Sheryl Brahnam

Local binary patterns variants as texture descriptors for medical image analysis

OBJECTIVE This paper focuses on the use of image-based machine learning techniques in medical image analysis. In particular, we present some variants of local binary patterns (LBP), which are widely considered the state of the art among texture descriptors. After we provide a detailed review of the literature about existing LBP variants and discuss the most salient approaches, along with their pros and cons, we report new experiments using several LBP-based descriptors and propose a set of novel texture descriptors for the representation of biomedical images. The standard LBP operator is defined as a gray-scale invariant texture measure, derived from a general definition of texture in a local neighborhood. Our variants are obtained by considering different shapes for the neighborhood calculation and different encodings for the evaluation of the local gray-scale difference. These sets of features are then used for training a machine-learning classifier (a stand-alone support vector machine). METHODS AND MATERIALS Extensive experiments are conducted using the following three datasets: RESULTS AND CONCLUSION Our results show that the novel variant named elongated quinary patterns (EQP) is a very performing method among those proposed in this work for extracting information from a texture in all the tested datasets. EQP is based on an elliptic neighborhood and a 5 levels scale for encoding the local gray-scale difference. Particularly interesting are the results on the widely studied 2D-HeLa dataset, where, to the best of our knowledge, the proposed descriptor obtains the highest performance among all the several texture descriptors tested in the literature.

Survey on LBP based texture descriptors for image classification

The aim of this work is to find the best way for describing a given texture using a local binary pattern (LBP) based approach. First several different approaches are compared, then the best fusion approach is tested on different datasets and compared with several approaches proposed in the literature (for fair comparisons, when possible we have used code shared by the original authors).Our experiments show that a fusion approach based on uniform local quinary pattern (LQP) and a rotation invariant local quinary pattern, where a bin selection based on variance is performed and Neighborhood Preserving Embedding (NPE) feature transform is applied, obtains a method that performs well on all tested datasets.As the classifier, we have tested a stand-alone support vector machine (SVM) and a random subspace ensemble of SVM. We compare several texture descriptors and show that our proposed approach coupled with random subspace ensemble outperforms other recent state-of-the-art approaches. This conclusion is based on extensive experiments conducted in several domains using six benchmark databases.

Local Ternary Patterns from Three Orthogonal Planes for human action classification

Research highlights? LBP features extracted from the human silhouette. ? Random subspace for human action classification. ? To combine LBP-TOP with LTP. Human action classification is a new field of study with applications ranging from automatically labeling video segments to recognition of suspicious behavior in video surveillance cameras. In this paper we present some variants of Local Binary Patterns from Three Orthogonal Planes (LBP-TOP), which is considered one of the state of the art texture descriptors for human action classification. The standard LBP-TOP operator is defined as a gray-scale invariant texture measure, derived from the standard Local Binary Patterns (LBP). It is obtained by calculating the LBP features from the xt and yt planes of a space-time volume. Our LBP-TOP variants combine the idea of LBP-TOP with Local Ternary Patterns (LTP). The encoding of LTP is used for the evaluation of the local gray-scale difference in the different planes of the space-time volume. Different histograms are concatenated to form the feature vector and a random subspace of linear support vector machines is used for classifying action using the Weizmann database of video images. To the best of our knowledge, our method offers the first set of classification experiments to obtain 100% accuracy using the 10-class Weizmann dataset.

Machine recognition and representation of neonatal facial displays of acute pain

OBJECTIVE It has been reported in medical literature that health care professionals have difficulty distinguishing a newborns facial expressions of pain from facial reactions to other stimuli. Although a number of pain instruments have been developed to assist health professionals, studies demonstrate that health professionals are not entirely impartial in their assessment of pain and fail to capitalize on all the information exhibited in a newborns facial displays. This study tackles these problems by applying three different state-of-the-art face classification techniques to the task of distinguishing a newborns facial expressions of pain. METHODS The facial expressions of 26 neonates between the ages of 18 h and 3 days old were photographed experiencing the pain of a heel lance and a variety of stressors, including transport from one crib to another (a disturbance that can provoke crying that is not in response to pain), an air stimulus on the nose, and friction on the external lateral surface of the heel. Three face classification techniques, principal component analysis (PCA), linear discriminant analysis (LDA), and support vector machine (SVM), were used to classify the faces. RESULTS In our experiments, the best recognition rates of pain versus nonpain (88.00%), pain versus rest (94.62%), pain versus cry (80.00%), pain versus air puff (83.33%), and pain versus friction (93.00%) were obtained from an SVM with a polynomial kernel of degree 3. The SVM outperformed two commonly used methods in face classification: PCA and LDA, each using the L1 distance metric. CONCLUSION The results of this study indicate that the application of face classification techniques in pain assessment and management is a promising area of investigation.

A local approach based on a Local Binary Patterns variant texture descriptor for classifying pain states

This paper focuses on the use of image-based techniques for classifying pain states, in particular we compare several texture descriptors based on Local Binary Patterns (LBP), and we proposed some novel solutions based on the combination of new texture descriptors: the Elongated Ternary Pattern (ELTP) and the Elongated Binary Pattern (ELBP). ELTP is the best performing descriptor in our experiments. The ELBP descriptor combines characteristics of the Local Ternary Pattern (LTP) and ELTP. These two variants of the standard LBP are obtained by considering different shapes for the neighborhood calculation and different encodings for the evaluation of the local gray-scale difference. The resulting extracted features are used to train a support vector machine classifier. Extensive experiments are conducted using the Infant COPE database of neonatal facial images. Our results show that a local approach based on the ELTP feature extractor produces a reliable system for classifying pain states.

