Multidimensional Feature Vector Research Articles

High-dimensional similarity searches using query driven dynamic quantization and distributed indexing.

The concept of similarity is used as the basis for many data exploration and data mining tasks. Nearest neighbor (NN) queries identify the most similar items, or in terms of distance the closest points to a query point. Similarity is traditionally characterized using a distance function between multi-dimensional feature vectors. However, when the data is high-dimensional, traditional distance functions fail to significantly distinguish between the closest and furthest points, as few dissimilar dimensions dominate the distance function. Localized similarity functions, i.e. functions that only consider dimensions close to the query, quantize each dimension independently and only compute similarity for the dimensions where the query and the points fall into the same bin. These quantizations are query-agnostic and there is potential to improve accuracy when a query-dependent quantization is used. In this work we propose a query dependent equi-depth (QED) on-the-fly quantization method to improve high-dimensional similarity searches. The quantization is done for each dimension at query time and localized scores are generated for the closest p fraction of the points while a constant penalty is applied for the rest of the points. QED not only improves the quality of the distancemetric,but also improves query time performance by filtering out non relevant data. We propose a distributed indexing and query algorithm to efficiently compute QED. Our experimental results show improvements in classification accuracy as well as query performance up to one order of magnitude faster than Manhattan-based sequential scan NN queries over datasets with hundreds of dimensions. Furthermore, similarity searches with QED show linear or better scalability in relation to the number of dimensions, and the number of compute nodes.

Saliency-Driven Oil Tank Detection Based on Multidimensional Feature Vector Clustering for SAR Images

A novel saliency-driven oil tank detection method based on multidimensional feature vector clustering (MFVC) is proposed in this letter for synthetic aperture radar (SAR) images. There are three major contributions: 1) a specially designed MFVC method, which is suitable for SAR images without true colors, is employed to detect oil tanks roughly by saliency analysis. Five important complementary features, including intensity, texture, structure, and 2-D coordinates, form a 5-D vector, and then an unsupervised strategy is employed for clustering the 5-D feature vectors to acquire the saliency map; 2) For accurate location, the shape limit coefficient is added to the original active contour model to extract contours of top surfaces; and 3) according to the relations of top, bottom, and the brightest arch, bottoms of oil tanks are computed precisely. Experiments are conducted in two aspects: evaluation for saliency analysis, and for bottom location. Results show that the MFVC method outperforms competing methods in maintaining complete oil tanks and accurate boundaries, and removing the background clutter as much as possible.

Scenario based e-commerce recommendation algorithm based on customer interest in Internet of things environment

With the development of mobile commerce, situational awareness and Internet of things, the boundaries of e-commerce have been greatly expanded, and it has entered a big data era of business information. However, customers are faced with the problem that information is rich but useful information is hard to get. E-commerce is facing the challenge of how to provide personalized information recommendation services for customers and motivate customers to purchase continuously. Therefore, this paper studies the problem of e-commerce recommendation under the condition of large data, and proposes a scenario-based e-commerce recommendation algorithm based on customer interest. Firstly, according to the characteristics of customer interest such as situational sensitivity and diversity in personalized recommendation, a multi-dimensional customer interest feature vector is established by using distributed cognitive theory to differentiate the sensitive scenarios of customer interest. Then, the collaborative filtering recommendation algorithm is used to realize customer similarity judgment and product recommendation in sensitive scenarios. Experimental results show that the method has good customer interest extraction ability. Compared with other recommendation methods, it has higher recommendation accuracy and can adapt to the high-quality commodity recommendation service in the process of customer continuous purchase under complex circumstances.

An Effective Subsuperpixel-Based Approach for Background Subtraction

How to achieve competitive accuracy and less computation time simultaneously for background estimation is still an intractable task. In this paper, an effective background subtraction approach for video sequences is proposed based on a subsuperpixel model. In our algorithm, the superpixels of the first frame are constructed using a simple linear iterative clustering method. After transforming the frame from a color format to gray level, the initial superpixels are divided into K smaller units, i.e., subsuperpixels, via the k -means clustering algorithm. The background model is then initialized by representing each subsuperpixel as a multidimensional feature vector. For the subsequent frames, moving objects are detected by the subsuperpixel representation and a weighting measure. In order to deal with ghost artifacts, a background model updating strategy is devised, based on the number of pixels represented by each cluster center. As each superpixel is refined via the subsuperpixel representation, the proposed method is more efficient and achieves a competitive accuracy for background subtraction. Experimental results demonstrate the effectiveness of the proposed method.

