TRIER AND TAXT: EVALUATION OF BINARIZATION METHODS 31 Evaluation of Binarization Methods for Document Images
نویسندگان
چکیده
This paper presents an evaluation of eleven locally adaptive binarization methods for gray scale images with low contrast, variable background intensity and noise. Niblack’s method with the addition of the postprocessing step of Yanowitz and Bruckstein’s method added performed the best, and was also one of the fastest binarization methods. Keywords— Locally adaptive binarization, Thresholding, Evaluation, Utility maps, Document images.
منابع مشابه
A Data Capture System for Hydrographic Maps
The main part of the thesis is five separate research papers published in or submitted to leading journals in the field of computer vision and pattern recognition. In addition, a data capture system for hydrographic maps has been designed and implemented. It places the results of the thesis papers in context and demonstrate their importance. The five thesis papers are [1] Øivind Due Trier and T...
متن کاملRecognition of Digits in Hydrographic Maps: Binary Versus Topographic Analysis
This paper compares the performance of topographic analysis and binary analysis for recognition of digits in hydrographic maps. The performance of each method was measured by the correct classification rate of the final symbol recognition step when processing a complete hydrographic map of size 0.45× 0.6m with about 35,000 digits. The experimental results indicated that binary analysis had a be...
متن کاملRecognition of Digits in Hydrographic Maps: Binary vs. Topographic Analysis
This paper compares the performance of topographic analysis and binary analysis for recognition of digits in hydrographic maps. Each of the methods processed the input image by extracting binary print components, recognizing long lines, splitting touching digits, and, finally, recognizing individual symbol candidates. The topographic analysis extracted the information by computing topographic l...
متن کاملFeature extraction methods for character recognition-A survey
-This paper presents an overview of feature extraction methods for off-line recognition of segmented (isolated) characters. Selection of a feature extraction method is probably the single most important factor in achieving high recognition performance in character recognition systems. Different feature extraction methods are designed for different representations 6f the characters, such as soli...
متن کاملA Structural Analysis Based Feature Extraction Method for OCR System For Myanmar Printed Document Images
This paper proposes a new feature extraction method for off-line recognition of Myanmar printed documents. One of the most important factors to achieve high recognition performance in Optical Character Recognition (OCR) system is the selection of the feature extraction methods. Different types of existing OCR systems used various feature extraction methods because of the diversity of the script...
متن کامل