scholarly journals Image-Level Structure Recognition Using Image Features, Templates, and Ensemble of Classifiers

Symmetry ◽  
2020 ◽  
Vol 12 (7) ◽  
pp. 1072 ◽  
Author(s):  
Altaf Khan ◽  
Alexander Chefranov ◽  
Hasan Demirel
Keyword(s):  
Autonomous Vehicle ◽  
Level Structure ◽  
Recognition Rate ◽  
Image Features ◽  
Depth Information ◽  
Structure Recognition ◽  
Scene Structure ◽  
Distribution Features ◽  
Individual Classifier ◽  
The Individual

Image-level structural recognition is an important problem for many applications of computer vision such as autonomous vehicle control, scene understanding, and 3D TV. A novel method, using image features extracted by exploiting predefined templates, each associated with individual classifier, is proposed. The template that reflects the symmetric structure consisting of a number of components represents a stage—a rough structure of an image geometry. The following image features are used: a histogram of oriented gradient (HOG) features showing the overall object shape, colors representing scene information, the parameters of the Weibull distribution features, reflecting relations between image statistics and scene structure, and local binary pattern (LBP) and entropy (E) values representing texture and scene depth information. Each of the individual classifiers learns a discriminative model and their outcomes are fused together using sum rule for recognizing the global structure of an image. The proposed method achieves an 86.25% recognition accuracy on the stage dataset and a 92.58% recognition rate on the 15-scene dataset, both of which are significantly higher than the other state-of-the-art methods.

Online Biological Literature MRI Image Classification Study

2013 ◽  
Vol 694-697 ◽  
pp. 2336-2340
Author(s):  
Yun Feng Yang ◽  
Feng Xian Tang
Keyword(s):  
Recognition Performance ◽  
Recognition Rate ◽  
Image Features ◽  
Feature Identification ◽  
Identification Method ◽  
Image Library ◽  
Text Information ◽  
Correct Recognition Rate ◽  
Biological Literature ◽  
Mri Image

In order to construct a certain standard structure MRI (Magnetic resonance imaging) image library by extracting and collating unstructured literature data information, an identification method of the image and text information fusion is proposed. The method makes use of PHOW (Pyramid Histogram Of Words) to represent image features, combines with the word frequency characteristics of the embedded icon note (text), and then uses posterior multiplication fusion method to complete the classification and identification of the online biological literature MRI image. The experimental results show that this method has better correct recognition rate and better recognition performance than feature identification method only based on PHOW or text. The study can offer use for reference to construct other structured professional database from online literature.

An Integrated Approach for Traffic Scene Understanding from Monocular Cameras

2021 ◽  
Author(s):  
Malte Oeljeklaus
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Scene Perception ◽  
Integrated Approach ◽  
Image Features ◽  
Road Users ◽  
Environment Model ◽  
Computational Performance ◽  
Spatial Reconstruction ◽  
The Individual

This thesis investigates methods for traffic scene perception with monocular cameras for a basic environment model in the context of automated vehicles. The developed approach is designed with special attention to the computational limitations present in practical systems. For this purpose, three different scene representations are investigated. These consist of the prevalent road topology as the global scene context, the drivable road area and the detection and spatial reconstruction of other road users. An approach is developed that allows for the simultaneous perception of all environment representations based on a multi-task convolutional neural network. The obtained results demonstrate the efficiency of the multi-task approach. In particular, the effects of shareable image features for the perception of the individual scene representations were found to improve the computational performance. Contents Nomenclature VII 1 Introduction 1 1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Outline and contributions . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2 Related Work and Fundamental Background 8 2.1 Advances in CNN...

Three-Dimensional Scene Reconstruction

2011 ◽  
pp. 142-162
Author(s):  
Dimitrios Chrysostomou ◽  
Antonios Gasteratos
Keyword(s):  
Vision System ◽  
Three Dimensional ◽  
3D Models ◽  
Scene Reconstruction ◽  
Depth Information ◽  
Vision Systems ◽  
Working Space ◽  
Scene Structure ◽  
Long Time ◽  
Dimensional Surface

The production of 3D models has been a popular research topic already for a long time, and important progress has been made since the early days. During the last decades, vision systems have established to become the standard and one of the most efficient sensorial assets in industrial and everyday applications. Due to the fact that vision provides several vital attributes, many applications tend to use novel vision systems into domestic, working, industrial, and any other environments. To achieve such goals, a vision system should robustly and effectively reconstruct the 3D surface and the working space. This chapter discusses different methods for capturing the three-dimensional surface of a scene. Geometric approaches to three-dimensional scene reconstruction are generally based on the knowledge of the scene structure from the camera’s internal and external parameters. Another class of methods encompasses the photometric approaches, which evaluate the pixels’ intensity to understand the three-dimensional scene structure. The third and final category of approaches, the so-called real aperture approaches, includes methods that use the physical properties of the visual sensors for image acquisition in order to reproduce the depth information of a scene.

