In recent years, the retrieval of plane geometry figures (PGFs) has attracted increasing attention in the fields of mathematics
education and computer science. However, the high cost of matching complex PGF features leads to the low efficiency of
most retrieval systems. This paper proposes an indirect classification method based on multi-label learning, which
improves retrieval efficiency by reducing the scope of compare operation from the whole database to small candidate
groups. Label correlations among PGFs are taken into account for the multi-label classification task. The primitive feature
selection for multi-label learning and the feature description of visual geometric elements are conducted individually to
match similar PGFs. The experiment results show the competitive performance of the proposed method compared with
existing PGF retrieval methods in terms of both time consumption and retrieval quality.
As there are increasing numbers of digital documents for education purpose, we realize that there is not a retrieval application for mathematic plane geometry images. In this paper, we propose a method for retrieving plane geometry figures (PGFs), which often appear in geometry books and digital documents. First, detecting algorithms are applied to detect common basic geometry shapes from a PGF image. Based on all basic shapes, we analyze the structural relationships between two basic shapes and combine some of them to a compound shape to build the PGF descriptor. Afterwards, we apply matching function to retrieve candidate PGF images with ranking. The great contribution of the paper is that we propose a structure analysis method to better describe the spatial relationships in such image composed of many overlapped shapes. Experimental results demonstrate that our analysis method and shape descriptor can obtain good retrieval results with relatively high effectiveness and efficiency.
In this paper, we propose a robust and fast line segment detector, which achieves accurate results with a controlled
number of false detections and requires no parameter tuning. It consists of three steps: first, we propose a novel edge
point chaining method to extract Canny edge segments (i.e., contiguous chains of Canny edge points) from the input
image; second, we propose a top-down scheme based on smaller eigenvalue analysis to extract line segments within each
obtained edge segment; third, we employ Desolneux et al.’s method to reject false detections. Experiments demonstrate
that it is very efficient and more robust than two state of the art methods—LSD and EDLines.
For objects with the same texture but different colors, it is difficult to discriminate them with the traditional scale invariant feature transform descriptor (SIFT), because it is designed for grayscale images only. Thus it is important to keep a high probability to make sure that the used key points are couples of correct pairs. In addition, mean distributed key points are much more expected than over dense and clustered key points for image match and other applications. In this paper, we analyze these two problems. First, we propose a color and scale invariant method to extract a more mean distributed key points relying on illumination intensity invariance but object reflectance sensitivity variance variable. Second, we modify the key point’s canonical direction accumulated error by dispersing each pixel’s gradient direction on a relative direction around the current key point. At last, we build the descriptors on a Gaussian pyramid and match the key points with our enhanced two-way matching regulations. Experiments are performed on the Amsterdam Library of Object Images dataset and some synthetic images manually. The results show that the extracted key points have better distribution character and larger number than SIFT. The feature descriptors can well discriminate images with different color but with the same content and texture.
As an effective information transmitting way, chart is widely used to represent scientific statistics datum in books, research papers, newspapers etc. Though textual information is still the major source of data, there has been an increasing trend of introducing graphs, pictures, and figures into the information pool. Text recognition techniques for documents have been accomplished using optical character recognition (OCR) software. Chart recognition techniques as a necessary supplement of OCR for document images are still an unsolved problem due to the great subjectiveness and variety of charts styles. This paper reviews the development process of chart recognition techniques in the past decades and presents the focuses of current researches. The whole process of chart recognition is presented systematically, which mainly includes three parts: chart segmentation, chart classification, and chart Interpretation. In each part, the latest research work is introduced. In the last, the paper concludes with a summary and promising future research direction.
XML is widely used in various document formats on the web. But it has caused negative impacts such as
expensive document distribution time over the web, and long content jumping and rendering delay, especially on
mobile devices. Hence we proposed a Schema-based efficient queryable XML compressor, called XTrim, which
significantly improves compression ratio by utilizing optimized information in XML Schema while supporting
efficient queries. Firstly, XTrim draws structure information from XML document and corresponding XML
Schema. Then a novel technique is used to transform the XML tree-like structure into a compact indexed
form to support efficient queries. At the same time, text values are obtained, and a language-based text trim
method (LTT) that facilitates language-specific text compressors is adopted to reduce the size of text values
in various languages. In LTT a word composition detection method is proposed to better process text in
non-Latin languages. To evaluate the performance of XTrim, we have implemented a compressor and query
engine prototype. Via extensive experiments, results show that XTrim outperforms XMill and existing queryable
alternatives in terms of compression ratio, as well as the query efficiency. By applying XTrim to documents, the
storage space can save up to 30% and the content jumping and rendering delay is reduced to less than 100ms
from 4 seconds.