Bearing Fault Diagnosis Based on Subband Time-Frequency Texture Tensor

The texture feature tensor established from a subband time-frequency image (TFI) was extracted and used to identify the fault states of a rolling bearing. The TFI of adaptive optimal-kernel distribution was optimally partitioned into TFI blocks based on the minimum frequency band entropy. The texture features were extracted from the co-occurrence matrix of each TFI block. Based on the order of the segmented frequency bands, the texture feature tensor was constructed using the multidimensional feature vectors from all the blocks; this preserved the inherent characteristic of the TFI structure and avoided the information loss caused by vectorizing multidimensional features. The linear support higher order tensor machine based on the feature tensor was applied to identify the fault states of the rolling bearing.

Deep hashing network for material defect image classification

Common non‐destructive material testing technology has some well‐known problems such as slow detection, low detection accuracy, and low level of information obtained. To solve these problems, this study applied recent advances in convolution neural networks to propose an effective deep learning network using casting datasets. The approach achieves non‐destructive material testing with automatic, intelligent detection technology. For most existing deep learning networks, an image is eventually transformed into a multidimensional visual feature vector for comparison and classification. However, such vectors may not optimally improve detection precision and speed, and can lead to significant storage problems. A deep hashing network is proposed in which images are mapped into compact binary codes. There are three key components: (i) a sub‐network with multiple convolution‐pooling layers to capture image representations; (ii) a hashing layer to generate compact binary hash codes; (iii) an encoder module to divide the image feature vector from the output of the sub‐network above into multiple branches, each encoded into one hash bit. Extensive experiments using a casting dataset show promising performance compared with the state‐of‐the‐art approach.

Locality sensitive hashing based space partitioning approach for indexing multidimensional feature vectors of fingerprint image data

In recent years, biometric applications have significantly gained popularity. Such applications involve voluminous databases of high dimensional data. These enormous databases increase the cost of identification and degrade the system performance. To resolve such an issue a plethora of algorithms based on geometric hashing, k-d tree, k -means clustering, etc., have been proposed in the literature. Although, these algorithms solve a number of concomitant challenges of multi-dimensional data, yet, they fail to present a universal solution. In this study, we propose an indexing mechanism, which partitions the data space effectively into zones and blocks using a set of hash functions. Furthermore, the index locations are divided into maximum nine sub-locations to store data. This helps in carrying out an efficient search of the queried data, thereby minimising the false acceptance and rejection rate. To validate the proposed approach, the mechanism has been applied to the fingerprint verification competition and National Institute of Standards and Technology fingerprint image databases. The experimental results substantiate the efficacy of our approach in terms of accuracy, speed, reduction of search space and the number of comparisons to store and retrieve data.

Seizure onset detection based on frequency domain metric of empirical mode decomposition

This paper explores the data-driven properties of the empirical mode decomposition (EMD) for detection of epileptic seizures. A new method in frequency domain is presented to analyze intrinsic mode functions (IMFs) decomposed by EMD. They are used to determine whether the electroencephalogram (EEG) recordings contain seizure or not. Energy levels of the IMFs are extracted as threshold level to detect the changes caused by seizure activity. A scalar value energy resulting from the energy levels is individually used as an indicator of the epileptic EEG without the requirements of multidimensional feature vector and complex machine learning algorithms. The proposed methods are tested on different EEG recordings to evaluate the effectiveness of the proposed method and yield accuracy rate up to 97.89%.

Improving rolling bearing online fault diagnostic performance based on multi-dimensional characteristics.

As the main cause of failure and damage to rotating machinery, rolling bearing failure can result in huge economic losses. As the rolling bearing vibration signal is nonlinear and has non-stationary characteristics, the health status information distributed in the rolling bearing vibration signal is complex. Using common time-domain or frequency-domain approaches cannot easily enable an accurate assessment of rolling bearing health. In this paper, a novel rolling bearing fault diagnostic method based on multi-dimensional characteristics was developed to meet the requirements for accurate diagnosis of different fault types and severities with real-time computational performance. First, a multi-dimensional feature extraction algorithm based on entropy characteristics, Holder coefficient characteristics and improved generalized fractal box-counting dimension characteristics was performed to extract the health status feature vectors from the bearing vibration signals. Second, a grey relation algorithm was employed to achieve bearing fault pattern recognition intelligently using the extracted multi-dimensional feature vector. This experimental study has illustrated that the proposed method can effectively recognize different fault types and severities after integration of the improved fractal box-counting dimension into the multi-dimensional characteristics, in comparison with existing pattern recognition methods.

