Novel Method For Recognition Research Articles

P128. Holographic superimposition of spine model

<h3>BACKGROUND CONTEXT</h3> The current surgical practices are undergoing evolutionary adoption of mixed reality-based technologies. Augmented reality (AR) comes into the field as a possible way of augmentation of the real anatomical structure during surgery without any attention drift of the surgeon. Operative error is a major concern during complex surgical procedures and disruption of the surgeon's attention potentiates toward it. Pedicle screw placement procedure in surgical fusion surgery is a complex procedure in nature and current conventional practices disrupt surgeons' attention. Implementation of head-mounted display based augmented reality platform, HoloLens, into the procedure increases the accuracy of fixation of pedicle screw where it depends on the use of the conventional method of recognition of the target object and of projection of holographic images into the surgeon's operative field which limits the required dynamic and interactive nature of the procedure. <h3>PURPOSE</h3> This paper aims to develop and validate a novel method of recognition of the target object and overlaying hologram into the target object of the field of spine surgery procedure with respecting the spatial relationship of the geometry of a reference tool in the surgical field. There are two tasks to achieve this objective. First, the development of a novel method of holographic projection for spinal surgery. Second, to examine the accuracy of the projection of the hologram into the target object with or without movement of the target spine model and patient reference model. <h3>STUDY DESIGN/SETTING</h3> The study has been divided into 1) development and 2) validation arms. The holographic model has been built with Unity Editor, Mixed Reality Tool Kit, and C# programming languages to define the behavior of the model. The target structure of the complex geometry of the spine model and the patient reference model has been designed and integrated into the game engine. The holographic behavior of both models has been designed with the script based on C# programming languages. The experiment has been designed to test the accuracy of the holographic superimposition. So, it has been experimented in laboratory benchwork condition. <h3>OUTCOME MEASURES</h3> The model will recognize the target patient reference model for spine surgery. <h3>METHODS</h3> The experiment has been conducted to test the target position of anatomical landmark structures with the help of virtually calibrated softwares. The mixed reality captures of the recognition of patient reference model has been taken and analyzed with IC Measure 2 software. <h3>RESULTS</h3> The HoloLens recognizes and projects holograms into the complex spinal geometry maintaining the spatial relationship of the simple geometry of the patient reference model with or without movement. It limits the maximum positional error at 1.31 +/- 3.57 mm, the form error rate at 0.022 mm +/- 0.17 mm and rotational error at0.89°+/- 1.65° without any statistically significant differences of error rate among all the axes. <h3>CONCLUSIONS</h3> This study has established a novel model to create a holographic projection of complex geometry and stabilization of the hologram with the dynamic procedure. So, this novel model would create the first way of dynamic augmentation of interactive surgical guidance system into the operative field of spine surgery procedure even in the spaces. <h3>FDA DEVICE/DRUG STATUS</h3> This abstract does not discuss or include any applicable devices or drugs.

Quantitative Nondestructive Testing of Broken Wires for Wire Rope Based on Magnetic and Infrared Information

The lifetime of wire rope is crucial in industry manufacturing, mining, and so on. The damage can be detected by using appropriate nondestructive testing techniques or destructive tests by cutting the part. For broken wires classification problems, this work is aimed at improving the recognition accuracy. Facing the defects at the exterior of the rope, a novel method for recognition of broken wires is firstly developed based on magnetic and infrared information fusion. A denoising method, which is adopted for magnetic signal, is proposed for eliminating baseline signal and wave strand. An image segmentation method is employed for parting the defects of infrared images. Characteristic vectors are extracted from magnetic images and infrared images, then kernel extreme learning machine network is applied to implement recognition of broken wires. Experimental results show that the denoising method and image segmentation are effective and the information fusion can improve the classification accuracy, which can provide useful information for estimating the residual lifetime of wire rope.

Recognition of Planar Object in Stack via Local Prediction Consistency

A novel method for recognition of planar object in stack via local prediction consistency is proposed in this paper. By checking the consistency of local predictions, an object can be recognized and located. The prediction method by local features under uncertain scale is emphatically discussed. According to the distribution prior for local predictions, the similarity scale can be determined and the consistent local predictions can be composited. A great number of experiments are carried out to prove the stability of this method.

Classification of wolfberry from different geographical origins by using electronic tongue and deep learning algorithm

Wolfberry is a traditional Chinese food. Its price and function are closely related to its geographical origin. Illegal labeling driven by commercial interests has brought serious food safety problems and damaged consumer confidence. In this study, a voltammetric electronic tongue (VE-tongue) combined with deep learning algorithm was developed to perform recognize of different origins of wolfberry samples. Training of deep learning model (Convolutional Neural Network, CNN) was performed with 260 wolfberry samples which were from 4 different geographical origins samples. To find the best performance CNN model, learning rate, optimizer and minibatch size were modified. The best classification accuracy of CNN was further compared with traditional machine learning method— BPNN with discrete wavelet transform (DWT) as feature extraction method. The classification accuracy of CNN, DWT-BPNN and BPNN are 98.27%, 88.46% and 48.08% respectively. This study provides a novel method for recognition and classification of wolfberry from different geographical origins, which holds great promise for its wide applications in geographical origin traceability for agricultural products.