Counterfactuals in Health and Risk Messaging

2017 ◽  
Author(s):  
Irina A. Iles ◽  
Xiaoli Nan
Keyword(s):  
Decision Making ◽  
Counterfactual Thinking ◽  
Depth Information ◽  
Negative Events ◽  
Positive Events ◽  
Political Sciences ◽  
The Social ◽  
The One ◽  
The Individual ◽  
And Control

Counterfactual thinking is the process of mentally undoing the outcome of an event by imagining alternate antecedent states. For example, one might think that if they had given up smoking earlier, their health would be better. Counterfactuals are more frequent following negative events than positive events. Counterfactuals have both aversive and beneficial consequences for the individual. On the one hand, individuals who engage in counterfactual thinking experience negative affect and are prone to biased judgment and decision making. On the other hand, counterfactuals serve a preparative function, and they help people reach their goals in the future by suggesting effective behavioral alternatives. Counterfactual thoughts have been found to influence an array of cognitive processes. Engaging in counterfactual thinking motivates careful, in-depth information processing, increases perceptions of self-efficacy and control, influences attitudes toward social matters, with consequences for behavioral intentions and subsequent behaviors. Although it is a heavily studied matter in some domains of the social sciences (e.g., psychology, political sciences, decision making), counterfactual thinking has received less attention in the communication discipline. Findings from the few studies conducted in communication suggest that counterfactual thinking is a promising message design strategy in risk and health contexts. Still, research in this area is critically needed, and it represents an opportunity to expand our knowledge.

scholarly journals Quantitative Nondestructive Testing of Wire Ropes Based on Features Fusion of Magnetic Image and Infrared Image

2019 ◽  
Vol 2019 ◽  
pp. 1-15 ◽  
Author(s):  
Shiliang Lu ◽  
Juwei Zhang
Keyword(s):  
Nondestructive Testing ◽  
Nearest Neighbor ◽  
Recognition Rate ◽  
Infrared Image ◽  
Wire Rope ◽  
Image Features ◽  
Magnetic Image ◽  
Wire Ropes ◽  
Processing Techniques ◽  
Modulus Maxima

Magnetic flux leakage (MFL) detection is one of the most widely used and best performing wire rope nondestructive testing (NDT) methods for more than a decade. However, the traditional MFL detection has the disadvantages of single source of information, low precision, easy to miss detection, and false detection. To solve these problems, we propose a method of fusion recognition of magnetic image features and infrared image features. A denoising algorithm based on Hilbert vibration decomposition (HVD) and wavelet transform is proposed to denoise the MFL signal, and the modulus maxima method is used to locate and segment the defect. An infrared image acquisition system was designed to collect the infrared image of the surface of the wire rope. Digital image processing techniques are used to segment infrared defect images. The features of the MFL image and the infrared image are extracted separately for fusion. The fusion feature is input into the nearest neighbor (NN) algorithm for quantitative identification, and the same data are input into the backpropagation (BP) neural network for comparison verification. The experimental results show that the fusion of MFL features and infrared features effectively improves the recognition rate of wire rope defects and reduces the recognition error.

Shape Classification Using Multiple Classifiers with Different Feature Sets

2011 ◽  
Vol 368-373 ◽  
pp. 1583-1587
Author(s):  
Jun Ying Chen ◽  
Jing Chen ◽  
Zeng Xi Feng
Keyword(s):  
Neural Network ◽  
Recognition Rate ◽  
Shape Classification ◽  
K Nearest Neighbor ◽  
Feed Forward Neural Network ◽  
Combination Strategy ◽  
Combination Rules ◽  
Feature Sets ◽  
Multiple Classifiers ◽  
Individual Classifier

In this paper, a new shape classification method based on different feature sets using multiple classifiers is proposed. Different feature sets are derived from the shapes by using different extraction methods. The implements of feature extraction are based on two ways: Fourier descriptors and Zernike moments. Multiple classifiers comprise Normal densities based linear classifier, k-nearest neighbor classifier, Feed-Forward neural network, Radial Basis Function neural network classifier. Each classifier is trained by two feature sets respectively to form two classification results. The final classification results are a combined response of the individual classifier using six different classifier combination rules and the results were compared with those derived from multiple classifiers based on the same feature sets and individual classifier. In this study we examined the different classification tasks on Kimia dataset. For the tasks the best combination strategy was found using the product rule, giving an average recognition rate of 95.83%.

scholarly journals Fuzzy integral-based multi-sensor fusion for arc detection in the pantograph-catenary system

