Bag Of Features Research Articles

Utilising Information of the Case Fee Catalogue to Enhance 30-Day Readmission Prediction in the German DRG System.

Unplanned hospital readmissions are a burden to the healthcare system and to the patients. To lower the readmission rates, machine learning approaches can be used to create predictive models, with the intention to provide actionable information for caregivers. According to the German Diagnosis Related Groups (G-DRG) system, for every stay in a German hospital, data are collected for the subsequent reimbursement calculations. After statistical evaluation, these data are summarised in the yearly updated Case Fee Catalogue, which not only contains the weights for the reimbursement calculations, but also the expected length of stay values. The aim of the present paper was to evaluate potential enhancements of the prediction accuracy of our 30-day readmission prediction model by utilising additional information from the Case Fee Catalogue. A bagged ensemble of 25 regression trees was applied to §21 datasets from five independent German hospitals from 2013 to 2017, resulting in 422,597 cases. The overall model showed an area under the receiver operating characteristics curve of 0.812. Three of the top five features ranked by out of bag feature importance emerged from the Case Fee Catalogue. We conclude, that additional information from the Case Fee Catalogue can enhance the accuracy of 30-day readmission prediction.

A novel method for differentiating and clustering multiple partial discharge sources using S transform and bag of words feature

Transformers are known as one of the most important equipment in power system transmission and distribution networks. Partial Discharge (PD) measurement and PRPD interpretation is a powerful tool to monitor the situation and evaluating the risk of power transformer failure. Multiple discharge sources affect the accuracy of interpretation of PRPD. This paper presents a PD signal separation algorithm based on extraction of high level image features. The time-frequency S transform (ST) is applied to the PD signal waveforms, acquired by digital detection instruments at 100 MS/s. The resultant ST matrix is then converted to gray scale image from which high level features are extracted using Bag of Words (BoW). Principle component analysis (PCA) transform is applied to BoW feature to reduce the dimension of features. Calinski-Harabasz criterion is calculated to identify the number of active sources and then Gaussian mixture model (GMM) clustering is used to discover clusters in the feature space. The proposed separation algorithm is examined with mixed current impulse signals acquired from PD experiments on artificial multi-defect models. The separation results indicate that the proposed algorithm is effective for identifying the number of active sources and separating mixed PD signals initiated from multiple sources.

BoCNF: efficient image matching with Bag of ConvNet features for scalable and robust visual place recognition

Recent advances in visual place recognition (VPR) have exploited ConvNet features to improve the recognition accuracy under significant environmental and viewpoint changes. However, it remains unsolved how to implement efficient image matching with high dimensional ConvNet features. In this paper, we tackle the problem of matching efficiency using ConvNet features for VPR, where the task is to accurately and quickly recognize a given place in large-scale challenging environments. The paper makes two contributions. First, we propose an efficient solution to VPR, based on the well-known bag-of-words (BoW) framework, to speed up image matching with ConvNet features. Second, in order to alleviate the problem of perceptual aliasing in BoW, we adopt a coarse-to-fine approach where we first, in the coarse stage, search for the top-K candidate images via BoW and then, in the fine stage, identify the best match among the candidates using a hash-based voting scheme. We conduct extensive experiments on six popular VPR datasets to validate the effectiveness of our method. Experimental results show that, in terms of recognition accuracy, our method is comparable to linear search, and outperforms other methods such as FABMAP and SeqSLAM by a significant margin. In terms of efficiecy, our method achieves a significant speed-up over linear search, with an average matching time as low as 23.5 ms per query on a dataset with 21K images.

Remote Sensing Image Scene Classification Using Bag of Convolutional Features

More recently, remote sensing image classification has been moving from pixel-level interpretation to scene-level semantic understanding, which aims to label each scene image with a specific semantic class. While significant efforts have been made in developing various methods for remote sensing image scene classification, most of them rely on handcrafted features. In this letter, we propose a novel feature representation method for scene classification, named bag of convolutional features (BoCF). Different from the traditional bag of visual words-based methods in which the visual words are usually obtained by using handcrafted feature descriptors, the proposed BoCF generates visual words from deep convolutional features using off-the-shelf convolutional neural networks. Extensive evaluations on a publicly available remote sensing image scene classification benchmark and comparison with the state-of-the-art methods demonstrate the effectiveness of the proposed BoCF method for remote sensing image scene classification.

