Jiangqin Wu

Retrieval of chinese calligraphic character image

Numerous collection of Chinese calligraphy is a valuable civilization legacy. However, it is very difficult to employ any existing techniques to retrieve them, because similarity measure is not a trivial problem for Chinese calligraphic characters. In this paper, a novel method is presented to retrieve Chinese calligraphic character images using approximate correspondence point algorithm. In this method, shapes of calligraphic characters are represented by their contour points. We first compute point contexts and find approximate point correspondence in the other character, and then retrieve calligraphic characters according to their accumulated matching cost. Finally, the efficiency of our algorithm is demonstrated by a preliminary experiment.

Latent Style Model: Discovering writing styles for calligraphy works

Chinese calligraphy works is a valuable part of the Chinese culture heritage. More and more calligraphy works images are digitized, preserved and exhibited in digital library. Users always want to appreciate the style-similar works simultaneously. To satisfy their need, calligraphic style representation and browsing calligraphy works by its style are the most important problems to be addressed. This paper proposes calligraphic style representation which is a multinomial probability distribution over visual words, and Latent Style Model to discover the style of calligraphy works and organize the works by style. In our experiments, we evaluated various factors that influence the model, and proved the effectiveness of the style representation and the model. At last, we illustrate the Calligraphic Style Browser to organize and exhibit the resource according to the styles.

Discovering calligraphy style relationships by Supervised Learning Weighted Random Walk Model

Chinese calligraphy is an important part of Chinese traditional culture. More and more calligraphy works are digitized, preserved and exhibited in digital libraries. Users may want to appreciate the style-similar works simultaneously. However, currently available services such as metadata-based browsing and searching can not satisfy such kind of requirement. To allow users to appreciate the style-similar works conveniently, we propose a Supervised Learning Weighted Random Walk Model to discover calligraphy style relationships. In the model, we consider the heterogeneity of both edges and nodes, and then use some preference pairs to learn the weights of different types of edges in the graph. After the weight learning, the style relationships can be discovered by random walk on the heterogeneous graphs. In order to solve the out-of-graph node problem, we pre-compute the personalized vector for each character or visual word, then utilize the Linearity Theory for vector addition to approximate the relationships between the new node and other nodes in graph. Then we demonstrate several applications which prove the effectiveness and efficiency of our proposed model and a user study for benefit verification. Finally, we explore some strategies to enhance the performance with the explicit or implicit user interaction including feedback, clickthrough data tracking.

Efficient shape matching for Chinese calligraphic character retrieval

An efficient search method is desired for calligraphic characters due to the explosive growth of calligraphy works in digital libraries. However, traditional optical character recognition (OCR) and handwritten character recognition (HCR) technologies are not suitable for calligraphic character retrieval. In this paper, a novel shape descriptor called SC-HoG is proposed by integrating global and local features for more discriminability, where a gradient descent algorithm is used to learn the optimal combining parameter. Then two efficient methods, keypoint-based method and locality sensitive hashing (LSH) based method, are proposed to accelerate the retrieval by reducing the feature set and converting the feature set to a feature vector. Finally, a re-ranking method is described for practicability. The approach filters query-dissimilar characters using the LSH-based method to obtain candidates first, and then re-ranks the candidates using the keypoint- or sample-based method. Experimental results demonstrate that our approaches are effective and efficient for calligraphic character retrieval.

D-Ocean: an unstructured data management system for data ocean environment

Together with the big datamovement,many organizations collect their own big data and build distinctive applications. In order to provide smart services upon big data, massive variable data should be well linked and organized to form Data Ocean, which specially emphasizes the deep exploration of the relationships among unstructured data to support smart services. Currently, almost all of these applications have to deal with unstructured data by integrating various analysis and search techniques upon massive storage and processing infrastructure at the application level, which greatly increase the difficulty and cost of application development.This paper presents D-Ocean, an unstructured data management system for data ocean environment. D-Ocean has an open and scalable architecture, which consists of a core platform, pluggable components and auxiliary tools. It exploits a unified storage framework to store data in different kinds of data stores, integrates batch and incremental processing mechanisms to process unstructured data, and provides a combined search engine to conduct compound queries. Furthermore, a so-called RAISE process modeling is proposed to support the whole process of Repository, Analysis, Index, Search and Environment modeling, which can greatly simplify application development. The experiments and use cases in production demonstrate the efficiency and usability of D-Ocean.

Hierarchical approximate matching for retrieval of chinese historical calligraphy character

As historical Chinese calligraphy works are being digitized, the problem of retrieval becomes a new challenge. But, currently no OCR technique can convert calligraphy character images into text, nor can the existing Handwriting Character Recognition approach does not work for it. This paper proposes a novel approach to efficiently retrieving Chinese calligraphy characters on the basis of similarity: calligraphy character image is represented by a collection of discriminative features, and high retrieval speed with reasonable effectiveness is achieved. First, calligraphy characters that have no possibility similar to the query are filtered out step by step by comparing the character complexity, stroke density and stroke protrusion. Then, similar calligraphy characters are retrieved and ranked according to their matching cost produced by approximate shape match. In order to speed up the retrieval, we employed high dimensional data structure — PK-tree. Finally, the efficiency of the algorithm is demonstrated by a preliminary experiment with 3012 calligraphy character images.

Region-based semantic similarity propagation for image retrieval

In order to reduce the gap between low-level image features and high-level image semantics, various long term learning strategies were integrated into content-based image retrieval system. The strategies always use the semantic relationships among images to improve the effectiveness of the retrieval system. This paper proposes a semantic similarity propagation method to mine the hidden semantic relationships among images. The semantic relationships are propagated between the similar images and regions. Experimental results verify the improvement on similarity propagation and image retrieval.

An approach to the compression of residual data with GPCA in video coding

Generalized Principle Component Analysis (GPCA) is a global solution to identify a mixture of linear models for signals. This method has been proved to be efficient in compressing natural images. In this paper we try to introduce GPCA into video coding. We focus on encoding residual frames with GPCA in place of classical DCT, and also propose to use it in MCTF based scalable video coding. Experiments show that GPCA really gets better PSNR with the same amount of data components as DCT, and this method is promising in our scalable video coding scheme.

Hold, Touch and Read It: Border Interactions in Mobile Reading Environment

With the popularity of mobile devices, more and more people read on their phones or tablets in fragmented time. Screen sizes, handedness and other habit factors make the user interface (UI) and interactions far from satisfying every reader. In this study, we present a capacitive sensor based prototype and some novel interactions. The palm grasp style and finger touch gestures are used to infer user reading intent. The user study shows our system can provide efficient recognition and good usability.

Multi-document summarization based on link analysis and text classification

This paper describes a multi-document summarizer in Chinese, ACRUX, which contains three new techniques: a fuzzy classification method based on KNN (FAMKNN), Subject-Oriented Multi-document Summarization (SOMS), and Multi-document Summarization with Link Analysis.