From Bag-of-Visual-Words to Bag-of-Visual-Phrases Using n-Grams

Stranieri

Computer Science &Amp; Information Technology ( CS &Amp; IT )

et al. 2014

Various texture, shape, boundary features have been used previously to classify regions of interest in radiological mammograms into normal and abnormal categories. Although, bag-ofphrases or n-gram model has been effective in text representation for classification or retrieval of text, these approaches have not been widely explored for medical image processing. Our purpose is to represent regions of interest using an n-gram model, then deploy the n-gram features into a back-propagation trained neural network for classifying regions of interest into normal and abnormal categories. Experiments on the benchmark miniMIAS database show that

Section: Literature Reviewmentioning

confidence: 99%

“…An image can be represented with the help of n-grams or bagof-visual-phrases model. Pedrosa [6] shows that the n-gram representation can improve the retrieval performance over bag-of-words model for medical as well as non-medical image datasets.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Technique Based on N-GRAM and Neural Networks for Classification of Mammographic Images

Stranieri

Computer Science &Amp; Information Technology ( CS &Amp; IT )

et al. 2014

“…Moreover, it is concluded from the experiments presented in [46], that SIFT based systems with optimized parameters slightly outperformed the GIFT (GNU Image finding tool) system. [10]. They used scale invariant Fourier transform (SIFT) features by identifying keypoints and then represented the image as a Bag of Visual Phrases model.…”

Section: Literature Reviewmentioning

confidence: 99%

“…An image can be represented with the help of n-grams or bagof-visual-phrases model. Pedrosa [10] shows that the visual n-gram representation can improve the retrieval performance over bag-of-words model for medical as well as non-medical image datasets. In languages such as Chinese, where there are no specific word boundaries a concept called character n-gram is very useful for document retrieval.…”

Section: Introductionmentioning

confidence: 99%

Visual Character N-Grams for Classification and Retrieval of Radiological Images

Kulkarni¹,

Stranieri²,

Kulkarni³

et al. 2014

IJMA

2015 IEEE International Symposium on Multimedia (ISM)

“…Commonly-used approaches for near-duplicate image detection are the Bag-of-Visual-Words and the Bag-of-Phrases models [6]. They encode the features at each local image region as a visual word and represent images as a histogram of the resulting words [3].…”

Section: Introductionmentioning

confidence: 99%

Self Similarity Wide-Joins for Near-Duplicate Image Detection

Carvalho

Santos

Oliveira

et al. 2015

Self Cite

Abstract-Near-duplicate image detection plays an important role in several real applications. Such task is usually achieved by applying a clustering algorithm followed by refinement steps, which is a computationally expensive process. In this paper we introduce a framework based on a novel similarity join operator, which is able both to replace and speed up the clustering step, whereas also releasing the need of further refinement processes. It is based on absolute and relative similarity ratios, ensuring that top ranked image pairs are in the final result. Experiments performed on real datasets shows that our proposal is up to three orders of magnitude faster than the best techniques in the literature, always returning a high-quality result set.