Biorthogonal wavelet transform based classification of human object using Adaboost classifier

The primitive machine learning algorithms that are present break down each problem into small modules and solve them individually. Nowadays requirement of detection algorithm is to work end to end and take less time to compute. Real-time detection and classification of objects from video records provide the foundation for generating many kinds of analytical aspects such as the amount of traffic in a particular area over the years or the total population in an area. In practice, the task usually encounters slow processing of classification and detection or the occurrence of erroneous detection due to the incorporation of small and lightweight datasets. To overcome these issues, YOLO (You Only Look Once) based detection and classification approach (YOLOv2) for improving the computation and processing speed and at the same time efficiently identify the objects in the video records. The classification algorithm creates a bounding box for every class of objects for which it is trained, and generates an annotation describing the particular class of object. The YOLO based detection and classification (YOLOv2) use of GPU (Graphics Processing Unit) to increase the computation speed and processes at 40 frames per second.

Segmentation and classification of objects in images is one of the most important and yet one of the most complex problems in computer vision. Many different things contribute to the complexity of this problem, but amongst those that are most significant are variations in object appearance due to various perspectives, changes in scene illumination and typically a large number of partially occluded objects in a scene. Humans have the ability to successfully deal with these complications and to recognize objects in scenes without seemingly much effort. However, to aid their recognition process, humans use different sources of information such as previous experiences, context of objects placed in a scene and rules learned in the past that suggest how the physical world should appear and behave. Computer vision is trying to replicate the same strategies used by human vision and apply them to computer systems with the aim of improving typical tasks of detection, localization and classification of image objects. In this work we propose a new model for natural image object classification using contextual information at the level of image segments. Context modeling is largely independent of appearance-based classification and proposed model enables simple upgrade of existing systems with information from global and/or local context. Context modeling is based on non-parametric use of appearance-based classification results which is a novel approach compared to previous systems that model context on a limited number of rules expressed with a fixed set of parameters. Model implementation resulted in a system that, in our simulations, showed stable improvement of the appearance-based object classification. DOI: http://dx.doi.org/10.5755/j01.itc.46.1.13610

<p>In this paper, multifocus image fusion using quarter shift dual tree complex wavelet transform is proposed. Multifocus image fusion is a technique that combines the partially focused regions of multiple images of the same scene into a fully focused fused image. Directional selectivity and shift invariance properties are essential to produce a high quality fused image. However conventional wavelet based fusion algorithms introduce the ringing artifacts into fused image due to lack of shift invariance and poor directionality. The quarter shift dual tree complex wavelet transform has proven to be an effective multi-resolution transform for image fusion with its directional and shift invariant properties. Experimentation with this transform led to the conclusion that the proposed method not only produce sharp details (focused regions) in fused image due to its good directionality but also removes artifacts with its shift invariance in order to get high quality fused image. Proposed method performance is compared with traditional fusion methods in terms of objective measures. </p>

There are many research efforts in object recognition. Most existing methods for object recognition are based on full objects. However, many images contain multiple objects with occluded shapes and regions. Due to the occlusion of objects, image retrieval can provide incomplete, uncertain, and inaccurate results. To resolve this problem, we propose a new method to reconstruct objects using symmetry properties since most objects in a given image database are represented by symmetrical figures. Even though there have been several efforts in object recognition with occlusion, current methods have been highly sensitive to object pose, rotation, scaling, and visible portion of occluded objects. In addition, many appearance-based and model-based object recognition methods assumed that they have known occluded regions of objects or images through extensive training processes with statistical approach. However, our new approach is not limited to recognizing occluded objects by pose and scale changes, and does not need extensive training processes. Unlike existing methods, the proposed method finds shapes and regions to reconstruct occluded shapes and regions within objects. We assume that we only consider the elliptical objects in recognition. The proposed approach can handle object rotation and scaling for dealing with occlusion, and does not require extensive training processes. The main advantage of our proposed approach is that it becomes simple to reconstruct objects from occlusions using symmetry. We present a robust method, which is based on the contours of objects, for recognizing partially occluded objects based on symmetry properties. The contour-based approach finds a symmetry axis using the maximum diameter from the occluded object. In experiments, we demonstrate how a proposed method reconstructs and recognizes occluded shapes and regions using symmetry. Experiments use rotated and scaled objects for dealing with occlusion. We use mirror symmetry to find possible occluded regions in objects. Examples of partially occluded objects are shown in Figure 1.1. We also evaluate the recognition rate of the reconstructed objects using symmetry and the visible portion of the occluded objects for recognition. The method produces average recognition rates for cups and plates above 88% with 30% occlusion. In this case, part of the

