This note summarizes methodologies employed in our submissions for the medical retrieval subtask of 2012 ImageCLEF competition. Our work aims to provide a systematic comparison of various similarity measures in the Medical CBIR application context. Our system consists of the standard bag-of-words features with SIFT. Computed features are then compared by using various plug-in similarity measure...

The ever increasing number of medical images in hospitals urges on the need for generic content based image retrieval systems. These systems are in an area of great importance to the healthcare providers. The first and foremost function in such system is feature extraction. In this paper, different feature extraction techniques have been utilized to represent medical blood cell images. They are...

Incorporation of evidence from clinical research requires critical appraisal of its quality. Information retrieval systems can facilitate clinicians' judgments by automatically labeling retrieved citations with their strength of evidence categories. Preliminary results of such a text classification experiment involving MEDLINE citations show that a "bag of words" approach is insufficient for ac...

content-based image retrieval: indexing based on inverted file representations or global descriptors. nearest-neighbor search in Euclidean space, product quantization application to compressed-domain image classification. video copy detection: using bag-of-words or global video representations action analysis in videos, video structuring 3D reconstruction with a multi-camera studio (kinovis.inr...

The traditional vector space model of IR treats a query as a structureless whole, a “bag of words”, thus failing to capture many finer points. We propose an algorithm that breaks a query up into smaller units, does retrieval on these, and then combines the results, thereby respecting some of the query structure. Experimental results for a standard test collection are given and discussed.

The last decade has witnessed great interest in research on content-based image retrieval. This has paved the way for a large number of new techniques and systems, and a growing interest in associated fields to support such systems. Likewise, digital imagery has expanded its horizon in many directions, resulting in an explosion in the volume of image data required to be organized. As a result, ...

We present an algorithm for simultaneously recognizing and localizing planar textured objects in an image. The algorithm can scale efficiently with respect to a large number of objects added into the database. In contrast to the current state-of-the-art on large scale image search, our algorithm can accurately work with query images consisting of several specific objects and/or multiple instanc...

Because of the popularity of online multimedia videos, there has been much interest in recent years in in multimedia event detection (MED) research. MED requires a system that can search user-submitted quality videos, like those found on YouTube, for specific events. Video features play a significant role is determining the content for MED tasks. However, the audio component for a given video c...

In natural language processing and information retrieval, the bag of words representation is used to implicitly represent the meaning of the text. Implicit semantics, however, are insufficient in supporting text or natural language based interfaces, which are adopted by an increasing number of applications. Indeed, in applications ranging from automatic ontology construction to question answeri...