Co-occurrence Bag of Words for Object Recognition
نویسندگان
چکیده
In the original ’bag of words’ model image features are seen as independent and orderless. In the real world, relative co-occurrence of image features defines the spatial order in which they appear. This means the spatial relationship between image features has potential information to be exploited in a classification task. Our model attempts to discover the usefulness of the co-occurrence information of image features with its extent ranging from local to global level targeting the image classification task. To establish the pair-wise relations between the features, we use the neighborhood of each image feature. To define the extent of neighborhood of an image feature at a local level and to achieve scale invariance, the model uses a circular area based on the elliptical scale at which each image feature is detected. To range from local to global level, the model explores the extent of the neighborhood spatially at integral multiples of the circular area radius. In turn, each image is described by a histogram of pair-wise visual words and a concatenated histogram of independent visual words with pair-wise visual words. We develop a stop word removal technique to eliminate noisy redundant visual words from the collection. Experimental results show that the pair-wise co-occurrences of visual words alone and their augmentation with independent occurrences leads to a positive improvement in the classification accuracy.
منابع مشابه
Higher-order Occurrence Pooling on Mid- and Low-level Features: Visual Concept Detection
In object recognition, the Bag-of-Words model assumes: i) extraction of local descriptors from images, ii) embedding these descriptors by a coder to a given visual vocabulary space which results in so-called mid-level features, iii) extracting statistics from mid-level features with a pooling operator that aggregates occurrences of visual words in images into so-called signatures. As the last s...
متن کاملA "Shape Aware" Model for semi-supervised Learning of Objects and its Context
We present an approach that combines bag-of-words and spatial models to perform semantic and syntactic analysis for recognition of an object based on its internal appearance and its context. We argue that while object recognition requires modeling relative spatial locations of image features within the object, a bag-of-word is sufficient for representing context. Learning such a model from weak...
متن کاملBag-of-words with aggregated temporal pair-wise word co-occurrence for human action recognition
http://dx.doi.org/10.1016/j.patrec.2014.07.014 0167-8655/ 2014 Elsevier B.V. All rights reserved. q This paper has been recommended for acceptance by G. Borgefors. ⇑ Corresponding author at: Department of Computer Languages and Systems, Universitat Jaume I, 12071 Castelló de la Plana, Spain. E-mail addresses: [email protected] (P. Agustí), [email protected] (V.J. Traver), pla@uji. es (F. Pla). Pau Ag...
متن کاملObject Category Recognition by Bag-of-Features Using Co-Occurrence Representation by Foreground and Background Information
متن کامل
Assessing the Effectiveness of Corpus-Based Methods in Solving SAT Sentence Completion Questions
This paper studies different corpus-based algorithms through which to answer SAT sentence completion questions. SAT sentence completion questions assess how well different words fit into a sentence, and the ability to answer such types of questions have wide implications in optical character and speech recognition post-processing as well as word-suggestion programs. In our study, we analyze sev...
متن کامل