Bag of Words Model in Computer Vision - Limitations and Recent Developments

Limitations and Recent Developments

One of notorious disadvantages of BoW is that it ignores the spatial relationships among the patches, which is very important in image representation. Researchers have proposed several methods to incorporate the spatial information. For feature level improvements, correlogram features can capture spatial co-occurrences of features. For generative models, relative positions of codewords are also taken into account. The hierarchical shape and appearance model for human action introduces a new part layer (Constellation model) between the mixture proportion and the BoW features, which captures the spatial relationships among parts in the layer. For discriminative models, spatial pyramid match performs pyramid matching by partitioning the image into increasingly fine sub-regions and compute histograms of local features inside each sub-region.

Furthermore, the BoW model has not been extensively tested yet for view point invariance and scale invariance, and the performance is unclear. Also the BoW model for object segmentation and localization is also lack of study.

Read more about this topic:  Bag Of Words Model In Computer Vision

Famous quotes containing the words limitations and/or developments:

    That all may be so, but when I begin to exercise that power I am not conscious of the power, but only of the limitations imposed on me.
    William Howard Taft (1857–1930)

    I don’t wanna live in a city where the only cultural advantage is that you can make a right turn on a red light.
    Freedom from labor itself is not new; it once belonged among the most firmly established privileges of the few. In this instance, it seems as though scientific progress and technical developments had been only taken advantage of to achieve something about which all former ages dreamed but which none had been able to realize.
    Hannah Arendt (1906–1975)