Non text eradication from degraded and non degraded videos and images

Abstract

Text Segmentation of text from degraded document images is a very complex task due to high mutation between the document background and foreground region. Automatic text extraction is one of the basic feature required for content-based video indexing, automated indexing, automated annotation, structuring and retrieval tasks. Text detection from videos demands conversion of entire video into smaller framesets. Further the framesets are binarized to ease the extraction procedure. This in turn is followed by application of detection procedure on the static frames generated from the video. Text detection can lead to extraction of both superficial and embedded text. Embedded text will be the focus of this research paper because a part of the information depicted in the superficial text is already present in the embedded region. The cycle would start from conversion of dynamic video into static frames, followed by application of filters for noise removal, use of basic morphological operation like dilation and erosion, creation of bounding boxes around the textual content and finally removal of the non text region in such a manner that only the textual region in enhanced. The enhanced textual region is retained while the non textual content is eliminated.