Content-Free Image Retrieval using Bayesian Product Rule

Abstract

Content-free image retrieval uses accumulated user feedback records to retrieve images without analyzing image pixels. We present a Bayesian-based algorithm to analyze user feedback and show that it outperforms a recent maximum entropy content-free algorithm, according to extensive experiments on trademark logo and 3D model datasets. The proposed algorithm also has the advantage of being applicable to both content-free and traditional content-based image retrieval, thus providing a common framework for these two paradigms.

Using a game to evaluate image retrieval, organization, and annotation

“…Searching based on keyword annotation and retrieving images using collaborative filters occurs entirely without knowledge of the image content itself, only relying on previous human actions. Collaborative filtering has previously been applied to image retrieval and is sometimes referred to as content-free image retrieval [4]. Table 1 summarizes the requirements for implementing a single interface that allows the three selected query methods to be simultaneously implemented.…”

Design of a Web-Based Interface for Image Retrieval Systems

“…Rather than analyzing the specific properties of images, it relies on past information regarding the relations between images (Liu and Chen, 2006). In a CFIR system a user may associate related images together.…”

Semantic force relevance feedback, content-free 3D object retrieval and annotation propagation: bridging the gap and beyond

“…Recently, a few efforts have taken place, which are aiming at the detachment of algorithms from the necessity of descriptor extraction. In [22,27], two quite similar methods are presented, which rely on accumulation of records of user feedback. The system recycles them in the form of collaborative filtering [56], just like a purchase recommendation system such as Amazon.com [1].…”