Document page retrieval based on geometric layout features

Abstract

Today, the keyword retrieval method is most standard and popular, and has been widely used in many applications. However, even the keyword retrieval method cannot always satisfy various types of information search subjects, because various kinds of information resources such as image data, graphics data, etc. must be managed in multi-media society, in addition to the worddependent information. Of course, the methods which are more or less applicable to the characteristics of data resources such as structure, design, application, usage, volumn, etc., are necessary to make information-based activities of users successful.In this paper, we address a document page retrieval method based on the characteristics of page layout structure. Although the keyword retrieval method is a very excellent means in document page retrieval, we must pay attention to the case that keyword are not necessarily effective: it is not easy for foreigners to use keywords in different language or it is difficult for children to remember unknown words. In our method, the main idea is to focus on the geometric/positional relationships between characteristic components in identifying the document pages. Moreover, our original viewport is to introduce the inverted index, used commonly in the conventional information retrieval systems, but not to make use of structural/spatial relationship between characteristic components, which are standard in traditional map retrieval systems.

Methods for Automatic Web Page Layout Testing and Analysis: A Review

“…This can affect the results because the implementation of the library used deviates from the environment of web browsers used by users. The importance of layout information of websites in information retrieval can be seen in papers [32]- [34]. The paper [32] uses the properties of div and table DOM elements.…”

“…The main conclusions in the paper are that people have consistent decisions about which blocks are essential and that, in addition to spatial features, better results can be obtained by integrating the content properties of the pages. Finally, the paper [34] presents a prototype tool that uses information about the layout of elements on web pages in the form of images. The disadvantage of the last paper is that the tool has not been adequately tested on actual data.…”

A proposal of smart means to retrieve impressively-referred document-page

“…Of course, the search method that we should investigate here does not replace the ordinary keyword search method, but is desirable to be complimentarily used by some persons who cannot operate the keyword search method effectually or is useful when some persons cannot make use of keyword search successfully in case that they forgot suddenly the appropriate technical-terms or they are unfamiliar to the keywords. Our first idea is to focus on the geometric layout structure in 2-dimensional document page [22,23]. Then, our second idea is to use a relevant/irrelevant feedback control mechanism with a view to selecting a more suitable page from a set of ones which were retrieved in the first step [11,20].…”

“…Namely, we consider how to attain our objective through the above 4 technical issues successively: indexing focused on position; similarity based on physical measurement; automatic extraction of technicalterms/keywords; and relevant/irrelevant feedback control. These issues have already been investigated individually as our research projects: [22] in 1), [13,22] in 2), [15] in 3), and [11,20] in 4) are ours.…”

“…The number of positions which we designed is at most 9 (=3*3) and is very small in comparison with the number of documents to be commonly assumed in the information retrieval systems. This small number Figure 6 shows such a grid structure [22].…”