VIDEO FOREGERY DEDUCTION OF INTERFRAME DUPLICATION

Video forgery detection aims to distinguish video forgeries from original videos. Video forgery detection in the form of features extraction from clustering the frames and matched with original videos. Scale Invariant Feature Transform (SIFT) are improved for detection of copy move attacks. Image keypoints are extracted and multi-dimensional feature vector named as SIFT descriptor is generated for each keypoint. Then, these keypoints are matched using distance among their descriptors. The experimental results show that our proposed algorithm has good at detection of copy move attacks. Total percentage of forged identify which frame to be forged and designed application as window based application with image processing techniques.

A computer vision-based system for monitoring Vojta therapy

A neurological illness is t he disorder in human nervous system that can result in various diseases including the motor disabilities. Neurological disorders may affect the motor neurons, which are associated with skeletal muscles and control the body movement. Consequently, they introduce some diseases in the human e.g. cerebral palsy, spinal scoliosis, peripheral paralysis of arms/legs, hip joint dysplasia and various myopathies. Vojta therapy is considered a useful technique to treat the motor disabilities. In Vojta therapy, a specific stimulation is given to the patient's body to perform certain reflexive pattern movements which the patient is unable to perform in a normal manner. The repetition of stimulation ultimately brings forth the previously blocked connections between the spinal cord and the brain. After few therapy sessions, the patient can perform these movements without external stimulation. In this paper, we propose a computer vision-based system to monitor the correct movements of the patient during the therapy treatment using the RGBD data. The proposed framework works in three steps. In the first step, patient's body is automatically detected and segmented and two novel techniques are proposed for this purpose. In the second step, a multi-dimensional feature vector is computed to define various movements of patient's body during the therapy. In the final step, a multi-class support vector machine is used to classify these movements. The experimental evaluation carried out on the large captured dataset shows that the proposed system is highly useful in monitoring the patient's body movements during Vojta therapy.

Clustering short temporal behaviour sequences for customer segmentation using LDA

AbstractCustomer segmentation based on temporal variation of subscriber preferences is useful for communication service providers (CSPs) in applications such as targeted campaign design, churn prediction, and fraud detection. Traditional clustering algorithms are inadequate in this context, as a multidimensional feature vector represents a subscriber profile at an instant of time, and grouping of subscribers needs to consider variation of subscriber preferences across time. Clustering in this case usually requires complex multivariate time series analysis‐based models. Because conventional time series clustering models have limitations around scalability and ability to accurately represent temporal behaviour sequences (TBS) of users, that may be short, noisy, and non‐stationary, we propose a latent Dirichlet allocation (LDA) based model to represent temporal behaviour of mobile subscribers as compact and interpretable profiles. Our model makes use of the structural regularity within the observable data corresponding to a large number of user profiles and relaxes the strict temporal ordering of user preferences in TBS clustering. We use mean‐shift clustering to segment subscribers based on their discovered profiles. Further, we mine segment‐specific association rules from the discovered TBS clusters, to aid marketers in designing intelligent campaigns that match segment preferences. Our experiments on real world data collected from a popular Asian communication service provider gave encouraging results.

Multi-class recognition of objects technical condition by classifier based on probabilistic neural network

The paper deals with the efficiency study of the classifier developed based on the probabilistic neural network for multi-class diagnostics of a complex spatial object in the presence of multi-site damage. For recognition, the multidimensional diagnostic feature vector is used, the values of the features may have a deviation of ±5 % for the defect-free condition of an object, and exceed the permissible deviation in case of occurrence and development of damage. For the vector containing 5 diagnostic features, 6 classes of technical condition of an object are substantiated. Formation of sets of training and test input vectors, used for the classifier training and testing is performed. In order to evaluate the multi-class recognition efficiency, the coefficient, which is a percentage of the probability of correct classification of test vectors, is used. The analysis of the dependence of the efficiency coefficient on the characteristics of the classifier and the set of training vectors is carried out. It is found that error-free multi-class recognition of the object condition over the entire set of input vectors with different values of deviation of feature elements is provided in the range of values of the classifier parameter spread of [0,02; 0.07]. It is revealed that the greater the diagnostic feature deviation in test vectors, the greater the influence of the dimension of the set of training vectors on the multi-class recognition efficiency. The minimum size of the set of training vectors (68 vectors) and the limit value of diagnostic feature deviation in test vectors (17 %), which provide error-free multi-class recognition by the developed classifier are determined.

