Visual Search Optimization using Concept Related Re-Ranking

نویسندگان

  • G. Lakshmi Narayanan
  • V. Kalaivani
چکیده

Visual search re-ranking defined as re-ordering visual documents like image, videos etc. based on the initial search. Ranking the multimedia content like images, videos are a challenging research topic in the noisy visual environment. Now days, leading search engines are fully depends on the description, title, surrounding information of an image which produce irrelevant image which are not equal to visual content. In this paper, a new approach proposed to improve the visual search precision level. First, the initial ranking occurred based on the textual information like tag, description relevancy which didn’t produce relevant images. Second, by using visual query examples in the search engine to filter the images based on feature. The visual equivalence between the images calculated to increase the relevance results. Mainly the Equivalence Reranking approach focused on the relationship between the concepts of documents considered to reorder the initial search result with higher resolution images for optimizing the list of images. And by avoiding and removing irrelevant image along with the low resolution images by re-ranking approach, will increase the performance of search engine.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Circular Re-ranking for Visual Search

Conventional approaches to visual search re-ranking empirically take the “classification performance” as the optimization objective, in which each visual document is determined relevant or not, followed by a process of increasing the order of relevant documents. First show that the classification performance fails to produce a globally optimal ranked list, and then formulate re-ranking as an op...

متن کامل

A Review on Content Based Image Re-Ranking using Semantic Analysis

A CBIR is an effective way to improve the relevancy rate for image search. Image search engines such as Google and Bing mostly use keyword queried by the user and they rely on surrounding text for searching images. But sometime it is not efficient and results in imprecise output therefor ambiguity of query images is difficult to describe accurately by using keyword for e.g. Sony is query keywor...

متن کامل

Image Filtering and Re-ranking Using Data mining Techniques

Search re-ranking is considered a typical thanks to boost retrieval exactitude. The matter yet isn't trivial particularly once there square measure multiple options or modalities to be thought-about for search, which frequently happens in image and video retrieval. This paper proposes a replacement re-ranking algorithmic program, named data processing based mostly on re-ranking, that reinforces...

متن کامل

An Effective Personalized Search Engine Architecture for Re-ranking Search Results Using User Behavior

Web search engines provide users with a Large number of results for a submitted query. However, not all return results are relevant to the uses needs. In this paper, we proposed a new web search personalization approach that captures the user's interest and references in the form of concepts by mining search results and they click through. In this paper an effective mixture personalized reranki...

متن کامل

Image Search Reranking

The existing methods for image search re ranking suffer from the unfaithfulness of the assumptions under which the text-based images search result. The resulting images contain more irrelevant images. Hence the re ranking concept arises to re rank the retrieved images based on the text around the image and data of data of image and visual feature of image. A number of methods are differentiated...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012