Abderrahim Mesbah | University of Sidi Mohammed Ben Abdellah (original) (raw)

Papers by Abderrahim Mesbah

Rigid and non-rigid 3D shape classification based on 3D Hahn moments neural networks model

Multimedia Tools and Applications

3D Shape Classification Using 3D Discrete Moments and Deep Neural Networks

Proceedings of the 2nd International Conference on Networking, Information Systems & Security - NISS19

In this paper, we propose a new model for 3D shape classification based on 3D discrete orthogonal... more In this paper, we propose a new model for 3D shape classification based on 3D discrete orthogonal moments and deep neural network (DNN) to enhance the classification accuracy of 3D objects under geometric transformations such as scale and rotation. The proposed model is derived by introducing image moments as an input vector in DNN, frequently utilized in many tasks of pattern recognition. Discrete orthogonal moments have the ability to capture global information from an image in lower orders. The aim of this work is to investigate the robustness of the proposed model to geometric transformations like rotation and scale. The simulations are performed on constructed dataset by applying some geometric transformations on selected objects from the McGill database to evaluate the performance of our proposed model. The obtained results show that the proposed model with Hahn moments achieves high classification rates and robust to geometric transformations than Krawtchouk moments.

Efficient color face recognition based on quaternion discrete orthogonal moments neural networks

Multimedia Tools and Applications, 2022

3D Object Classification using 3D Racah Moments Convolutional Neural Networks

Proceedings of the 2nd International Conference on Networking, Information Systems & Security - NISS19, 2019

In this paper, we propose a new architecture of deep neural network called 3D Racah Moments Convo... more In this paper, we propose a new architecture of deep neural network called 3D Racah Moments Convolutional Neural Network (3D RMCNN) to improve the classification accuracy and reduce the computational complexity of a 3D pattern recognition system. The proposed architecture consists of fusioning the concepts of image Racah moments and convolutional neural network (CNN), largely utilized in pattern recognition applications. Indeed, the advantages of the moments concerning their global information coding mechanism even in lower orders, along with the high effectiveness of the CNN, are combined to make up the proposed robust network. The aim of this work is to investigate the classification capabilities of 3D RMCNN on 3D shape datasets. The experiment simulations with 3D RMCNN have been performed on SHREC 2011 and ModelNet10 databases. The obtained results show high performance in the classification accuracy of the proposed model and its ability to decrease the computational cost by training low number of features generated by the first moment layer.

Color Face Recognition by Using Quaternion and Deep Neural Networks

2019 International Conference on Wireless Technologies, Embedded and Intelligent Systems (WITS), 2019

In this paper we propose a new model for color face recognition based on quaternion number and de... more In this paper we propose a new model for color face recognition based on quaternion number and deep neural networks (DNN), to enhance the classification accuracy of color face recognition. The proposed model is derived by introducing image represented in quaternion domain as an input vector in DNN model, frequently, utilized in many vision tasks of pattern recognition. The utilization of quaternion representation (QR) aims to reduce the size of input vector and consequently the computational complexity. On the other hand, color information from the image while obtaining best classification results. The simulations results are performed on color face databases to demonstrate the effectiveness of the proposed model. The obtained results show that they outperform other existing algorithms.

Automobile Insurance Claims Auditing: A Comprehensive Survey on Handling Awry Datasets

Lecture Notes in Electrical Engineering, 2021

Fraud is a very costly criminal activity. Insurance companies face the very challenging task of i... more Fraud is a very costly criminal activity. Insurance companies face the very challenging task of identifying and preventing fraudulent claims. Just like any big problem in recent years, Machine Learning has been heavily applied to fraud detection in both a supervised and non-supervised manner. But, usually supervised models do not perform well in the presence of awry, asymmetrical Datasets. This paper presents a novel approach for auditing claims in automobile insurance. Our data pipeline consists of preprocessing, feature selection, data balancing, and classification. This robust fraud detection model, built upon existing fraud detection research, gives very promising results compared to state of the art in the industry.

