Abstract

Lately, 3D imaging techniques have achieved a lot of progress due to recent developments in 3D sensor technologies. This leads to a great interest regarding 3D image feature extraction and classification techniques. As pointed out in literature, one of the most important and discriminative features in images is the textural content. Within this context, we propose a texture feature extraction technique for volumetric images with improved discrimination power. The method could be used in textured volumetric data classification tasks. To achieve this, we fuse two complementary pieces of information, feature vectors derived from Local Binary Patterns (LBP) and the Gray-Level Co-occurrence Matrix-based methods. They provide information regarding the image pattern and the contrast, homogeneity and local anisotropy in the volumetric data, respectively. The performance of the proposed technique was evaluated on a public dataset consisting of volumetric textured images affected by several transformations. The classifiers used are the Support Vector Machine, k-Nearest Neighbours and Random Forest. Our method outperforms other handcrafted 3D or 2D texture feature extraction methods and typical deep-learning networks. The proposed technique improves the discrimination power and achieves promising results even if the number of images per class is relatively small.

Highlights

  • We propose a volumetric feature extraction technique which fuses two types of feature vectors: one based on the signs of the differences between neighbouring voxels generated by an Local Binary Patterns (LBP)-based technique and one that takes into account the magnitude of the differences between pixels, derived from a Gray-Level Co-Occurrence Matrix (GLCM)-based feature extraction method

  • The LBP-based technique is the 3D version of the BM3DELBP algorithm, which provides invariance to different image transformations and robustness to Gaussian noise, while the GLCM-based method is an improved volumetric version of the popular GLCM based on image intensity and on the gradient image information

  • We evaluated the performance of the proposed texture feature extraction method on a public dataset containing synthetic 3D textures altered by several transformations

Read more

Summary

Introduction

The training step uses a training set of images for which the categories to which they belong are known. These images are analysed by using a feature extraction technique, which is used to provide the most important and discriminative features in an image (stored as a feature vector). The same feature extraction method is used to determine the feature vector for the new image At this point, a classification operation is used to compare this feature vector with the ones obtained in the training phase and to assign the new image to the nearest class based on a specific criterion. The LBP operator provides a local representation of textured images which is obtained by computing differences between neighbouring pixels.

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call