Recognition of web users with the aid of biometric user model

Methods aimed at recognition of users are able to identify browsers or machines, but cannot distinguish physical persons. Multiple identities of single users are common on the Internet and this phenomenon decreases trustfulness of presented content as well as quality of provided services. This paper proposes a novel method for recognition of persons on the Web using input device usage patterns (keyboard, computer mouse, touchscreen), behavioral biometrics. The essential part of this method is a biometric component attached to the user model of an information system serving as a biometric identifier. The recognition of users relies in matching these components, specifically comparing values distribution shapes, which are characterizing users. The paper presents results of the method performance, which were obtained in a series of experiments focused on different aspects of evaluation (recognition rate, scalability, etc.). More specifically, a conducted case study shows application of the method to solve an issue in website visits analysis caused by erasing cookies.

A Novel Method for Recognition of Persian Alphabet by Using Fuzzy Neural Network

This paper presents a system that can recognize handwritten words expressed using broken letters of the Persian alphabet. The proposed system can be used for most activities related to the gathering of public information. Statistical features of the separated/broken letters are employed in the system. Each letter is recognized using interconnected fuzzy neural network. The advantages of this method include high precision owing to the strength of the neural network algorithm and the possibility of extending dataset instance codes in a simple manner. At last, an evaluation for the proposed method is provided experimentally.

Recent Trends and Technologies in Hand Gesture Recognition

Hand gesture recognition is a growing field of research. Gestures are an important aspect of human interaction, both interpersonal and in the context of human computer interface. The interaction between computers and humans are provided by the hand gestures. Gestures provide a way for computers to understand human body language. Hand gesture recognition deals with the goal of interpreting hand gestures via mathematical algorithms. The techniques discussed are based on detection of some shape based features like centroid, orientation of hand, presence of finger, thumb in image and contour based features like convex hull and convexity defects. Hand gesture recognition system provides a user friendly way of interaction with the computer which is more familiar to the human beings. Hand gesture recognition process includes capturing input image which will be processed and segmented so as to extract features to identify different gestures. Different methods of hand gesture recognition techniques are evaluated and proposed a novel method for recognition. This method explains how the users hand is detected and the corresponding gesture is identified in an accurate manner. This paper also explains the various applications that can take advantage of this type of interaction mechanism.

DWT-based Feature Extraction and Radon Transform Based Contrast Enhancement for Improved Iris Recognition

Iris based authentication system is essentially a pattern recognition technique that makes use of iris patterns, which are statistically unique, for the purpose of personal identification. In this paper, a novel method for recognition of iris patterns is proposed by using a combination of pre-processing using Radon transform and Top hat filtering, feature extraction using Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT), and feature selection using Binary Particle Swarm Optimization. Individual stages are examined and an attempt is made to improve each stage. Radon transform is used for detecting lines present in the iris textures and Top hat filtering is used for image enhancement. A combination of DWT and DCT is used to extract the salient iris features. A BPSO-based feature selection algorithm is used to search the feature vector space for the optimal feature subset. Experimental results on two benchmark iris databases, namely Phoenix and IITD, depict promising performance of the proposed techniques for iris recognition.

A Novel Method for Recognition of Bioradiolocation Signal Breathing Patterns for Noncontact Screening of Sleep Apnea Syndrome

A novel method for recognition of breathing patterns of bioradiolocation signals breathing patterns (BSBP) in the task of noncontact screening of sleep apnea syndrome (SAS) is proposed and implemented on the base of wavelet transform (WT) and neural network (NNW) applications. Selection of the optimal parameters of WT includes determination of the proper level of wavelet decomposition and the best basis for feature extraction using modified entropy criterion. Selection of the optimal properties of NNW includes defining the best number of hidden neurons and learning algorithm for the chosen NNW topology. The effectiveness of the proposed approach is tested on clinically verified database of BRL signals corresponding to the three classes of breathing patterns: obstructive sleep apnea (OSA); central sleep apnea (CSA); normal calm sleeping (NCS) without sleep-disordered breathing (SDB) episodes.

