A Hybrid Supervised-Unsupervised Vocabulary Generation Algorithm for Visual Concept Recognition
نویسندگان
چکیده
Vocabulary generation is the essential step in the bag-ofwords image representation for visual concept recognition, because its quality affects classification performance substantially. In this paper, we propose a hybrid method for visual word generation which combines unsupervised density-based clustering with the discriminative power of fast support vector machines. We aim at three goals: breaking the vocabulary generation algorithm up into two sections, with one highly parallelizable part, reducing computation times for bag of words features and keeping concept recognition performance at levels comparable to vanilla k-means clustering. On the two recent data sets Pascal VOC2009 and ImageCLEF2010 PhotoAnnotation, our proposed method either outperforms various baseline algorithms for visual word generation with almost same computation time or reduces training/test time with on par classification performance.
منابع مشابه
Supervised learning of Gaussian mixture models for visual vocabulary generation
The creation of semantically relevant clusters is vital in bag-of-visual words models which are known to be very successful to achieve image classification tasks. Generally, unsupervised clustering algorithms, such as K-means, are employed to create such clusters from which visual dictionaries are deduced. K-means achieves a hard assignment by associating each image descriptor to the cluster wi...
متن کاملVisual Vocabulary Learning and Its Application to 3D and Mobile Visual Search
In this technical report, we review related works and recent trends in visual vocabulary based web image search, object recognition, mobile visual search, and 3D object retrieval. Especial focuses would be also given for the recent trends in supervised/unsupervised vocabulary optimization, compact descriptor for visual search, as well as in multi-view based 3D object representation.
متن کاملProceedings of the Morpho Challenge 2010 Workshop
In natural language processing many practical tasks, such as speech recognition, information retrieval and machine translation depend on a large vocabulary and statistical language models. For morphologically rich languages, such as Finnish and Turkish, the construction of a vocabulary and language models that have a sufficient coverage is particularly difficult, because of the huge amount of d...
متن کاملEntropy Based Supervised Merging for Visual Categorization
Bag Of visual Words (BoW) is widely regarded as the standard representation of visual information present in the images and is broadly used for retrieval and concept detection in videos. The generation of visual vocabulary in the BoW framework generally includes a quantization step to cluster the image features into a limited number of visual words. This quantization achieved through unsupervis...
متن کاملAn incremental speaker-adaptation technique for hybrid HMM-MLP recognizer
One of the problems of the speaker-independent continuous speech recognition systems is their inability to cope with the inter-speaker variability. When we find test speakers with different characteristics from the ones presented in the training pool we observe a large degradation on the system performance. To overcome this problem speaker-adaptation techniques may be used to provide near speak...
متن کامل