TECPRO

As graphical information spreads and plays an important role in various areas, techniques for extracting the text information from mixed textual and graphical images are being explored by computer vision researchers recent text segmentation scheme have approached this problem in several ways such as: bottom up using connected component grouping from characters, words, text lines, to paragraphs or run-length smoothing algorithms or top down, by first splitting large blocks then subdividing each block and identify the specific regions. At TEC PRO, you have an opportunity get complete assistance during preparation of graphical information thesis and graphical text projects at very nominal costs.

The basic idea in our approach is motivated from knowledge of various characteristics of printed lettering or fonts. It is designed to eliminate background image information and to highlight or identify the regions of the image that contain text. The algorithm uses the fact that text regions in an image may be identified by searching for several repeated instances of uniform gray intensity of approximately the same width. Combining this with the fact that the ratio of typeface, stroke width to height is often fixed provides a useful technique for extracting text from images. Partial results of this technique are presented.

S.Athirayan