Set Of Rotation Invariant Features Research Articles

Rotation invariant features based on three dimensional Gaussian Markov random fields for volumetric texture classification

This paper proposes a set of rotation invariant features based on three dimensional Gaussian Markov Random Fields (3D-GMRF) for volumetric texture image classification. In the method proposed here, the mathematical notion of spherical harmonics is employed to produce a set of features which are used to construct the rotation invariant descriptor. Our proposed method is evaluated and compared with other method in the literature for datasets containing synthetic textures as well as medical images. The results of our experiments demonstrate excellent classification performance for our proposed method compared with state-of-the-art methods. Furthermore, our method is evaluated using a clinical dataset and show good performance in discriminating between healthy individuals and COPD patients. Our method also performs well in classifying lung nodules in the LIDC-IDRI dataset. Our results indicate that our 3D-GMRF-based method enjoys more superior performance compared with other methods in the literature.

An accurate approach for the computation of polar harmonic transforms

Polar Harmonic Transforms (PHTs) can be used as a feature extraction technique by exploiting their orthogonal basis that generate a set of rotation invariant features. PHTs have distinct traits as compared with other transforms and moments. This is because of their less redundant information. Applied to digital images polar harmonic transforms suffer from various numerical and statistical errors. In this paper a computational framework based on two different numerical integration schemes which reduce the numerical errors in the computation of the transforms. Extensive experiments are carried out in order to assess the accuracy of the proposed technique in face recognition problem. Two standard face databases are employed, i.e., ORL and JAFFE, which contain images with different variations. Furthermore, the rotation invariant trait of the proposed approach is evaluated using different rotation angles. The proposed approach attenuates the numerical errors as well as provides numerical stability to PHTs of high orders.

Multi-Classifier Framework for Medical Image Analysis using Mutual Information Criterion

The efficacy of the medical image analysis with the level-set shape along with fractal texture and intensity features to discriminate PF (Posteriorfossa) tumor from other tissues in the brain image. Further, extracted features may not be adequate to differentiate amongst the medical images. To enhance the medical image processing, to devise an automotive subjective optimality model for segmentation of images based on different sets of selected features from the unsupervised learning model of extracted features. After segmentation, it is necessary to classify the image based on different classes it belongs to. To classify a medical image, a multiple classifier framework and classify the image based on the classes like normal body cells, infected cells, and highly infected cells. The classifier is designed based on the mutual information coefficient of the selected features underwent for image segmentation procedures. The classification is done with set of rotation invariant features being selected on the lines of subjective-optimality and different classifiers are organized using different features sets trained in different data. An experimental performance is evaluated with benchmark data sets extracted from research repositories of both real and synthetic data sets. The performance parameter used for the analysis of the proposed multi-classifier framework using mutual concept criterion [MFMCC] for medical image analysis are Multiple Class intensity, Mutual information coefficient of rich features and efficiency.

Sorting of rice grains using Zernike moments

Two important factors that determine the efficiency and reliability of a rice sorting machine are the overall processing speed and the classification accuracy. In this paper, an efficient rice sorting process which uses a subset of Zernike moments (ZM) and a multilayer perceptron is presented. Since the falling rice grains during sorting process can be in any orientation, a rotational invariant feature set is crucial in this application. Hence, the set of ZM with its inherent rotational invariance property is chosen in this context. Nevertheless, one of the main drawbacks of ZM in real-time application is its long computation time. To overcome this, a subset of ZM is selected from its original full set of 12 orders, using the combination of fuzzy ARTMAP and genetic algorithm. To further reduce the computation time, the combination of q-recursive method and Zernike polynomials’ inherent symmetry property is utilized. Hence, the processing time of the subset of ZM is significantly reduced by almost 67% while maintaining the classification accuracy as compared to computing the original full set of ZMs.

