Learning. Machine Learning allows the system to be more efficient and accurate with successive iteration. Pattern recognition is perhaps the most common problem that can be solved using machine learning approach. The K space nearest neighbor algorithm is one of the most efficient machine learning algorithm that can be used for pattern recognition problem and works well with limited data for learning. The process followed consist of following steps: Image Input, Preprocessing, Segmentation, Feature Extraction and Classification. A kNN trained for classification is designed to take input samples and classify them into groups or clusters. These groups may be fuzzy, without clearly defined boundaries. This project concerns detecting printed and handwritten characters and wishes to improve upon previous character recognition systems. The developed system performed as per the expectations successfully identifying multiple characters in a single row and worked well with handwritten characters as test data even when no handwritten character data was provided in training set.