Iris recognition using combined support vector machine and Hamming distance approach

Iris based authentication system is essentially a pattern recognition technique that makes use of iris patterns, which are statistically unique, for the purpose of personal identification. In this study, a novel method for recognition of iris patterns is considered by using a combination of support vector machine and Hamming distance. The zigzag collarette area of the iris is selected for iris feature extraction because it captures the most important areas of iris complex pattern and higher recognition rate is achieved. The proposed approach also used parabola detection and trimmed median filter for the purpose of eyelid and eyelash detection & removal, respectively. The proposed method is computationally effective as well as reliable with a recognition rate of 99.91% and 99.88% on CASIA and Chek image database respectively.

Off-line Recognition of Persian Handwritten Digits using Statistical Concepts

In this paper a novel method for recognition of Persian handwritten digits is proposed. This approach uses central moments, Covariance, Median and Variance that are obtained at each the box digit image as the features set. The features set consist of 140 dimensions for each instance. In the classification phase of our proposed method the support vector machines, K-Nearest Neighbor and Sequential Minimal Optimization separately are employed. In this paper is used the principal components analysis (PCA) to reduce dimension features set. the performance of these three classifiers is observed on this application in terms of the correct classification and misclassification and how the performance of K-Nearest Neighbor classifier can be improved by varying the value of k.To evaluate our proposed scheme a database of Persian handwritten digits consist of 1699 handwritten digit images is used. In the best case proposed scheme using SMO classifiers yields a recognition rate of 92.3875% for handwritten Farsi numerals.

Boolean logic analysis for flow regime recognition of gas–liquid horizontal flow

In order to develop a flowmeter for the accurate measurement of multiphase flows, it is of the utmost importance to correctly identify the flow regime present to enable the selection of the optimal method for metering. In this study, the horizontal flow of air and water in a pipeline was studied under a multitude of conditions using electrical resistance tomography but the flow regimes that are presented in this paper have been limited to plug and bubble air–water flows. This study proposes a novel method for recognition of the prevalent flow regime using only a fraction of the data, thus rendering the analysis more efficient. By considering the average conductivity of five zones along the central axis of the tomogram, key features can be identified, thus enabling the recognition of the prevalent flow regime. Boolean logic and frequency spectrum analysis has been applied for flow regime recognition. Visualization of the flow using the reconstructed images provides a qualitative comparison between different flow regimes. Application of the Boolean logic scheme enables a quantitative comparison of the flow patterns, thus reducing the subjectivity in the identification of the prevalent flow regime.

Study of Modulation Recognition Algorithm Based on Wavelet Transform and Neural Network

Modulation identification for communication signals has important applications both in military and civilian areas. Aimed at the non-stationary modulated signal of which signal to noise ratio (SNR) changes large, a novel method for recognition of modulation signals by wavelet transform and neural network theory is introduced. In this algorithm, instantaneous feature parameters of received signals are extracted using wavelet transform. Then, make singular value decomposition to the matrix which is composed of instantaneous parameters to get singular values. Error back propagation neural network (BPNN) with supervised training is to be made the classifier. The singular values obtained are used as feature vector and inputted to the classifier. So the automatic modulation recognition of signal is realized. The identification in category for FSK and PSK are simulated respectively, and the simulation results prove the approach proposed in this paper is efficient.

Iris matching using multi-dimensional artificial neural network

Iris recognition is one of the most widely used biometric technique for personal identification. This identification is achieved in this work by using the concept that, the iris patterns are statistically unique and suitable for biometric measurements. In this study, a novel method of recognition of these patterns of an iris is considered by using a multi-dimensional artificial neural network. The proposed technique has the distinct advantage of using the entire resized iris as an input at once. It is capable of excellent pattern recognition properties as the iris texture is unique for every person used for recognition. The system is trained and tested using two publicly available databases (CASIA and UBIRIS). The proposed approach shows significant promise and potential for improvements, compared with the other conventional matching techniques with regard to time and efficiency of results.

On the use of graph parsing for recognition of isolated hand postures of Polish Sign Language

A novel method of recognition of hand postures of Polish Sign Language (PSL) is presented in the paper. The method is based on a syntactic pattern recognition paradigm. A construction of algorithms for generating a structural (graph) description of hand postures that can be analyzed with the ETPL ( k ) graph grammar parsing model has been a main objective of the research. A structural description generated with these algorithms is unique and unambiguous that results in good discriminative properties of the method.