Thalamus segmentation using multi-modal feature classification: Validation and pilot study of an age-matched cohort

Automatic segmentation of the thalamus can be used to measure differences and track changes in thalamic volume that may occur due to disease, injury or normal aging. An automatic thalamus segmentation algorithm incorporating features from diffusion tensor imaging (DTI) and thalamus priors constructed from multiple atlases is proposed. Multiple atlases with corresponding manual thalamus segmentations are registered to the target image and averaged to generate the thalamus prior. At each voxel in a region of interest around the thalamus, a multidimensional feature vector that includes the thalamus prior as well as a set of DTI features, including fractional anisotropy, mean diffusivity, and fiber orientation is formed. A random forest is trained to classify each voxel as belonging to the thalamus or background within the region of interest. Using a leave-one-out cross-validation on nine subjects, the proposed algorithm achieves a mean Dice score of 0.878 and 0.890 for the left and right thalami, respectively, which are higher Dice scores than the three state-of-art methods we compared to. We demonstrate the utility of the method with a pilot study exploring the difference in the thalamus fraction between 21 multiple sclerosis (MS) patients and 21 age-matched healthy controls. The left and right thalamic volumes (normalized by intracranial volumes) are larger in healthy controls by 7.6% and 7.3% respectively, compared to MS patients (though neither result is statistically significant).

A Study and usage of Visual Features in Content Based Image Retrieval Systems

Image retrieval is a prominent area of digital image processing. Images can be retrieved from a large collection of databaseimages on the basis of text, color and structure. Content-based image retrieval uses the visual content ofimages such as color, shape, texture and spatial layout for representing and indexing the images. In a typical CBIR system, thevisual content of the images in the database are extracted and displayed by multi-dimensional feature vectors. Thefeature vector of the images in the database is a feature database. To retrieve the images, users provide theretrieval system with query images. The system then changes query into its internal representation offeature vectors for both query and database images .In this paper we present introduction and literaturereview on various content based image retrieval techniques.

Statistical appearance models based on probabilistic correspondences.

Model-based image analysis is indispensable in medical image processing. One key aspect of building statistical shape and appearance models is the determination of one-to-one correspondences in the training data set. At the same time, the identification of these correspondences is the most challenging part of such methods. In our earlier work, we developed an alternative method using correspondence probabilities instead of exact one-to-one correspondences for a statistical shape model(Hufnagel etal., 2008). In this work, a new approach for statistical appearance models without one-to-one correspondences is proposed. A sparse image representation is used to build a model that combines point position and appearance information at the same time. Probabilistic correspondences between the derived multi-dimensional feature vectors are used to omit the need for extensive preprocessing of finding landmarks and correspondences as well as to reduce the dependence of the generated model on the landmark positions. Model generation and model fitting can now be expressed by optimizing a single global criterion derived from a maximum a-posteriori (MAP) approach with respect to model parameters that directly affect both shape and appearance of the considered objects inside the images. The proposed approach describes statistical appearance modeling in a concise and flexible mathematical framework. Besides eliminating the demand for costly correspondence determination, the method allows for additional constraints as topological regularity in the modeling process. In the evaluation the model was applied for segmentation and landmark identification in hand X-ray images. The results demonstrate the feasibility of the model to detect hand contours as well as the positions of the joints between finger bones for unseen test images. Further, we evaluated the model on brain data of stroke patients to show the ability of the proposed model to handle partially corrupted data and to demonstrate a possible employment of the correspondence probabilities to indicate these corrupted/pathological areas.

