Detection and Localization of Texts from Natural Scene Images: A Hybrid Approach

Text detection in images or videos is an important step to achieve multimedia content retrieval. In this paper, an efficient algorithm which can automatically detect, localize and extract horizontally aligned text in images (and digital videos) with complex backgrounds is presented. The proposed approach is based on the application of a color reduction technique, a method for edge detection, and the localization of text regions using projection profile analyses and geometrical properties. The outputs of the algorithm are text boxes with a simplified background, ready to be fed into an OCR engine for subsequent character recognition. Our proposal is robust with respect to different font sizes, font colors, languages and background complexities Text recognition and analysis includes many applications such as: license plate recognition, sign detection as well translation, helping tourists and blind persons to understanding environment, drawing attention of a driver, content-based
image search and so on. Locating text in case of variation in style, color, as well as complex image background makes text reading from images more challenging. In this paper the various techniques available for detecting and recognizing text are explained, finally a hybrid approach using segmentation explained which can improve the qualitative texture analysis among other techniques.