Non-rigid 3D Model Classification Using 3D Hahn Moment Convolutional Neural Networks

In this paper, we propose a new architecture of 3D deep neural network called 3D Hahn Moments Con... more In this paper, we propose a new architecture of 3D deep neural network called 3D Hahn Moments Convolutional Neural Network (3D HMCNN) to enhance the classification accuracy and reduce the computational complexity of a 3D pattern recognition system. The proposed architecture is derived by combining the concepts of image Hahn moments and convolutional neural network (CNN), frequently utilized in pattern recognition applications. Indeed, the advantages of the moments concerning their global information coding mechanism even in lower orders, along with the high effectiveness of the CNN, are combined to make up the proposed robust network. The aim of this work is to investigate the classification capabilities of 3D HMCNN on small 3D datasets. The experiment simulations with 3D HMCNN have been performed on the articulated parts of McGill 3D shape Benchmark database and SHREC 2011 database. The obtained results show the significantly high performance in the classification rates of the prop...

Radial Charlier moment invariants for 2D object/image recognition

2016 5th International Conference on Multimedia Computing and Systems (ICMCS), 2016

Radial Charlier moments as discrete orthogonal moments in the polar coordinate are better descrip... more Radial Charlier moments as discrete orthogonal moments in the polar coordinate are better descriptor in image processing applications and pattern recognition. However, the translation and scale invariant property of these moments have not been studied due to its complexity of the problem. In this paper, we present a method to construct a set of rotation invariants extracted from radial Charlier moments, named radial Charlier moment invariants (RCMI). Experimental results show the efficiency and the robustness to reconstruction error (MSE), peak signal to noise ratio (PSNR) of the proposed method.

Procedia Computer Science, 2019

In this paper, we propose a new model for 3D shape classification based on 3D image Racah moments... more In this paper, we propose a new model for 3D shape classification based on 3D image Racah moments and deep neural networks to enhance the classification accuracy and reduce the computational complexity of 3D object recognition. The proposed model is derived by introducing 3D image Racah moments as an input vector in deep neural network (DNN), ordinarily utilized in many applications of pattern recognition. Discrete Racah moments have the property to extract pertinent features from an image in lower orders, and with the effectiveness of the DNN, we can make up the proposed model. This work aims to investigate the classification capabilities of the proposed model on non-rigid 3D datasets. Experiment simulations are conducted on SHREC 2011 database to evaluate the performance of our proposed method. The obtained results indicate that the proposed model achieves high performance classification rates.

Multimedia Tools and Applications, 2017

In the original publication, the photo of Aissam Berrahou was missing including the photo and bio... more In the original publication, the photo of Aissam Berrahou was missing including the photo and biography of Hassan Qjidaa. The authors would like to present the missing photos and biography below.

2016 5th International Conference on Multimedia Computing and Systems (ICMCS), 2016

Car to Car Communication in VANET using Cooperative Mobility Services of the Future (CoMoSeF)

3D Research, 2017

In this paper, we introduce a new set of 3D weighed dual Hahn moments which are orthogonal on a n... more In this paper, we introduce a new set of 3D weighed dual Hahn moments which are orthogonal on a non-uniform lattice and their polynomials are numerically stable to scale, consequent, producing a set of weighted orthonormal polynomials. The dual Hahn is the general case of Tchebichef and Krawtchouk, and the orthogonality of dual Hahn moments eliminates the numerical approximations. The computational aspects and symmetry property of 3D weighed dual Hahn moments are discussed in details. To solve their inability to invariability of large 3D images, which cause to overflow issues, a generalized version of these moments noted 3D generalized weighed dual Hahn moment invariants are presented where whose as linear combination of regular geometric moments. For 3D pattern recognition, a generalized expression of 3D weighted dual Hahn moment invariants, under translation, scaling and rotation transformations, have been proposed where a new set of 3D-GWDHMIs have been provided. In experimental studies, the local and global capability of free and noisy 3D image reconstruction of the 3D-WDHMs has been compared with other orthogonal moments such as 3D Tchebichef and 3D Krawtchouk moments using Princeton Shape Benchmark database. On pattern recognition using the 3D-GWDHMIs like 3D object descriptors, the experimental results confirm that the proposed algorithm is more robust than other orthogonal moments for pattern classification of 3D images with and without noise. Keywords 3D weighted dual Hahn moments Á 3D pattern recognition Á 3D Image reconstruction Á 3D weighted dual Hahn moment invariants

