A text independent handwriting forgery detection system based on branchlet features and Gaussian mixture models
Chin‐Shyurng Fahn, Chuping Lee, Heng-I Chen · 2016
In this paper, a handwriting forgery detection system based on branchlet features and Gaussian mixture models(GMMs) is presented. At the beginning, the input handwriting images are processed by binarization and morphological operations to enhance sign traces. Subsequently, a thinning algorithm is employed to obtain the skeleton of character strokes, and find branchlet points in the skeleton image to extract handwriting features. Next, the feature data of input handwriting images are combined into some groups exhaustively to create their own GMMs. Then the similarity between each group and input handwriting images is measured. Through a voting system, the input handwriting images that possess higher similarity values are deemed as real signs. In a sequel, a new GMM is created by the real sign images to measure the similarity of all input handwriting images. Finally, we calculate the sample mean and standard deviation of the above measured similarity values. By incorporating these statistical terms, the input handwriting images whose similarity values are below an assigned threshold will be predicted as forgery. In the experiments, we adopt the IAM Handwriting Database that includes 657 writers' handwriting images whose resolution is fixed at 300dpi, and stored as 256 gray scale PNG images. The experimental results reveal that in case of 20% forgery our proposed system can reach up to 95% accuracy. When performing cross-validation under the input handwriting images consisting of 20% to 60% forgery, the system can reach at the average accuracy of 80.52%. This unsupervised learning scheme is effectively to detect the forged handwriting in scanned documents.