In this paper, we propose an effective approach for a PDA-based sign system, and it presents user the sign translator. Its main functions include 3 parts: detection, recognition and translation. Automatic detection and recognition of text in natural scenes is a prerequisite for automatic sign translator. In order to make the system robust for text detection in various natural scenes, the detection approach efficiently embeds multi-resolution, adaptive search in a hierarchical framework with different emphases at each layer. We also introduce an intensity-based OCR method to recognize character in various fonts and lighting condition, where we employ Gabor transform to obtain local features, and LDA for selection and classification of features. The recognition rate is 92.4% for the testing set got from the natural sign. Sign is different from the normal used sentence. It is brief, with a lot of abbreviations and place nouns. We here only briefly introduce a rule-based place name translation. We have integrated all these functions in a PDA, which can capture sign image, auto segment and recognize the Chinese sign, and translate it into English.

In this paper, we propose an approach for detecting signs from natural scenes. The approach efficiently embeds multiresolution, adaptive search, and affine rectification algorithms in a hierarchical framework, with different emphases at each layer. We combine multi-resolution and multi-scale edge detection techniques to effectively detect text in different sizes. Different from the existing approaches, by using the cues from text inside the image, we introduce affine rectification transformation to recover deformation of the text region caused by an inappropriate camera view angle. This procedure can significantly improve text detection rate and OCR (Optical Character Recognition) accuracy. Experimental results have demonstrated feasibility of the proposed algorithms. We have applied the proposed approach to a Chinese sign translation system, which can

Abstract not found

... text in video frames. This text may appear as a part of the scene (scene text) or may be rendered artificially during production (superimposed text). By detecting and recognizing videotext, it is possible to index and easily manage large video archives. There are some basic properties, which makes videotext detectable. These properties are, distinguishing texture, high contrast, and uniform color. By employing these properties it is possible to detect text regions and binarize image for character recognition after thresholding these regions. In this thesis, a complete framework for detection and recognition of videotext is presented. The performance of the system is tested for its recognition rate for various combinations. The system is capable of character recognition rate up to 59%, which is quite reasonable for most purposes.

images and video frames constitutes a valuable source of high-level semantics for multimedia indexing and retrieval systems. Text detection is the most crucial step in a multimedia text extraction system and although it has been extensively studied the past decade still, it does not exist a generic architecture that would work for artificial and scene text in multimedia content. In this paper we propose a system for text detection of both artificial and scene text in images and video frames. The system is based on a machine learning stage which uses an Random Forest classifier and a highly discriminative feature set produced by using a new texture operator called Multilevel Adaptive Color edge Local Binary Pattern (MACeLBP). MACeLBP describes the spatial distribution of color edges in multiple adaptive levels of contrast. Then, a gradientbased algorithm is applied to achieve distinction among text lines as well as refinement in the localization of the text lines. The whole algorithm is situated in a multiresolution framework to achieve invariance to scale for the detection of text lines. Finally, an optional connected-component step segments text lines into words based on the distances between the resulting components. The experimental results are