Neural Computing and Applications, 2016

In this work, we propose new sets of 2D and 3D rotation invariants based on orthogonal radial dua... more In this work, we propose new sets of 2D and 3D rotation invariants based on orthogonal radial dual Hahn moments, which are orthogonal on a non-uniform lattice. We also present theoretical mathematics to derive them. Thus, this paper presents in the first case new 2D radial dual Hahn moments based on polar representation of an image by one-dimensional orthogonal discrete dual Hahn polynomials and a circular function. The dual Hahn polynomials are general case of Tchebichef and Krawtchouk polynomials. In the second case, we introduce new 3D radial dual Hahn moments employing a spherical representation of volumetric image by one-dimensional orthogonal discrete dual Hahn polynomials and a spherical function, which are orthogonal on a non-uniform lattice. The 2D and 3D rotational invariants are extracts from the proposed 2D and 3D radial dual Hahn moments respectively. In order to test the proposed approach, three problems namely image reconstruction, rotational invariance and pattern recognition are attempted using the proposed moments. The result of experiments shows that the radial dual Hahn moments have performed better than the radial Tchebichef and Krawtchouk moments, with and without noise. Simultaneously, the mentioned reconstruction converges quickly to the original image using 2D and 3D radial dual Hahn moments, and the test images are clearly recognized from a set of images that are available in COIL-20 database for 2D image and PSB database for 3D image. Keywords Radial dual Hahn moments Á 3D image Á 2D and 3D rotation invariants Á Classification Á Recognition

Fast and efficient computation of three-dimensional Hahn moments

Journal of Electronic Imaging, 2016

Abstract. We propose an algorithm for fast computation of three-dimensional (3-D) Hahn moments. F... more Abstract. We propose an algorithm for fast computation of three-dimensional (3-D) Hahn moments. First, the symmetry property of Hahn polynomials is provided to decrease the computational complexity at 12%. Second, 3-D Hahn moments are computed by using an algorithm based on matrix multiplication. The proposed algorithm enormously reduces the computational complexity of a 3-D Hahn moment and its inverse moment transform. It can be also implemented easily for high order of moments. The performance of the proposed algorithm is proved through object reconstruction experiments. The experimental results and complexity analysis show that the proposed method outperforms the straightforward method, especially for large size noise-free and noisy 3-D objects.

An Algorithm for Fast Computation of 3D Krawtchouk Moments for Volumetric Image Reconstruction

Lecture Notes in Electrical Engineering, 2016

Discrete Krawtchouk moments are powerful tools in the field of image processing application and p... more Discrete Krawtchouk moments are powerful tools in the field of image processing application and pattern recognition. In this paper we propose an efficient method based on matrix multiplication and symmetry property to compute 3D Krawtchouk moments. This new method is used to reduce the complexity and computational time for 3D object reconstruction. The validity of the proposed algorithm is proved by simulated experiments using volumetric image.

WSEAS Transactions on Computers

Discrete Tchebichef moments are wid ely used in the field of image processing application and pat... more Discrete Tchebichef moments are wid ely used in the field of image processing application and pattern recognition. In this paper we propose a compact method of 3D Tchebichef moments computation. This new method based on Clenshaw's recurrence formula and the symmetry property produces a drastic reduction in the complexity and computational time. The recursive algorithm is then developed for fast computation of inverse Tchebichef moments transform for image reconstruction. We also extract scale and translation 3D moment invariants using a proposed direct method. The validity of the proposed algorithm is prov ed by simulated experiments using 3D image/Object.

