Filtering Internet image search results towards keyword based category recognition

Abstract

In this work we aim to capitalize on the availability of Internet image search engines to automatically create image training sets from user provided queries. This problem is particularly difficult due to the low precision of image search results. Unlike many existing dataset gathering approaches, we do not assume a category model based on a small subset of the noisy data or an ad-hoc validation set. Instead we use a nonparametric measure of strangeness [8] in the space of holistic image representations, and perform an iterative feature elimination algorithm to remove the most strange examples from the category. This is the equivalent of keeping only features that are found to be consistent with others in the class. We show that applying our method to image search data before training improves average recognition performance, and demonstrate that we obtain comparative precision and recall results to the current state of the art, all the while maintaining a significantly simpler approach. In the process we also extend the strangeness-based feature elimination algorithm to automatically select good threshold values and perform filtering of a single class when the background is given.

K-way min-max cut for image clustering and junk images filtering from Google images

“…Unfortunately, the search results are still unsatisfactory because of the relatively low precision ratio and the existence of large number of junk images [1,2,3,4]. One big reason for this drawback is due to the fact that Google Images simplifies the image search problem as a text-based problem: the images are not indexed by their appearance but by text keywords which are extracted from the context of the images.…”

“…In addition, many real world web applications, such as photo-sharing websites, may only be able to provide noisy tags for image annotation which could further misguide keyword-based image search engines such as Google Images. Therefore, there is an urgent need to develop new algorithms for filtering out junk images from Google Images [1,2,3,4].…”

Disaster Image Filtering and Summarization Based on Multi-layered Affinity Propagation

“…In [6], the TSI-pLSA method is presented for image categorization based on a visual vocabulary, where the performance heavily relies on the quality of the training data. Wnuk et al [7] propose a nonparametric measure of strangeness based on visual characteristics of images. It neglects the role of textual features in capturing image semantics.…”

An Adaptive Query Prototype Modeling Method for Image Search Reranking

“…However, it would be reluctant or difficult for many users to provide the query image or the query image is difficult to be given. And some applications also need to harvest images for one query from the web [20,24].…”