Scale coding bag of deep features for human attribute and action recognition

Most approaches to human attribute and action recognition in still images are based on image representation in which multi-scale local features are pooled across scale into a single, scale-invariant encoding. Both in bag-of-words and the recently popular representations based on convolutional neural networks, local features are computed at multiple scales. However, these multi-scale convolutional features are pooled into a single scale-invariant representation. We argue that entirely scale-invariant image representations are sub-optimal and investigate approaches to scale coding within a bag of deep features framework. Our approach encodes multi-scale information explicitly during the image encoding stage. We propose two strategies to encode multi-scale information explicitly in the final image representation. We validate our two scale coding techniques on five datasets: Willow, PASCAL VOC 2010, PASCAL VOC 2012, Stanford-40 and Human Attributes (HAT-27). On all datasets, the proposed scale coding approaches outperform both the scale-invariant method and the standard deep features of the same network. Further, combining our scale coding approaches with standard deep features leads to consistent improvement over the state of the art.

A discriminative algorithm for indoor place recognition based on clustering of features and images

In order to solve the problem of indoor place recognition for indoor service robot, a novel algorithm, clustering of features and images (CFI), is proposed in this work. Different from traditional indoor place recognition methods which are based on kernels or bag of features, with large margin classifier, CFI proposed in this work is based on feature matching, image similarity and clustering of features and images. It establishes independent local feature clusters by feature cloud registration to represent each room, and defines image distance to describe the similarity between images or feature clusters, which determines the label of query images. Besides, it improves recognition speed by image scaling, with state inertia and hidden Markov model constraining the transition of the state to kill unreasonable wrong recognitions and achieves remarkable precision and speed. A series of experiments are conducted to test the algorithm based on standard databases, and it achieves recognition rate up to 97% and speed is over 30 fps, which is much superior to traditional methods. Its impressive precision and speed demonstrate the great discriminative power in the face of complicated environment.

Fault diagnosis for rotary machinery with selective ensemble neural networks

Abstract The diagnosis of rotary machinery systems is gaining interest both in academic and industry fields, which assures machinery operational safety and reliability in terms of typical rotary machinery components such as bearings and gears. With a view to gain better generalization ability of fault diagnosis along with multiple monitored variables with corresponding fault patterns, a novel fault diagnosis method (particle swarm optimization based selective ensemble learning, PSOSEN) that utilizes ensemble learning with differentiated probabilistic neural networks (PNNs) is proposed, where nonlinear decreasing inertia weight based adaptive particle swarm optimization (APSO) is employed to effectively reinforce the learning process by selecting superior individuals for integration instead of all. First, statistical features in the time domain and frequency domain are extracted and integrated from vibration signals, and feature selection based on bagging feature representation is applied to generate desirable PNNs. Second, APSO is used to improve the performance by balancing diversity and accuracy, aiming to eliminate similar individuals via weight assignation and retain the classifiers with better performance in the initial iteration. The globe-best vectors are then, by means of linear transformation, mapped into a matching matrix in which row vectors indicate the corresponding weights of the selected classifiers. Singular value decomposition (SVD) is employed on the established matrix, where an optimal weight vector is thus obtained according to the orthogonal matrices parameters. The fault diagnosis result is finally achieved by ensemble computing of PNNs based on the calculated weight coefficients. Comparative experiments are included in this paper to demonstrate the effectiveness in fault diagnosis of rotary machinery including varying working conditions and different severe degrees.