Fast Computation of Krawtchouk Moments For 3D object reconstruction

WSEAS Transactions on Circuits and Systems

Discrete Tchebichef moments are widely used in the field of image processing application and patt... more Discrete Tchebichef moments are widely used in the field of image processing application and pattern recognition. In this paper we propose a compact method of 3D Tchebichef moments computation. This new method based on Clenshaw's recurrence formula and the symmetry property produces a drastic reduction in the complexity and computational time. The recursive algorithm is then developed for fast computation of inverse Tchebichef moments transform for image reconstruction. We also extract scale and translation 3D moment invariants using a proposed direct method. The validity of the proposed algorithm is proved by simulated experiments using 3D image/Object

Translation and scale invariants of three-dimensional Tchebichef moments

2015 Intelligent Systems and Computer Vision (ISCV), 2015

ABSTRACT

Multimedia Tools and Applications, 2020

In this paper, we propose a new model based on 3D discrete orthogonal moments and deep neural net... more In this paper, we propose a new model based on 3D discrete orthogonal moments and deep neural networks (DNN) to improve the classification accuracy of 3D objects under geometric transformations and noise. However, the utilization of moment invariants presents some drawbacks: They can't describe the object efficiently, and their computation process is time consuming. Discrete orthogonal moments have the property to extract pertinent features from an image even in lower orders and are robust to noise. The main goal of this work is to investigate the robustness of the proposed model to geometric transformations like translation, scale and rotation and noisy conditions. The experiment simulations are conducted on datasets formed by applying some geometric transformations and noise on selected objects from McGill database. The obtained results indicate that the proposed model achieves high performance classification rates, robust to geometric transformations and noise degradation than other methods based on moment invariants.

Rigid and non-rigid 3D shape classification based on 3D Hahn moments neural networks model

Multimedia Tools and Applications

3D Shape Classification Using 3D Discrete Moments and Deep Neural Networks

Proceedings of the 2nd International Conference on Networking, Information Systems & Security - NISS19

In this paper, we propose a new model for 3D shape classification based on 3D discrete orthogonal... more In this paper, we propose a new model for 3D shape classification based on 3D discrete orthogonal moments and deep neural network (DNN) to enhance the classification accuracy of 3D objects under geometric transformations such as scale and rotation. The proposed model is derived by introducing image moments as an input vector in DNN, frequently utilized in many tasks of pattern recognition. Discrete orthogonal moments have the ability to capture global information from an image in lower orders. The aim of this work is to investigate the robustness of the proposed model to geometric transformations like rotation and scale. The simulations are performed on constructed dataset by applying some geometric transformations on selected objects from the McGill database to evaluate the performance of our proposed model. The obtained results show that the proposed model with Hahn moments achieves high classification rates and robust to geometric transformations than Krawtchouk moments.

Efficient color face recognition based on quaternion discrete orthogonal moments neural networks

Multimedia Tools and Applications, 2022

3D Object Classification using 3D Racah Moments Convolutional Neural Networks

Proceedings of the 2nd International Conference on Networking, Information Systems & Security - NISS19, 2019

In this paper, we propose a new architecture of deep neural network called 3D Racah Moments Convo... more In this paper, we propose a new architecture of deep neural network called 3D Racah Moments Convolutional Neural Network (3D RMCNN) to improve the classification accuracy and reduce the computational complexity of a 3D pattern recognition system. The proposed architecture consists of fusioning the concepts of image Racah moments and convolutional neural network (CNN), largely utilized in pattern recognition applications. Indeed, the advantages of the moments concerning their global information coding mechanism even in lower orders, along with the high effectiveness of the CNN, are combined to make up the proposed robust network. The aim of this work is to investigate the classification capabilities of 3D RMCNN on 3D shape datasets. The experiment simulations with 3D RMCNN have been performed on SHREC 2011 and ModelNet10 databases. The obtained results show high performance in the classification accuracy of the proposed model and its ability to decrease the computational cost by training low number of features generated by the first moment layer.