Background: Detection of hidden objects in the soil layer is a problem that is important in construction, archeology, humanitarian demining, non-destructive testing of road surfaces, flaw detection etc. Studying the peculiarities of electromagnetic filed behavior in heterogeneous media provides a possibility to create subsurface survey systems that can work effectively in real conditions. Objectives: To recognize an object hidden in a heterogeneous medium using ultrawideband ground penetrating radar (GPR) and artificial neural network (ANN), to evaluate the performance of a neural network that is trained only on homogeneous medium, to investigate the stability of recognition results in the presence of noise of different levels in the received time dependencies, to compare the results with a network which is trained on heterogeneous media. Check the ability of the ANN to correctly identify typical objects that were not involved in training. Materials and methods: Modeling of the electrodynamic problem of electromagnetic field propagation is carried out using the finite difference in time domain (FDTD) method. The classification of hidden objects is carried out using the approach of artificial neural networks. Results: An effective algorithm for detecting objects in a heterogeneous soil model was developed using ground-penetrating radar and ANN. Probability distributions of the classification of hidden objects in presence of additive Gaussian noise in time dependencies were obtained. Conclusion: The use of ANNs has shown successful results in the classification of objects located in a heterogeneous ground model. The ability to detect objects containing only a few metal parts was demonstrated. The developed algorithm has a high level of noise immunity even at high signal-to-noise levels. The results of detection and recognition of typical objects, which were not involved in ANN training, showed the effectiveness of this approach.

Recurrent neural networks are powerful tools for handling incomplete data problems in computer vision, thanks to their significant generative capabilities. However, the computational demand for these algorithms is too high to work in real time, without specialized hardware or software solutions. In this paper, we propose a framework for augmenting recurrent processing capabilities into a feedforward network without sacrificing much from computational efficiency. We assume a mixture model and generate samples of the last hidden layer according to the class decisions of the output layer, modify the hidden layer activity using the samples, and propagate to lower layers. For visual occlusion problem, the iterative procedure emulates feedforward-feedback loop, filling-in the missing hidden layer activity with meaningful representations. The proposed algorithm is tested on a widely used dataset and shown to achieve 2× improvement in classification accuracy for occluded objects. When compared to Restricted Boltzmann Machines, our algorithm shows superior performance for occluded object classification.

This paper presents a sensorial-cooperative architecture to detect, track and classify entities in semi-structured outdoor scenarios for intelligent vehicles. In order to accomplish this task, information provided by in-vehicle Lidar and monocular vision is used. The detection and tracking phases are performed in the laser space, and the object classification methods work both in laser space (using a Gaussian Mixture Model classifier) and in vision spaces (AdaBoost classifier). A Bayesian-sum decision rule is used in order to combine the results of both classification techniques, and hence a more reliable object classification is achieved. Experiments confirm the effectiveness of the proposed architecture.

The recognition of fully multi-oriented handwritten characters is a challenging problem. Contrary to univariate signals where the shift invariance property in the Fourier transform can be used, multivariate signals like images require special care to extract rotation invariant features. Several strategies to solve such classification tasks are possible. The proposed method considers input features obtained by the Radon transform or Polar transform. A convolutional neural network is then used for extracting higher level features. This classifier includes in addition the Fast Fourier Transform for extracting shift invariant features at the neural network level. The Radon transform and the convolutional layers process the image at the pixel level while the Fourier transform and the upper layers of the neural network process rotation invariant features. The classifier is evaluated on multi-oriented handwritten digits based on the MNIST database (Arabic digits) and on the ISI database (Bangla digits). The average recognition rate for multi-oriented characters is 93.10% for the Arabic digits and 77.01% for the Bangla digits. This neural architecture highlights the interest of the radial convolutional layer for the recognition of multi-oriented shapes.

Object classification is one of main problems in computer vision and lots of state-of-the-art machine learning methods have been proposed recently. Traditional classifier may have the drawback of low effectiveness for image representations. In this paper, an improved eXtreme Gradient Boosting (XGBoost) based on weighted column (feature) subsampling is proposed to classify image representations for object classification. The contributions of the paper are as follows. First, Convolutional Neural Networks (CNN) pre-trained on large-scale image database ILSVRC and fine-tuned on PASCAL VOC 2012 dataset is used to extract features from object images. Besides, we concatenate multiple layers of learned features to obtain more information of image contents for determining their categories. Second, due to the high dimensional of extracted features, feature redundancy will unavoidably be incurred, so a weighted column subsampling method is proposed to applied to XGBoost algorithm, in order to draw the features by the importance during growing each tree. Futhermore, our proposed method is general, which can be easily extended to other methods which need column subsampling, when the feature of data is high dimensional and redundant. Finally, we validate performance of proposed method on the PASCAL VOC 2007 dataset. Compared with four typical methods, the proposed method has superior average precision (AP) on 5 out of 20 classes, e.g. the AP of person class we obtained is 92.1, 1% higher than that of best method mentioned above.