Vehicle Recognition Based on Local Feature

This paper introduced a vehicle recognition system based on Speed-up Robust Feature (SURF) and bag-of-features (BOF). In the system, we extract SURF features of vehicle images, and use k-means algorithm to analyze the features, clustering center of the features, so we can get some “visual words”. Then we describe all images use those “words”, and generate histogram to quantize the features. In this paper, term frequency- inverse document frequency (tf-idf) is used to weight the features to weaken the influence of useless features. We have 22 different type and brand of vehicle, including sedan, SUV, bus and so on. The experiment shows that this way can make the recognition accuracy over 90%.

Scene Classification Using Multi-Resolution WAHOLB Features and Neural Network Classifier

This article approaches scene classification problem by proposing an enhanced bag of features (BoF) model and a modified radial basis function neural network (RBFNN) classifier. The proposed BoF model integrates the image features extracted by histogram of oriented gradients, local binary pattern and wavelet coefficients. The extracted features are obtained in a hierarchical multi-resolution manner. The proposed approach is able to capture multi-level (the pixel-, patch-, and image-level) features. The histograms of features constructed by BoF model are then used for training a modified RBFNN classifier. As a modification, we propose using a new variant of particle swarm optimization, in which the parameters are updated adaptively, for determining the center of Gaussian functions in RBFNN. Experimental results demonstrate that our proposed approach significantly outperforms the state-of-the-art methods on scene classification of OT, FP, and LSP benchmark datasets.

Multi-layer multi-view topic model for classifying advertising video

The recent proliferation of advertising (ad) videos has driven the research in multiple applications, ranging from video analysis to video indexing and retrieval. Among them, classifying ad video is a key task because it allows automatic organization of videos according to categories or genres, and this further enables ad video indexing and retrieval. However, classifying ad video is challenging compared to other types of video classification because of its unconstrained content. While many studies focus on embedding ads relevant to videos, to our knowledge, few focus on ad video classification. In order to classify ad video, this paper proposes a novel ad video representation that aims to sufficiently capture the latent semantics of video content from multiple views in an unsupervised manner. In particular, we represent ad videos from four views, including bag-of-feature (BOF), vector of locally aggregated descriptors (VLAD), fisher vector (FV) and object bank (OB). We then devise a multi-layer multi-view topic model, mlmv_LDA, which models the topics of videos from different views. A topical representation for video, supporting category-related task, is finally achieved by the proposed method. Our empirical classification results on 10,111 real-world ad videos demonstrate that the proposed approach effectively differentiate ad videos.

Image classification for detection of winter grapevine buds in natural conditions using scale-invariant features transform, bag of features and support vector machines

In viticulture, there are several applications where bud detection in vineyard images is a necessary task, susceptible of being automated through the use of computer vision methods. A common and effective family of visual detection algorithms are the scanning-window type, that slide a (usually) fixed size window along the original image, classifying each resulting windowed-patch as containing or not containing the target object. The simplicity of these algorithms finds its most challenging aspect in the classification stage. Interested in grapevine buds detection in natural field conditions, this paper presents a classification method for images of grapevine buds ranging 100–1600 pixels in diameter, captured in outdoor, under natural field conditions, in winter (i.e., no grape bunches, very few leaves, and dormant buds), without artificial background, and with minimum equipment requirements. The proposed method uses well-known computer vision technologies: Scale-Invariant Feature Transform for calculating low-level features, Bag of Features for building an image descriptor, and Support Vector Machines for training a classifier. When evaluated over images containing buds of at least 100 pixels in diameter, the approach achieves a recall higher than 0.9 and a precision of 0.86 over all windowed-patches covering the whole bud and down to 60% of it, and scaled up to window patches containing a proportion of 20–80% of bud versus background pixels. This robustness on the position and size of the window demonstrates its viability for use as the classification stage in a scanning-window detection algorithms.

