Calligraphy Style Correlation Discovery Based on Graph Model and Its Applications
نویسنده
چکیده
As more and more works of calligraphy exists in digital library, traditional browsing and searching are not satisfying. This paper presents an algorithm for calligraphy style correlation discovery based on graph model. We first segment calligraphy work into characters, extract their texture features through 64 Gabor channels, and estimate the calligraphy style using a probability multi-class SVM classifier. Then we compute the style similarity between each pair of characters and select the top k neighbors to generate a data graph. Finally we use random walk on the graph to discover the correlation among works and authors. Three experimental analyses show our proposed approach works well. Index Terms — Calligraphy Style, Correlation Discovery, Graph Model, Random Walk, Visualization.
منابع مشابه
Computational method for calligraphic style representation and classification
A large collection of reproductions of calligraphy on paper was scanned into images to enable web access for both the academic community and the public. Calligraphic paper digitization technology is mature, but technology for segmentation, character coding, style classification, and identification of calligraphy are lacking. Therefore, computational tools for classification and quantification o...
متن کاملStyle Consistent Calligraphy Tablet Design
A style-consistent calligraphy tablet designing approach is proposed in this paper. The layout of the tablet is calculated firstly. The calligraphy characters are retrieved from the ones written by the specific calligrapher, while the style-consistency calligraphy character synthesis approach is applied to synthesize the non-existent ones. Finally, these characters are adjusted so that their st...
متن کاملReal-Time intrusion detection alert correlation and attack scenario extraction based on the prerequisite consequence approach
Alert correlation systems attempt to discover the relations among alerts produced by one or more intrusion detection systems to determine the attack scenarios and their main motivations. In this paper a new IDS alert correlation method is proposed that can be used to detect attack scenarios in real-time. The proposed method is based on a causal approach due to the strength of causal methods in ...
متن کاملTraining a calligraphy style classifier on a non-representative training set
Calligraphy collections are being scanned into document images for preservation and accessibility. The digitization technology is mature and calligraphy character recognition is well underway, but automatic calligraphy style classification is lagging. Special style features are developed to measure style similarity of calligraphy character images of different stroke configurations and GB (or Un...
متن کاملCreate Your Own Chinese Calligraphy Artwork
In this work, we aim to transform handwritten Chinese characters into calligraphy style characters on a stroke-by-stroke basis. We extracted strokes from a set of handwritten characters by identifying the primary orientation of each stroke. We then adopted autoencoder and self-organizing maps to cluster the extracted strokes into 100 different groups. Using the neural networks obtained, we clus...
متن کامل