Medical Image Categorization using a Texture Based Symbolic Description

Florea, Filip; Barbu, Eugen; Rogozan, Alexandrina; Bensrhair, Abdelaziz; Buzuloiu, Vasile

doi:10.1109/icip.2006.312564

Cited by 12 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This problem calls for classification algorithms able to use the most discriminative information from the available data. The challenge described above is well known in the medical image annotation literature, where it is usually referred to as the interclass vs intra-class variability problem (Setia et al, 2006;Lehmann et al, 2004;Florea et al, 2006a). It appears also in other visual classification problems, such as face recognition and robotics (Sim and Zhang, 2004;Kim et al, 2007).…”

Section: Introductionmentioning

confidence: 99%

Discriminative cue integration for medical image annotation

Tommasi

Orabona

Caputo

2008

Pattern Recognition Letters

View full text Add to dashboard Cite

a b s t r a c tAutomatic annotation of medical images is an increasingly important tool for physicians in their daily activity. Hospitals nowadays produce an increasing amount of data. Manual annotation is very costly and prone to human mistakes. This paper proposes a multi-cue approach to automatic medical image annotation. We represent images using global and local features. These cues are then combined using three alternative approaches, all based on the support vector machine algorithm. We tested our methods on the IRMA database, and with two of the three approaches proposed here we participated in the 2007 ImageCLEFmed benchmark evaluation, in the medical image annotation track. These algorithms ranked first and fifth, respectively among all submission. Experiments using the third approach also confirm the power of cue integration for this task.

show abstract

Section: Introductionmentioning

confidence: 99%

Discriminative cue integration for medical image annotation

Tommasi

Orabona

Caputo

2008

Pattern Recognition Letters

View full text Add to dashboard Cite

show abstract

“…The proposed PCA-ORTH feature selection method achieves the running time close to the approximation method because it only repeats the calculation of cosine distance between vectors in the possible subsets of the coefficient matrix k, of which the size is not quite large for the chosen image descriptor. For example, only 2…”

Section: Resultsmentioning

confidence: 99%

“…Texture feature description plays fundamental roles in many computer vision applications, especially general texture classification that can be widely used in material surface inspection [1], medical imaging [2][3][4], object recognition [5][6][7], scene recognition [8], and image retrieval [9,10]. Because of its significance, a large number of texture description approaches have been proposed during the past decades [11][12][13][14].…”

Section: Introductionmentioning

confidence: 99%

A Novel Local Human Visual Perceptual Texture Description with Key Feature Selection for Texture Classification

Chi

Zhang

et al. 2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

This paper proposes a novel local texture description method which defines six human visual perceptual characteristics and selects the minimal subset of relevant as well as nonredundant features based on principal component analysis (PCA). We assign six texture characteristics, which were originally defined by Tamura et al., with novel definition and local metrics so that these measurements reflect the human perception of each characteristic more precisely. Then, we propose a PCA-based feature selection method exploiting the structure of the principal components of the feature set to find a subset of the original feature vector, where the features reflect the most representative characteristics for the textures in the given image dataset. Experiments on different publicly available large datasets demonstrate that the proposed method provides superior performance of classification over most of the state-of-the-art feature description methods with respect to accuracy and efficiency.

show abstract

“…Florea et al [4] have compared the automatic image categorization capabilities of different PACSs and have found that these systems are capable to recognize the main anatomical structures even in complex environment. However, the reliability of the recognition has been highly various among the different body regions.…”

Section: Related Workmentioning

confidence: 99%