Bag-of-Feature model for sweet and bitter almond classification

The use of computer vision techniques in post-harvest processing of agricultural products has increased considerably in recent years due to their non-destructive and rapid monitoring abilities. Image processing, combined with pattern recognition, has been applied in fruit sorting and classification. In this study, a Bag-of-Feature (BoF) model is used for the classification of 20 sweet and bitter almond varieties. Harris, Harris–Laplace, Hessian, Hessian–Laplace and Maximally Stable Extremal Regions (MSER) keypoint detectors along with a Scale Invariant Feature Transform (SIFT) descriptor are used in the BoF model. The k-means clustering method is applied for building a codebook from keypoint descriptors. The performance of 3 classifiers, which were k-Nearest Neighbour (k-NN), linear and chi-square Support Vector Machine (L-SVM and Chi-SVM, respectively) were compared using classification results in the model. It was observed that the Chi-SVM classifier outperformed the k-NN and L-SVM classifiers. Using the BoF model, it was possible to detect and classify sweet and bitter varieties with high overall accuracy.

Perceptual quality prediction on authentically distorted images using a bag of features approach.

Current top-performing blind perceptual image quality prediction models are generally trained on legacy databases of human quality opinion scores on synthetically distorted images. Therefore, they learn image features that effectively predict human visual quality judgments of inauthentic and usually isolated (single) distortions. However, real-world images usually contain complex composite mixtures of multiple distortions. We study the perceptually relevant natural scene statistics of such authentically distorted images in different color spaces and transform domains. We propose a “bag of feature maps” approach that avoids assumptions about the type of distortion(s) contained in an image and instead focuses on capturing consistencies—or departures therefrom—of the statistics of real-world images. Using a large database of authentically distorted images, human opinions of them, and bags of features computed on them, we train a regressor to conduct image quality prediction. We demonstrate the competence of the features toward improving automatic perceptual quality prediction by testing a learned algorithm using them on a benchmark legacy database as well as on a newly introduced distortion-realistic resource called the LIVE In the Wild Image Quality Challenge Database. We extensively evaluate the perceptual quality prediction model and algorithm and show that it is able to achieve good-quality prediction power that is better than other leading models.

Realistic action recognition with salient foreground trajectories

Human action recognition has great potential in many applications relevant to artificial intelligence, which can accelerate some research on expert and intelligent systems, such as feature selection. To improve the performance on human action recognition in realistic scenarios, a novel Salient Foreground Trajectory extraction method based on saliency detection and low-rank matrix recovery is proposed to learn the discriminative features from complicated video context. Specifically, a new trajectory saliency combining appearance saliency and motion saliency is proposed to divide the dense trajectories into salient trajectories and non-salient ones. The salient trajectories are approximately corresponding to the interested foreground region, while the non-salient subset is mainly composed of the dominating background trajectories. Furthermore, according to the low rank property of background motion, if the video has background motion, the background trajectory subspace is further constructed on the non-salient trajectory subset via low-rank matrix recovery method. Then the possible background trajectories in the salient subset could be subtracted. Finally, the resulting salient foreground trajectory features are encoded by the approach of Bag of Features or Fisher Vector for action classification. Experiments on KTH, UCF Sports and Olympic Sports have shown that the proposed Salient Foreground Trajectory method is effective and achieves comparable results to the state of the art.

A Dataset and Benchmarks for Segmentation and Recognition of Gestures in Robotic Surgery.

State-of-the-art techniques for surgical data analysis report promising results for automated skill assessment and action recognition. The contributions of many of these techniques, however, are limited to study-specific data and validation metrics, making assessment of progress across the field extremely challenging. In this paper, we address two major problems for surgical data analysis: First, lack of uniform-shared datasets and benchmarks, and second, lack of consistent validation processes. We address the former by presenting the JHU-ISI Gesture and Skill Assessment Working Set (JIGSAWS), a public dataset that we have created to support comparative research benchmarking. JIGSAWS contains synchronized video and kinematic data from multiple performances of robotic surgical tasks by operators of varying skill. We address the latter by presenting a well-documented evaluation methodology and reporting results for six techniques for automated segmentation and classification of time-series data on JIGSAWS. These techniques comprise four temporal approaches for joint segmentation and classification: hidden Markov model, sparse hidden Markov model (HMM), Markov semi-Markov conditional random field, and skip-chain conditional random field; and two feature-based ones that aim to classify fixed segments: bag of spatiotemporal features and linear dynamical systems. Most methods recognize gesture activities with approximately 80% overall accuracy under both leave-one-super-trial-out and leave-one-user-out cross-validation settings. Current methods show promising results on this shared dataset, but room for significant progress remains, particularly for consistent prediction of gesture activities across different surgeons. The results reported in this paper provide the first systematic and uniform evaluation of surgical activity recognition techniques on the benchmark database.