An optimised multidimensional feature vector for automatic tumour detection and retrieving similar images for diagnosing clinically

High speed advancements in the medical technology are revolutionising the medication. The usage of Computer-Aided Diagnosis (CAD) systems plays a potential role in improving the quality of clinical radiotherapy care. The tumours are fatal in nature and may invade the other parts of the body. Precise diagnosis is essential for accurate treatment of the tumour. In that direction to make easy access in the future all medical images are registered in a medical image database. Content-Based Medical Image Retrieval (CBMIR) techniques attract greater interest to facilitate medical fields in retrieving the interested medical images. Consequently, based on this, we propose an intellectual three-step CBMIR system which retrieves corresponding images from a large medical database to support the radiologist in the diagnosis tumour images. The initial step detects the tumour in the image. Based on this information it retrieves the nearby similar images within the pre-classified database with the optimised futures. In the final step, the performance of the retrieval system is enhanced by adapting the subjective feedback method. The experimental results show that the proposed region-based multiple features and integrated with classifier and subjective feedback method yield better results than classical retrieval systems.

An optimised multidimensional feature vector for automatic tumour detection and retrieving similar images for diagnosing clinically

High speed advancements in the medical technology are revolutionising the medication. The usage of Computer-Aided Diagnosis (CAD) systems plays a potential role in improving the quality of clinical radiotherapy care. The tumours are fatal in nature and may invade the other parts of the body. Precise diagnosis is essential for accurate treatment of the tumour. In that direction to make easy access in the future all medical images are registered in a medical image database. Content-Based Medical Image Retrieval (CBMIR) techniques attract greater interest to facilitate medical fields in retrieving the interested medical images. Consequently, based on this, we propose an intellectual three-step CBMIR system which retrieves corresponding images from a large medical database to support the radiologist in the diagnosis tumour images. The initial step detects the tumour in the image. Based on this information it retrieves the nearby similar images within the pre-classified database with the optimised futures. In the final step, the performance of the retrieval system is enhanced by adapting the subjective feedback method. The experimental results show that the proposed region-based multiple features and integrated with classifier and subjective feedback method yield better results than classical retrieval systems.

Combining SURF and MSER along with Color Features for Image Retrieval System Based on Bag of Visual Words

Content-Based Image Retrieval (CBIR) has received an extensive attention from researchers due to the rapid growing and widespread of image databases. Despite the massive research efforts consumed for CBIR, the completely satisfactory results have not yet been attained. In this article, we offer a new CBIR technique that relies on extracting Speeded Up Robust Features (SURF) and Maximally Stable Extremal Regions (MSER) feature descriptors as well as the color features; color correlograms and Improved Color Coherence Vector (ICCV). These features are joined and used to build a multidimensional feature vector. Bag-of-Visual-Words (BoVW) technique is utilized to quantize the extracted feature vector. Then, a multiclass Support Vector Machine (SVM) is implemented to classify the query images. The performance of the presented retrieval framework is analyzed and scrutinized by comparing it with three alternative approaches. The first one is based on extracting SURF descriptors while the second one is based on extracting SURF descriptors, color correlograms and ICCV. The third approach, on the other hand, is based on extracting MSER, color correlograms and ICCV. All implemented schemes are tested on two benchmark datasets; Corel-1000 and COIL-100 datasets. The empirical results show that our suggested approach has a superior discriminative classification and retrieval performance with respect to other approaches. The proposed method achieves average precisions of 88 and 93% for the Corel-1000 and COIL-100 datasets, respectively. Moreover, the proposed system has shown a substantial advance in the retrieval precision when compared with other existing systems.

Im2Fit: Fast 3D Model Fitting and Anthropometrics using Single Consumer Depth Camera and Synthetic Data

Recent advances in consumer depth sensors have created many opportunities for human body measurement and modeling. Estimation of 3D body shape is particularly useful for fashion e-commerce applications such as virtual try-on or fit personalization. In this paper, we propose a method for capturing accurate human body shape and anthropometrics from a single consumer grade depth sensor. We first generate a large dataset of synthetic 3D human body models using real-world body size distributions. Next, we estimate key body measurements from a single monocular depth image. We combine body measurement estimates with local geometry features around key joint positions to form a robust multi-dimensional feature vector. This allows us to conduct a fast nearest-neighbor search to every sample in the dataset and return the closest one. Compared to existing methods, our approach is able to predict accurate full body parameters from a partial view using measurement parameters learned from the synthetic dataset. Furthermore, our system is capable of generating 3D human mesh models in real-time, which is significantly faster than methods which attempt to model shape and pose deformations. To validate the efficiency and applicability of our system, we collected a dataset that contains frontal and back scans of 83 clothed people with ground truth height and weight. Experiments on real-world dataset show that the proposed method can achieve real-time performance with competing results achieving an average error of 1.9 cm in estimated measurements.