Text and Texture Extraction for Various Images using Combinational Methods

Text data contains useful information for automatic explanation, indexing, and structuring of images. The typical low-level features that are extracted in images and video include measures of color, texture, or shape. Extraction of this information involves detection, localization, tracking, extraction, enhancement, and recognition of the text from a given image. The objective of this paper is to compare three basic approaches of text and texture extraction in natural images namely; edge-based , connected-component based and text based method . The edge based and connected component based method shows how to extract text from an image whereas the text extraction method shows how to extract texture information from an image here creating a GLCM, and then extracting statistical measures from this matrix. Further, the image entropy and energies are also computed in order to correlate the skin symptoms to the skin texture images.