An Alternate Approach for Designing a Domain Specific Image Search Prototype Using Histogram

• 作者: Debajyoti Mukhopadhyay Rana Dattagupta Sukanta Sinha
• 来源期刊: 软件工程与应用(英文)
• 学科: 工学
• 关键词: DOMAIN SPECIFIC Crawling HISTOGRAM GRAY-SCALE IMAGE IMAGE SEARCH Ontology SEARCH Engine
• 年，卷（期）: 2013,（3）
• 页码范围: 131-139
• 页数: 9页
• 分类号: TP39

摘要

Everyone knows that thousand of words are represented by a single image. As a result, image search has become a very popular mechanism for the Web-searchers. Image search means, the search results are produced by the search engine should be a set of images along with their Web-page Unified Resource Locator (URL). Now Web-searcher can perform two types of image search, they are “Text to Image” and “Image to Image” search. In “Text to Image” search, search query should be a text. Based on the input text data, system will generate a set of images along with their Web-page URL as an output. On the other hand, in “Image to Image” search, search query should be an image and based on this image, system will generate a set of images along with their Web-page URL as an output. According to the current scenarios, “Text to Image” search mechanism always not returns perfect result. It matches the text data and then displays the corresponding images as an output, which is not always perfect. To resolve this problem, Web researchers have introduced the “Image to Image” search mechanism. In this paper, we have also proposed an alternate approach of “Image to Image” search mechanism using Histogram.