Proc. SPIE. 5296, Document Recognition and Retrieval XI
KEYWORDS: Lithium, Statistical analysis, Visual process modeling, Image segmentation, Image processing, Associative arrays, Optical character recognition, Document image analysis, 3D image processing, RGB color model
This paper presents a decision tree based adaptive binarization method for text retrieval in color document images. This method extends Ni-Black windowed thresholding technique and hue (H), saturation (S) and value (V) are employed. First, an observation window is retrieved, and based on standard deviation of H, S and V, a pre-defined decision tree is used for selecting proper variables that should be employed. Secondly, Karhunen-Loeve Transform (KLT) is used for eliminating correlation and reducing dimension. Finally, center point of the window is classified based on 2-D standard normal distribution. The result shows that our binarization method generates better result than Ni-Black and other global thresholding binarization method such as Otsu’s in color document images. A comparison using a commercial OCR system shows that our method can be used in various situations for high quality text retrieval.