From visual words to a visual grammar: using language modelling for image classification
This work addresses the semantic gap in computer vision for image classification, but it appears incremental as it builds on existing BoVW methods.
The paper tackled the problem of improving image classification by adapting language grammar properties to the Bag-of-Visual-Words paradigm, resulting in enhanced classification accuracy and reduced descriptor size.
The Bag--of--Visual--Words (BoVW) is a visual description technique that aims at shortening the semantic gap by partitioning a low--level feature space into regions of the feature space that potentially correspond to visual concepts and by giving more value to this space. In this paper we present a conceptual analysis of three major properties of language grammar and how they can be adapted to the computer vision and image understanding domain based on the bag of visual words paradigm. Evaluation of the visual grammar shows that a positive impact on classification accuracy and/or descriptor size is obtained when the technique are applied when the proposed techniques are applied.