An Analysis of Machine- and Human-Analytics in Classification.

In this work, we present a study that traces the technical and cognitive processes in two visual analytics applications to a common theoretic model of soft knowledge that may be added into a visual analytics process for constructing a decision-tree model. Both case studies involved the development of classification models based on the "bag of features" approach. Both compared a visual analytics approach using parallel coordinates with a machine-learning approach using information theory. Both found that the visual analytics approach had some advantages over the machine learning approach, especially when sparse datasets were used as the ground truth. We examine various possible factors that may have contributed to such advantages, and collect empirical evidence for supporting the observation and reasoning of these factors. We propose an information-theoretic model as a common theoretic basis to explain the phenomena exhibited in these two case studies. Together we provide interconnected empirical and theoretical evidence to support the usefulness of visual analytics.

Computer Aided Segmentation of Breast Ultrasound Images Using Scale Invariant Feature Transform (SIFT) and Bag Of Features

Automatic and precise segmentation of breast ultrasound (BUS) image is a challenging task. The proposed method successfully implemented a segmentation algorithm by region growing from a seed point based on texture features generated by Gray Level Co-occurrence Matrix (GLCM). The seed points generated by canny edge detection and wavelet modulus maxima methods are refined by Support Vector Machine (SVM) trained by Scale Invariant Feature Transform (SIFT). The segmented images are compared with ground truth images and True Positive Rate (TPR) of 90.1% and average SI (Similarity Index) of 0.85 demonstrates that the proposed method can segment the tumor regions efficiently and accurately.

Image retrieval using a scale-invariant feature transform bag-of-features model with salient object detection

How to effectively retrieve digital images is a focus of image retrieval research. Developed in the 1990s, content-based image retrieval (CBIR) systems are used to extract low-level visual features. However, semantic gaps exist between these features and high-level semantic concepts. This study proposes an image retrieval solution based on a bag-of-features (BoF) model integrated with scale-invariant feature transform (SIFT) and salient object detection. An image search system based on this image retrieval solution, which used object images as the query image, was subsequently constructed. Overall, the results verify the feasibility of the object-based image retrieval solution. Finally, the enhanced image search method and precision enabled constructing an image search system. The system is expected to improve through the search pattern, as well as improve the accuracy of images search, images search system to make a real attempt to solve the huge amount of data and images search difficult problems arising.

CODM: an outlier detection method for medical insurance claims fraud

Data is the high dimensional in medical insurance claims management, and there are both dense and sparse regions in these datasets, so traditional outlier detection methods are not suitable for these data. In this paper, we propose a novel method to detect the outliers for abnormal medical insurance claims. Our method consists of three core steps - feature bagging to reduce the dimensions of data, calculating the core of the object's k-nearest neighbours, and computing the outlier score for each object by measuring the amount of movement of core by sequentially increasing k. Experimental results demonstrate our method is promising to tackle this problem.

RGBD Co-saliency Detection via Bagging-Based Clustering

With the additional depth information, RGBD co-saliency detection, which is an emerging and interesting issue in saliency detection, aims to discover the common salient objects in a set of RGBD images. This letter proposes a novel RGBD co-saliency model using bagging-based clustering. First, candidate object regions are generated based on RGBD single saliency maps and region pre-segmentation. Then, in order to make regional clustering more robust to different image sets, the feature bagging method is introduced to randomly generate multiple clustering results and the cluster-level weak co-saliency maps. Finally, a clustering quality (CQ) criterion is devised to adaptively integrate the weak co-saliency maps into the final co-saliency map for each image. Experimental results on a public RGBD co-saliency dataset show that the proposed co-saliency model significantly outperforms the state-of-the-art co-saliency models.