Gaussian noise is an important problem in computer vision. The novel methods that become popular in recent years for Gaussian noise reduction are Bayesian techniques in wavelet domain. In wavelet domain, the Bayesian techniques require a prior distribution of wavelet coefficients. In general case, the wavelet coefficients might be better modeled by non-Gaussian density such as Laplacian, two-sided gamma, and Pearson type VII densities. However, statistical analysis of textural image is Gaussian model. So, we require flexible model between non-Gaussian and Gaussian models. Indeed, Gumbel density is a suitable model. So, we present new Bayesian estimator for Gumbel random vectors in AWGN (additive white Gaussian noise). The proposed method is applied to dual-tree complex wavelet transform (DT-CWT) as well as orthogonal discrete wavelet transform (DWT). The simulation results show that our proposed methods outperform the state-of-the-art methods qualitatively and quantitatively.

A fusion of dolphin swarm optimization and improved sine cosine algorithm for automatic detection and classification of objects from surveillance videos

Recently, shape-based matching and retrieval of 3D polygonal models has become one of the most fundamental problems in computer vision. Dealing with families of objects instead of a single one may impose further challenges on regular geometric algorithms. In this paper we focus on the classification of 3D objects based on their geodesic distance & path calculated on a mesh using an iterative algorithm for solving the Eikonal equation. For the classification process, we use both Multiclass Support Vector Machine (M-SVM) classifier,K-Nearest Neighbors (KNN), Decision Tree (DT) and Artificial Neural Networks (ANN) to better evaluate our descriptors. We illustrate the potential of extracted characteristics by two 3D benchmarks. The recognition rates achieved in all experiments show that a small number of curve between 9 and 12 can correctly categorize a family of 3D objects.

The paper addresses the issue of insuring the required probability of correct classification of marine objects in low-frequency passive sonar systems. The solution to the issue is sought through the application of methods for the synthesis of neural network classification algorithms using poly-Gaussian probabilistic models (Gaussian mixture models, GMM). It is shown that the use of GMM makes it possible to solve a number of problems specific to the issue; classification algorithms synthesized using mentioned methods can be implemented in the form of neural networks, which in turn can be described in C++/VHDL to create endpoint computing devices or software systems. The results of modeling of synthesized classification algorithms on experimental data are presented; it is demonstrated that such algorithms make it possible to increase the probability of correct classification of marine objects and to satisfy typical requirements for classification systems in low-frequency passive sonar systems.

Object classification from images is an important task for machine vision and it is a crucial ingredient for many computer vision applications, ranging from security and surveillance to marketing. Image based object classification techniques properly integrate image processing and machine learning (i.e., classification) procedures. In this paper we present a system for automatic simultaneous optimization of algorithms and parameters for object classification from images. More specifically, the proposed system is able to process a dataset of labelled images and to return a best configuration of image processing and classification algorithms and of their parameters with respect to the accuracy of classification. Experiments with real public datasets are used to demonstrate the effectiveness of the developed system.

Objectives: For over six years, Morocco has been engaged in an initiative aimed at promoting inclusive and sustainable territorial development, characterized by the implementation of an advanced regionalization experiment. However, the main challenge facing government leaders today is managing a growing number of regional development conventions. Methods: To achieve these objectives, we developed a predictive model using artificial intelligence and machine learning aimed at anticipating the outcomes of regional development conventions. Through this method, we were able to identify the risks associated with their potential failure and forecast their impact. Simultaneously, various data extraction methods and classification algorithms were implemented. We collected and analyzed information from 310 past and current regional development conventions, spanning from 2016 to 2020, considering various factors influencing their success or failure. We conducted extensive experiments to assess the effectiveness of various predictive models. Results: The results we obtained indicate that the classifiers Ada Boost, Random Forest, and Bernoulli NB are the three most effective algorithms for predicting the outcomes of regional development conventions. Conclusion: This study contributes to shaping a broader discourse on the practical application of artificial intelligence in public policies and regional development, highlighting its potential to enhance resource allocation and alleviate the burden of repetitive administrative tasks for organizations with limited resources.