Prediction of protein structure classes by incorporating different protein descriptors into general Chou's pseudo amino acid composition.

Successful protein structure identification enables researchers to estimate the biological functions of proteins, yet it remains a challenging problem. The most common method for determining an unknown proteins structural class is to perform expensive and time-consuming manual experiments. Because of the availability of amino acid sequences generated in the post-genomic age, it is possible to predict an unknown proteins structural class using machine learning methods given a proteins amino-acid sequence and/or its secondary structural elements. Following recent research in this area, we propose a new machine learning system that is based on combining several protein descriptors extracted from different protein representations, such as position specific scoring matrix (PSSM), the amino-acid sequence, and secondary structural sequences. The prediction engine of our system is operated by an ensemble of support vector machines (SVMs), where each SVM is trained on a different descriptor. The results of each SVM are combined by sum rule. Our final ensemble produces a success rate that is substantially better than previously reported results on three well-established datasets. The MATLAB code and datasets used in our experiments are freely available for future comparison at http://www.dei.unipd.it/node/2357.

Machine assessment of neonatal facial expressions of acute pain

We propose that a machine assessment system of neonatal expressions of pain be developed to assist clinicians in diagnosing pain. The facial expressions of 26 neonates (age 18-72h) were photographed experiencing the acute pain of a heel lance and three nonpain stressors. Four algorithms were evaluated on out-of-sample observations: PCA, LDA, SVMs and NNSOA. NNSOA provided the best classification rate of pain versus nonpain (90.20%), followed by SVM with linear kernel (82.35%). We believe these results indicate a high potential for developing a decision support system for diagnosing neonatal pain from images of neonatal facial displays.

Wavelet images and Chou’s pseudo amino acid composition for protein classification

The last decade has seen an explosion in the collection of protein data. To actualize the potential offered by this wealth of data, it is important to develop machine systems capable of classifying and extracting features from proteins. Reliable machine systems for protein classification offer many benefits, including the promise of finding novel drugs and vaccines. In developing our system, we analyze and compare several feature extraction methods used in protein classification that are based on the calculation of texture descriptors starting from a wavelet representation of the protein. We then feed these texture-based representations of the protein into an Adaboost ensemble of neural network or a support vector machine classifier. In addition, we perform experiments that combine our feature extraction methods with a standard method that is based on the Chou’s pseudo amino acid composition. Using several datasets, we show that our best approach outperforms standard methods. The Matlab code of the proposed protein descriptors is available at http://bias.csr.unibo.it/nanni/wave.rar.

High performance set of PseAAC and sequence based descriptors for protein classification

The study of reliable automatic systems for protein classification is important for several domains, including finding novel drugs and vaccines. The last decade has seen a number of advances in the development of reliable systems for classifying proteins. Of particular interest has been the exploration of new methods for extracting features from a protein that enhance classification for a given problem. Most methods developed to date, however, have been evaluated in only one or two application areas. Methods have not been explored that generalize well across a number of application areas and datasets. The aim of this study is to find a general method, or an ensemble of methods, that works well on different protein classification datasets and problems. Towards this end, we evaluate several feature extraction approaches for representing proteins starting from their amino acid sequence as well as different feature descriptor combinations using an ensemble of classifiers (support vector machines). In our experiments, more than ten different protein descriptors are compared using nine different datasets. We develop our system using a blind testing protocol, where the parameters of the system are optimized using one dataset and then validated using the other datasets (and so on for each dataset). Although different stand-alone classifiers work well on some datasets and not on others, we have discovered that fusion among different methods obtains a good performance across all the tested datasets, especially when using the weighted sum rule. Included in our feature descriptor combinations is the introduction of two new descriptors, one based on wavelets and the other based on amino acid groups. Using our system, both outperform their standard implementations. We also consider as a baseline the simple amino acid composition (AC) and dipeptide composition (2G), since they have been widely used for protein classification. Our proposed method outperforms AC and 2G.

A simple method for improving local binary patterns by considering non-uniform patterns

The basic idea behind LBP is that an image is composed of micropatterns. A histogram of these micropatterns contains information about the local features in an image. These micropatterns can be divided into two types: uniform and non-uniform. In standard applications using LBP, only the uniform patterns are used. The non-uniform patterns are considered in only a single bin of the histogram that is used to extract features in the classification stage. Non-uniform patterns have undesirable characteristics: they are of a high dimension, partially correlated, and introduce unwanted noise. To offset these disadvantages, we explore using random subspace, well-known to work well with noise and correlated features, to train features based also on non-uniform patterns. We find that a stand-alone support vector machine performs best with the uniform patterns and random subspace with histograms of 50 bins performs best with the non-uniform patterns. Superior results are obtained when the two are combined. Based on extensive experiments conducted in several domains using several benchmark databases, it is our conclusion that non-uniform patterns improve classifier performance.