COMPARING THE PROTEOME OF SQUAMOUS CELL CARCINOMA VERSUS NORMAL ESOPHAGUS TO FIND MOLECULAR MARKERS FOR RECOGNITION OF THE DISEASE

Since esophagus cancer is among the most fatal cancers all over the world and our country has the most frequent number of patients, identification of squamous cell carcinoma associated proteins would be essential. Finding molecular markers for recognition of the disease could be beneficial for efficient and early treatment of the disease. As protein expression in cancerous cells is different from normal ones, identification of protein expression pattern could be helpful for recognition of the disease. Proteomics is a novel method for recognition of protein collection in a specific tissue. In this method 2D gel electrophoresis is performed to separate all proteins, and then spot analysis will be done through mass spectrometry and bioinformatics software would help in the recognition of proteins. In comparison to normal tissue in cancerous cells, we would have up-regulation, down-regulation, appearance or disappearance of a specific protein. So, protein extraction was performed from healthy and cancerous mucosal tissue of esophagus and all peptides were separated through 2D gel electrophoresis. After spot analysis, proteins with different expression were identified with mass spectrometry and bioinformatics. In comparison to normal tissue, 14 proteins were found to over expressed or have no expression in tumors. The main objective of this study is that proteomics is an ideal method to find the molecular basis of squamous cell carcinoma in esophageal cancer.

Damage classification of concrete structures based on grey level co-occurrence matrix using Haar's discrete wavelet transform

A novel method for recognition, characterization, and quantification of deterioration in bridge components and laboratory concrete samples is presented in this paper. The proposed scheme is based on grey level co-occurrence matrix texture analysis using Haar\'s discrete wavelet transform on concrete imagery. Each image is described by a subset of band-filtered images containing wavelet coefficients, and then reconstructed images are employed in characterizing the texture, using grey level co-occurrence matrices, of the different types and degrees of damage: map-cracking, spalling and steel corrosion. A comparative study was conducted to evaluate the efficiency of the supervised maximum likelihood and unsupervised K-means classification techniques, in order to classify and quantify the deterioration and its extent. Experimental results show both methods are relatively effective in characterizing and quantifying damage; however, the supervised technique produced more accurate results, with overall classification accuracies ranging from 76.8% to 79.1%.

A novel and sensitive method for recognition and indirect determination of Al III in biological fluid based on the quenching of resonance Rayleigh scattering intensities of “Al III-EV-DNA” complexing system

A novel method for recognition and indirect determination of Al III by using biological molecules has been established based on the quenching of RRS intensity. In the weak acidic medium, the reaction of ethyl violet (EV) and DNA would result in great enhancement of RRS intensity. However, the presence of Al III would lead to the decrease of the RRS intensity owing to the competition coordination of Al with DNA. The decreased intensity of RRS is directly proportional to the concentration of Al III in the range of (0.1–2.5) × 10 −6 and (0.30–4.5) × 10 −5 M, respectively. The method has high sensitivity and its detection limit (3 σ) is 3.6 × 10 −8 M. The characteristics of RRS spectra of the system, the optimum conditions of the reaction, and the reaction mechanism have been investigated. The method can recognize Al III selectively owing to its strong binding to the phosphate backbone of DNA, and has been applied to the determination of Al III concentration in synthetic biological samples with satisfactory results. Therefore, the proposed method is promising as an effective means for selective recognition and sensitive determination in situ of Al III. Furthermore, this study would contribute to further understanding of the biological significance of Al neurotoxicity.

Wavelet packet analysis for face recognition

A novel method for recognition of frontal views of human faces under roughly constant illumination is presented. The proposed scheme is based on the analysis of a wavelet packet decomposition of the face images. Each face image is first located and then, described by a subset of band filtered images containing wavelet coefficients. From these wavelet coefficients, which characterize the face texture, we build compact and meaningful feature vectors, using simple statistical measures. Then, we show how an efficient and reliable probabilistic metric derived from the Bhattacharrya distance can be used in order to classify the face feature vectors into person classes. Experimental results are presented using images from the FERET and the FACES databases. The efficiency of the proposed approach is analyzed according to the FERET evaluation procedure and by comparing our results with those obtained using the well-known Eigenfaces method.

Recognition Using Region Correspondences

Recognition systems attempt to recover information about the identity of observed objects and their location in the environment. A fundamental problem in recognition is pose estimation. This is the problem of using a correspondence between some portions of an object model and some portions of an image to determine whether the image contains an instance of the object, and, in case it does, to determine the transformation that relates the model to the image. The current approaches to this problem are divided into methods that use “global” properties of the object (e.g., centroid and moments of inertia) and methods that use “local” properties of the object (e.g., corners and line segments). Global properties are sensitive to occlusion and, specifically, to self occlusion. Local properties are difficult to locate reliably, and their matching involves intensive computation. We present a novel method for recognition that uses region information. In our approach the model and the image are divided into regions. Given a match between subsets of regions (without any explicit correspondence between different pieces of the regions) the alignment transformation is computed. The method applies to planar objects under similarity, affine, and projective transformations and to projections of 3-D objects undergoing affine and projective transformations. The new approach combines many of the advantages of the previous two approaches, while avoiding some of their pitfalls. Like the global methods, our approach makes use of region information that reflects the true shape of the object. But like local methods, our approach can handle occlusion.