Abstract:
Although text recognition gives rise to many applications, this research aims to identify, locate, and recognize characters in name boards using various font styles and partial letters. English language displayed in name boards is used to predict partial and whole characters in this work. First, the image is preprocessed with grayscale transformation and thresholding, followed by morphological transformations and connected component analysis to localize the text sections. The text is then segmented using the Skeleton analysis method in the next phase. Further, the segmented character image is turned into strings using the Coefficient of Correlation and Structural Similarity Index methods. As a result, characters with disfigurements can be identified using the most similar character image with an accuracy of 81.7%.