2016 ◽  
Vol 232 (1) ◽  
pp. 159-170 ◽  
Author(s):  
Ilhan Aydin ◽  
Selahattin B Celebi ◽  
Sami Barmada ◽  
Mauro Tucci
Keyword(s):  
Detection Method ◽  
Electrical Power ◽  
Classifier Fusion ◽  
Support Vector ◽  
Fuzzy Integral ◽  
Detection Accuracy ◽  
Correct Operation ◽  
Railway Traffic ◽  
Individual Classifier ◽  
The Individual

The pantograph-catenary subsystem is a fundamental component of a railway train since it provides the traction electrical power. A bad operating condition or, even worse, a failure can disrupt the railway traffic creating economic damages and, in some cases, serious accidents. Therefore, the correct operation of such subsystems should be ensured in order to have an economically efficient, reliable and safe transportation system. In this study, a new arc detection method was proposed and is based on features from the current and voltage signals collected by the pantograph. A tool named mathematical morphology is applied to voltage and current signals to emphasize the effect of the arc, before applying the fast Fourier transform to obtain the power spectrum. Afterwards, three support vector machine-based classifiers are trained separately to detect the arcs, and a fuzzy integral technique is used to synthesize the results obtained by the individual classifiers, therefore implementing a classifier fusion technique. The experimental results show that the proposed approach is effective for the detection of arcs, and the fusion of classifier has a higher detection accuracy than any individual classifier.

A KNOWLEDGE-BASED SYSTEM FOR THE IMAGE CORRESPONDENCE PROBLEM

1990 ◽  
Vol 04 (01) ◽  
pp. 45-55 ◽  
Author(s):  
CHUNG-MONG LEE ◽  
TING-CHUEN PONG ◽  
JAMES R. SLAGLE
Keyword(s):  
Image Features ◽  
Correspondence Problem ◽  
Knowledge Based System ◽  
Knowledge Based ◽  
Matching Process ◽  
Expert System Shell ◽  
Image Correspondence ◽  
Global Matching ◽  
Temporal Vision ◽  
The Individual

The image correspondence problem has generally been considered the most difficult step in both stereo and temporal vision. Most existing approaches match area features or linear features extracted from an image pair. The approach described in this paper is novel in that it uses an expert system shell to develop an image correspondence knowledge-based system for the general image correspondence problem. The knowledge it uses consists of both physical properties and spatial relationships of the edges and regions in images for every edge or region matching. A computation network is used to represent this knowledge. It allows the computation of the likelihood of matching two edges or regions with logical and heuristic operators. Heuristics for determining the correspondences between image features and the problem of handling missing information will be discussed. The values of the individual matching results are used to direct the traversal and pruning of the global matching process. The problem of parallelizing the entire process will be discussed. Experimental results on real-world images show that all matching edges and regions have been identified correctly.

scholarly journals Performance Analysis of Iris Recognition using Multi Stage Wavelet Transform Decomposition and Bicubic Interpolation Technique

2019 ◽  
Vol 8 (6) ◽  
pp. 1-10
Keyword(s):  
Wavelet Transform ◽  
Discrete Wavelet Transform ◽  
Iris Recognition ◽  
Image Features ◽  
Discrete Wavelet ◽  
Multi Stage ◽  
Human Iris ◽  
The Individual ◽  
Matching Score ◽  
Bicubic Interpolation

Biometric identification is highly reliable for human identification. Biometric is a field of science used for analyzing the physiological or behavioural characteristics of human. Iris features are unique, stable and can be visible from longer distances. It uses mathematical pattern-recognition techniques on video images of one or both iris of an individual's. Compared to other biometric traits, iris is more challenging and highly secured tool to identify the individual. In this paper iris recognition based on the combination of Discrete Wavelet Transform (DWT), Inverse Discrete Wavelet Transform (IDWT), Independent Component Analysis (ICA) and Binariezed Statistical Image Features (BSIF) are adopted to generate the hybrid iris features. The first level and second level DWT are employed in order to extract the more unique features of the iris images. The concept of bicubic interpolation is applied on high frequency coefficients generated by first level decomposition of DWT to produce new set of sub-bands. The approximation band generated by second level decomposition of DWT and new set of sub-bands produced by second level decomposition of DWT are applied on IDWT to reconstruct the coefficients. The ICA 5x5 filters and BSIF are adopted for selecting the appropriate images to extract the final features. Finally based on the matching score between the database image and test image the genuine and imposters are identified. Using CASIA database, training and testing of the features is performed and performance is evaluated considering different combinations of Person inside Database (PID) and Person outside Database (POD).

Sign in / Sign up

Export Citation Format

Share Document