Color Face Recognition by Using Quaternion and Deep Neural Networks

2019 International Conference on Wireless Technologies, Embedded and Intelligent Systems (WITS), 2019

In this paper we propose a new model for color face recognition based on quaternion number and de... more In this paper we propose a new model for color face recognition based on quaternion number and deep neural networks (DNN), to enhance the classification accuracy of color face recognition. The proposed model is derived by introducing image represented in quaternion domain as an input vector in DNN model, frequently, utilized in many vision tasks of pattern recognition. The utilization of quaternion representation (QR) aims to reduce the size of input vector and consequently the computational complexity. On the other hand, color information from the image while obtaining best classification results. The simulations results are performed on color face databases to demonstrate the effectiveness of the proposed model. The obtained results show that they outperform other existing algorithms.

Automobile Insurance Claims Auditing: A Comprehensive Survey on Handling Awry Datasets

Lecture Notes in Electrical Engineering, 2021

Fraud is a very costly criminal activity. Insurance companies face the very challenging task of i... more Fraud is a very costly criminal activity. Insurance companies face the very challenging task of identifying and preventing fraudulent claims. Just like any big problem in recent years, Machine Learning has been heavily applied to fraud detection in both a supervised and non-supervised manner. But, usually supervised models do not perform well in the presence of awry, asymmetrical Datasets. This paper presents a novel approach for auditing claims in automobile insurance. Our data pipeline consists of preprocessing, feature selection, data balancing, and classification. This robust fraud detection model, built upon existing fraud detection research, gives very promising results compared to state of the art in the industry.

Non-rigid 3D Model Classification Using 3D Hahn Moment Convolutional Neural Networks

In this paper, we propose a new architecture of 3D deep neural network called 3D Hahn Moments Con... more In this paper, we propose a new architecture of 3D deep neural network called 3D Hahn Moments Convolutional Neural Network (3D HMCNN) to enhance the classification accuracy and reduce the computational complexity of a 3D pattern recognition system. The proposed architecture is derived by combining the concepts of image Hahn moments and convolutional neural network (CNN), frequently utilized in pattern recognition applications. Indeed, the advantages of the moments concerning their global information coding mechanism even in lower orders, along with the high effectiveness of the CNN, are combined to make up the proposed robust network. The aim of this work is to investigate the classification capabilities of 3D HMCNN on small 3D datasets. The experiment simulations with 3D HMCNN have been performed on the articulated parts of McGill 3D shape Benchmark database and SHREC 2011 database. The obtained results show the significantly high performance in the classification rates of the prop...

Radial Charlier moment invariants for 2D object/image recognition

2016 5th International Conference on Multimedia Computing and Systems (ICMCS), 2016

Radial Charlier moments as discrete orthogonal moments in the polar coordinate are better descrip... more Radial Charlier moments as discrete orthogonal moments in the polar coordinate are better descriptor in image processing applications and pattern recognition. However, the translation and scale invariant property of these moments have not been studied due to its complexity of the problem. In this paper, we present a method to construct a set of rotation invariants extracted from radial Charlier moments, named radial Charlier moment invariants (RCMI). Experimental results show the efficiency and the robustness to reconstruction error (MSE), peak signal to noise ratio (PSNR) of the proposed method.

