Wan Zhang

Symbol Recognition with Kernel Density Matching

We propose a novel approach to similarity assessment for graphic symbols. Symbols are represented as 2D kernel densities and their similarity is measured by the Kullback-Leibler divergence. Symbol orientation is found by gradient-based angle searching or independent component analysis. Experimental results show the outstanding performance of this approach in various situations

An interactive example-driven approach to graphics recognition in engineering drawings

An interactive example-driven approach to graphics recognition in engineering drawings is proposed. The scenario is that the user first interactively provides an example of a graphic object; the system instantly learns its graphical knowledge and uses the acquired knowledge to recognize the same type of graphic objects. The proposed approach represents the graphical knowledge of an object in terms of its structural components and their syntactical relationships. We summarize four types of geometric constraints for knowledge representation, based on which we develop an algorithm for knowledge acquisition. Another algorithm for graphics recognition using the acquired graphical knowledge is also proposed, which is actually a sequential examination of these constraints. In the algorithm, we first guess the next component’s attributes (e.g., size, position and orientation) by reasoning from an earlier found component and the constraint between them, and then search for this hypothetical component in the drawing. If all of the hypothetical components are found, a graphic object of this type is recognized. For improving the system’s recognition accuracy, we develop a user feedback scheme, which can update the graphical knowledge from both positive (missing) and negative (mis-recognized) examples provided by the user for subsequent recognition. Experiments have shown that our proposed approach is both efficient and effective for recognizing various types of graphic objects in engineering drawings.

A New Vectorial Signature for Quick Symbol Indexing, Filtering and Recognition

In this paper, we propose a novel descriptor based on symbol signatures for symbol filtering and recognition. First of all, all symbols are assumed in vectorial forms. All the primitive-pair relationships in a symbol are recorded and employed to create the signature representing the symbol. Although the approach aims at discriminating the symbol rapidly, it still preserves high recognition accuracy. Experiments on the data sets in GREC2003 [6] show its invariance on rotation, scaling, and other affine transformations.

Using a user-interactive QA system to capture student’s interest and authority about course content

A method for capturing the interest and authority of students about course content is proposed and implemented as a user modeling approach in a Web-based user-interactive question-answering (QA) system. An instructor has to define a topic ontology (or concept hierarchy) for the course content so that the system can generate the corresponding structure of boards to hold relevant questions. The students can interactively post questions, and browse, select, and answer others’ questions in their interested boards. The users’ log data are accumulated and organized as the users’ historical data, which are used to build the association space containing the association relations between the users’ historical data and the topic ontology. From the association space, the interest and authority of students about the questions in each board can be computed first and the interest and authority of students about each topic in the ontology can be computed based on the corresponding parameters of its offspring (sub-topics or questions). These user models (interest and authority) can be used to automatically and properly distribute relevant questions and answers to relevant students to enhance learning efficiency and help instructors design suitable teaching materials to enhance instruction efficiency.

A Discriminative Representation for Symbolic Image Similarity Evaluation

Visual similarity evaluation plays an important role in intelligent graphics system. A basic problem of it is how to extract the content information of an image and how to describe the information with an intermediate representation, namely, image representation, because the image representation has great influence on the efficiency and performance of the similarity evaluation. In this paper, we focus on the domain of symbolic image recognition and introduce the Directional Division Tree representation, which is the image representation used in our algorithm. The conducted experiment shows that similarity evaluation algorithm based on this representation can yield satisfactory efficiency and performance.

A New Syntactic Approach to Graphic Symbol Recognition

This paper presents a novel syntactic symbol recognition approach to the vector based symbol recognition problem. Different from existing syntactic approaches, which usually describe the geometric relations among primitives, our method formulates a new model to describe the geometric information of a primitive with respect to the whole symbol object based on mathematical analysis. The mathematical model is theoretically rotation and scale invariant and experiments show its accuracy for vector based symbol recognition.

Safeguard against unicode attacks : generation and applications of UC-simlist

A severe potential security problem in utilization of Unicode on the Web is identified, which is resulted from the fact that there are many similar characters in the Universal Character Set (UCS). The foundation of our solution relies on evaluating the similarity of characters in UCS. We develop a solution based on the renowned Kernel Density Estimation (KDE) method to establish such a Unicode Similarity List (UC-SimList).