摘要：Problem statement: A generalized skeleton transform allows a shape to be represented as a collection of modestly overlapped octagonal shape parts. One problem with several generalized Morphological skeleton transforms is that they generate noise after decomposition. The noise rate may not be effective for ordinary images; however this effect will be more when applied on printed or handwritten characters. Approach: The present study tackled this issue by applying a noise removal algorithm after morphological decomposition. Results: The algorithm was applied on various types of decomposition images. The Present method was compared with generalized skeleton algorithm and octagon-generating decomposition algorithm. Conclusion: The error rates with original image were evaluated using various error functions. The experimental results indicated that the present decomposition algorithm produces images with good clarity when compared with other algorithms.
关键词：Shape; noise; printed hand written characters; error-rate; error functions