Procedia Computer Science, 2019

In this paper, we propose a new model for 3D shape classification based on 3D image Racah moments... more In this paper, we propose a new model for 3D shape classification based on 3D image Racah moments and deep neural networks to enhance the classification accuracy and reduce the computational complexity of 3D object recognition. The proposed model is derived by introducing 3D image Racah moments as an input vector in deep neural network (DNN), ordinarily utilized in many applications of pattern recognition. Discrete Racah moments have the property to extract pertinent features from an image in lower orders, and with the effectiveness of the DNN, we can make up the proposed model. This work aims to investigate the classification capabilities of the proposed model on non-rigid 3D datasets. Experiment simulations are conducted on SHREC 2011 database to evaluate the performance of our proposed method. The obtained results indicate that the proposed model achieves high performance classification rates.

Multimedia Tools and Applications, 2017

In the original publication, the photo of Aissam Berrahou was missing including the photo and bio... more In the original publication, the photo of Aissam Berrahou was missing including the photo and biography of Hassan Qjidaa. The authors would like to present the missing photos and biography below.

2016 5th International Conference on Multimedia Computing and Systems (ICMCS), 2016

Car to Car Communication in VANET using Cooperative Mobility Services of the Future (CoMoSeF)

3D Research, 2017

In this paper, we introduce a new set of 3D weighed dual Hahn moments which are orthogonal on a n... more In this paper, we introduce a new set of 3D weighed dual Hahn moments which are orthogonal on a non-uniform lattice and their polynomials are numerically stable to scale, consequent, producing a set of weighted orthonormal polynomials. The dual Hahn is the general case of Tchebichef and Krawtchouk, and the orthogonality of dual Hahn moments eliminates the numerical approximations. The computational aspects and symmetry property of 3D weighed dual Hahn moments are discussed in details. To solve their inability to invariability of large 3D images, which cause to overflow issues, a generalized version of these moments noted 3D generalized weighed dual Hahn moment invariants are presented where whose as linear combination of regular geometric moments. For 3D pattern recognition, a generalized expression of 3D weighted dual Hahn moment invariants, under translation, scaling and rotation transformations, have been proposed where a new set of 3D-GWDHMIs have been provided. In experimental studies, the local and global capability of free and noisy 3D image reconstruction of the 3D-WDHMs has been compared with other orthogonal moments such as 3D Tchebichef and 3D Krawtchouk moments using Princeton Shape Benchmark database. On pattern recognition using the 3D-GWDHMIs like 3D object descriptors, the experimental results confirm that the proposed algorithm is more robust than other orthogonal moments for pattern classification of 3D images with and without noise. Keywords 3D weighted dual Hahn moments Á 3D pattern recognition Á 3D Image reconstruction Á 3D weighted dual Hahn moment invariants

Neural Computing and Applications, 2016

In this work, we propose new sets of 2D and 3D rotation invariants based on orthogonal radial dua... more In this work, we propose new sets of 2D and 3D rotation invariants based on orthogonal radial dual Hahn moments, which are orthogonal on a non-uniform lattice. We also present theoretical mathematics to derive them. Thus, this paper presents in the first case new 2D radial dual Hahn moments based on polar representation of an image by one-dimensional orthogonal discrete dual Hahn polynomials and a circular function. The dual Hahn polynomials are general case of Tchebichef and Krawtchouk polynomials. In the second case, we introduce new 3D radial dual Hahn moments employing a spherical representation of volumetric image by one-dimensional orthogonal discrete dual Hahn polynomials and a spherical function, which are orthogonal on a non-uniform lattice. The 2D and 3D rotational invariants are extracts from the proposed 2D and 3D radial dual Hahn moments respectively. In order to test the proposed approach, three problems namely image reconstruction, rotational invariance and pattern recognition are attempted using the proposed moments. The result of experiments shows that the radial dual Hahn moments have performed better than the radial Tchebichef and Krawtchouk moments, with and without noise. Simultaneously, the mentioned reconstruction converges quickly to the original image using 2D and 3D radial dual Hahn moments, and the test images are clearly recognized from a set of images that are available in COIL-20 database for 2D image and PSB database for 3D image. Keywords Radial dual Hahn moments Á 3D image Á 2D and 3D rotation invariants Á Classification Á Recognition