Airborne pollen texture discrimination using wavelet transforms in combination with cooccurrence matrices

In the recent years, image processing and pattern recognition techniques have been applied to develop intelligent systems for both of fresh and fossil pollen grains discrimination. In this paper, we aim at the texture identification of pollen surface images. A method of texture description using wavelet transforms in combination with cooccurrence matrices is presented, and a neural network is used to classify the extracted image features. In this combined method, through wavelet decomposition and reconstruction, an approximation image and a new details image are generated for the input image. The surface texture of pollen grains is characterised by using a rotational invariant feature set, which is formed from the joint distribution of the grey level and the details information. In order to form effective feature vectors, the moment invariants also were employed to describe the surface shape of pollen grains. Both the back-propagation (BP) and the learning vector quantisation (LVQ) networks were used for classification of the resulting feature vectors. In experiments with sixteen types of airborne pollen grains, more than 91% pollen images are correctly classified using both the methods.

Wavelet-based rotational invariant roughness features for texture classification and segmentation

In this paper, we introduce a rotational invariant feature set for texture segmentation and classification, based on an extension of fractal dimension (FD) features. The FD extracts roughness information from images considering all available scales at once. In this work, a single scale is considered at a time so that textures with scale-dependent properties are satisfactorily characterized. Single-scale features are combined with multiple-scale features for a more complete textural representation. Wavelets are employed for the computation of single- and multiple-scale roughness features because of their ability to extract information at different resolutions. Features are extracted in multiple directions using directional wavelets, and the feature vector is finally transformed to a rotational invariant feature vector that retains the texture directional information. An iterative K-means scheme is used for segmentation, and a simplified form of a Bayesian classifier is used for classification. The use of the roughness feature set results in high-quality segmentation performance. Furthermore, it is shown that the roughness feature set exhibits a higher classification rate than other feature vectors presented in this work. The feature set retains the important properties of FD-based features, namely insensitivity to absolute illumination and contrast.

Recognition and pose estimation of unoccluded three-dimensional objects from a two-dimensional perspective view by banks of neural networks

This paper describes a neural network (NN) based system for recognition and pose estimation of an unoccluded three-dimensional (3-D) object from any single two-dimensional (2-D) perspective view. The approach is invariant to translation, orientation, and scale. First, the binary silhouette of the object is obtained and normalized for translation and scale. Then, the object is represented by a set of rotation invariant features derived from the complex orthogonal pseudo-Zernike moments of the image. The recognition scheme combines the decisions of a bank of multilayer perceptron NN classifiers operating in parallel on the same data. These classifiers have different topologies and internal parameters, but are trained on the same set of exemplar perspective views of the objects. Next, two pose parameters, elevation and aspect angles, are obtained by a novel two-stage NN system consisting of a quadrant classifier followed by NN angle estimators. Performance is tested on clean and noisy data bases of military ground vehicles. Comparative studies with three other classifiers (a single NN, the weighted nearest-neighbor classifier, and a binary decision tree) are carried out.

Invariant image recognition by Zernike moments

The problem of rotation-, scale-, and translation-invariant recognition of images is discussed. A set of rotation-invariant features are introduced. They are the magnitudes of a set of orthogonal complex moments of the image known as Zernike moments. Scale and translation invariance are obtained by first normalizing the image with respect to these parameters using its regular geometrical moments. A systematic reconstruction-based method for deciding the highest-order Zernike moments required in a classification problem is developed. The quality of the reconstructed image is examined through its comparison to the original one. The orthogonality property of the Zernike moments, which simplifies the process of image reconstruction, make the suggest feature selection approach practical. Features of each order can also be weighted according to their contribution to the reconstruction process. The superiority of Zernike moment features over regular moments and moment invariants was experimentally verified.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Rotation invariant image recognition using features selected via a systematic method

In this paper a new set of rotation invariant features for image recognition is introduced. The features are the magnitudes of a set of orthogonal complex moments of the image called Zernike moments. These features could easily be constructed to an arbitrary high order. Taking advantage of the orthogonality property, a systematic feature selection method for choosing an appropriate number of the Zernike features is developed. It is based on computing a measure of the information content differences of features of different classes. The performance of the method is experimentally tested on a 26-class and a 10-class data set involving differently oriented binary images. The first set consists of 624 images of all English characters. The second one is an extensive set of numeric handprinted characters involving 16,550 samples. Using a nearest neighbor classifier 99% and 84% classification accuracies are obtained respectively.