Before smartphones, English learners used to organize words in their notebooks. As smartphones became more popular over time, more people started to study by storing words in word book apps than notebooks. Users will be able to study words anytime, anywhere via their smartphones. These word-field apps are a way for users to enter data themselves. However, this paper designed and implemented an app that automatically enters words using vision system and letter recognition. The app recognizes areas painted with highlighter first, then recognizes words within the highlighter area and organizes them into tables. It also helps to understand how certain words are used in contexts in certain English bodies with simple actions. Because the data of words can have multiple words in a particular body, the database schema was designed in a one-to-many relationship between the images taken with the camera and the words contained in that body. The differentiated advantages of this app are as follows: First, it increases the time efficiency of studying. Second, it improves learners' vocabulary by learning based on context. These advantages are described in detail in this paper through practical research materials and techniques. The app's platform used Apple Inc.'s iOS. Character recognition, a key technology in the app, utilizes OpenCV's library and Apple Inc.'s CoreML.