Fast and efficient computation of three-dimensional Hahn moments

Journal of Electronic Imaging, 2016

Abstract. We propose an algorithm for fast computation of three-dimensional (3-D) Hahn moments. F... more Abstract. We propose an algorithm for fast computation of three-dimensional (3-D) Hahn moments. First, the symmetry property of Hahn polynomials is provided to decrease the computational complexity at 12%. Second, 3-D Hahn moments are computed by using an algorithm based on matrix multiplication. The proposed algorithm enormously reduces the computational complexity of a 3-D Hahn moment and its inverse moment transform. It can be also implemented easily for high order of moments. The performance of the proposed algorithm is proved through object reconstruction experiments. The experimental results and complexity analysis show that the proposed method outperforms the straightforward method, especially for large size noise-free and noisy 3-D objects.

An Algorithm for Fast Computation of 3D Krawtchouk Moments for Volumetric Image Reconstruction

Lecture Notes in Electrical Engineering, 2016

Discrete Krawtchouk moments are powerful tools in the field of image processing application and p... more Discrete Krawtchouk moments are powerful tools in the field of image processing application and pattern recognition. In this paper we propose an efficient method based on matrix multiplication and symmetry property to compute 3D Krawtchouk moments. This new method is used to reduce the complexity and computational time for 3D object reconstruction. The validity of the proposed algorithm is proved by simulated experiments using volumetric image.

WSEAS Transactions on Computers

Discrete Tchebichef moments are wid ely used in the field of image processing application and pat... more Discrete Tchebichef moments are wid ely used in the field of image processing application and pattern recognition. In this paper we propose a compact method of 3D Tchebichef moments computation. This new method based on Clenshaw's recurrence formula and the symmetry property produces a drastic reduction in the complexity and computational time. The recursive algorithm is then developed for fast computation of inverse Tchebichef moments transform for image reconstruction. We also extract scale and translation 3D moment invariants using a proposed direct method. The validity of the proposed algorithm is prov ed by simulated experiments using 3D image/Object.

Fast Computation of Krawtchouk Moments For 3D object reconstruction

WSEAS Transactions on Circuits and Systems

Discrete Tchebichef moments are widely used in the field of image processing application and patt... more Discrete Tchebichef moments are widely used in the field of image processing application and pattern recognition. In this paper we propose a compact method of 3D Tchebichef moments computation. This new method based on Clenshaw's recurrence formula and the symmetry property produces a drastic reduction in the complexity and computational time. The recursive algorithm is then developed for fast computation of inverse Tchebichef moments transform for image reconstruction. We also extract scale and translation 3D moment invariants using a proposed direct method. The validity of the proposed algorithm is proved by simulated experiments using 3D image/Object

Translation and scale invariants of three-dimensional Tchebichef moments

2015 Intelligent Systems and Computer Vision (ISCV), 2015

ABSTRACT

Multimedia Tools and Applications, 2020

In this paper, we propose a new model based on 3D discrete orthogonal moments and deep neural net... more In this paper, we propose a new model based on 3D discrete orthogonal moments and deep neural networks (DNN) to improve the classification accuracy of 3D objects under geometric transformations and noise. However, the utilization of moment invariants presents some drawbacks: They can't describe the object efficiently, and their computation process is time consuming. Discrete orthogonal moments have the property to extract pertinent features from an image even in lower orders and are robust to noise. The main goal of this work is to investigate the robustness of the proposed model to geometric transformations like translation, scale and rotation and noisy conditions. The experiment simulations are conducted on datasets formed by applying some geometric transformations and noise on selected objects from McGill database. The obtained results indicate that the proposed model achieves high performance classification rates, robust to geometric transformations and noise degradation than other methods based on moment invariants.