hossein ebrahimnezhad | Sahand University of Tec. (original) (raw)

Uploads

Papers by hossein ebrahimnezhad

2014 4th International Conference on Computer and Knowledge Engineering (ICCKE), 2014

In this paper a method is developed to estimate human articulated body parts bending motion based... more In this paper a method is developed to estimate human articulated body parts bending motion based on Dictionary-Learning Sparse Representation (DLSR). The extracted features for training the dictionary are achieved by deformation gradient of proposed part, which is the non-translation portion of an affine transformation that determines the change between original shape and deformed shape. In order to train the dictionary for motion classification, we minimize the reconstruction error of the target shape. Then, all trained dictionaries from motion classes are combined to construct an over-complete dictionary for sparse representation and classification. We evaluate our approach to different topological structure of human arm and leg shape. The experimental results show the effectiveness of our approach for treating the bending motion classification in different images.

International journal of information and communication technology research, Dec 30, 2011

In this paper, we propose a novel geometric features based method to categorize 3D models using p... more In this paper, we propose a novel geometric features based method to categorize 3D models using probabilistic neural network and support vector machine classifiers. The employed features are extracted from face and vertex characteristics. In addition, we utilize the proposed features in 3D object retrieval. To achieve this end, each model is decomposed into a set of local/global geometrical features. We use histograms of two variables, i.e., deviation angle of normal vector on the object surface point from the vector that connect shape center to that point; and distance of object surface point from shape center. To achieve better separability of different models, mutual Euclidean distance histogram for the pairs of surface points is also used. The most advantage of using histogram to represent the features is that it shows the density of data and enables creating of low dimensional feature vector and consequently decreasing of computational cost in classification process. The effectiveness of our proposed 3D object categorization system has been evaluated on the generalized McGill 3D model dataset in terms of both accuracy and speed measures. Widespread experimental results and comparison with the other similar methods, demonstrate efficiency of the proposed approach to improve both accuracy and speed of categorization system.

Signal and Data Processing, Sep 15, 2014

IEEE Conference Proceedings, 2019

Head pose estimation has many applications in the field of computer vision and it is a useful par... more Head pose estimation has many applications in the field of computer vision and it is a useful part of pose-invariant face recognition. In this paper, we propose a novel method to estimate head pose (yaw and pitch rotations) based on fuzzy systems by facial geometric features. Firstly, seven certain points are selected on face. These points includes some main properties. They are all visible even for large pose variations. Since no point is selected on mouth region, obviously this method is insensitive to facial expression. By these points, some ratios and angles are computed as the inputs of two fuzzy systems. The output data of these systems are the corresponding yaw and pitch angles. After training them and determining some parameters, they are used for head yaw and pitch estimation. This method is evaluated on two databases and the experimental results demonstrate that our proposed method is strongly accurate, robust, and beneficial for head pose estimation.

Journal of Ambient Intelligence and Humanized Computing, Nov 5, 2021

Journal of Information Systems and Telecommunication (JIST), Mar 1, 2015

International Journal on Artificial Intelligence Tools, Jun 1, 2016

In this paper, a novel shape descriptor for shape recognition is proposed. An evolutionary proces... more In this paper, a novel shape descriptor for shape recognition is proposed. An evolutionary process is introduced in which a contour is reconstructed from the bounding circle of the shape. In this evolutionary process, circle points always move toward the shape in normal direction until they arrive at the shape contour. Three different descriptors are extracted from this process: the first descriptor is defined as the number of steps that every circle point should pass from circle to shape contour which is called evolution steps (ES). The second descriptor is considered as the boundary distance (BD) of the sample points at the end of the evolution process. The third descriptor is the mean of curvature of the evolution lines that are created by moving points, (MCEL). In matching stage, dynamic programming is employed to best matching between shapes. Finally, normalizing the features makes them to be invariant to scale. Sparse representation as a new framework for classification is applied in the recognition stage. The proposed descriptors are evaluated for task of shape recognition on several data sets. Experimental results demonstrate the advantaged performance of the proposed method in shape recognition.

3D research, Jan 10, 2018

Multimedia Tools and Applications, Jul 2, 2015

In this paper, a new steganography scheme with high embedding payload and good visual quality is ... more In this paper, a new steganography scheme with high embedding payload and good visual quality is presented. Before embedding process, secret information is encoded as a block using Reed-Muller error correction code. After data encoding and embedding into the low-order bits of the host image, modulus function is used to increase the visual quality of stego image. Since the proposed method is able to embed secret information into more significant bits of the image, it has improved embedding payload. The steps of extracting data from the host image are independent of the original image. Therefore, the proposed algorithm has a blind detection process which is more suitable for practical and online applications. The simulation results show that the proposed algorithm is also able to retrieve destroyed data by intentional or unintentional attacks such as the addition of noise and filtering due to the use of the error correction code. In addition, the payload is improved in comparison with...

Multimedia Tools and Applications

Materials Today Communications

Journal of Visualization, 2022

Journal of Intelligent Procedures in Electrical Technology, 2012

Today, the connection between human and computer is possible using mouse, keyboard and etc. These... more Today, the connection between human and computer is possible using mouse, keyboard and etc. These devices have some limitations like application speed. Making easy the interaction between human and computer is final objective of technology. In this paper, we propose one method for gesture recognition using curvature of B-Spline curves. First, the image of hand is extracted from different frames and some numbers of points are selected on the contour of hand in equal distances. Then, B-spline curves for groups of 4 points are calculated. Next, the slope of curvature for B-spline curves is calculated and used as feature vector of HMM classifier. The proposed method is inariant to rotation, movement and size of image because of using the slope of curvature. The results on 15 video sequences (with 150 frames in average) give recognition rate of 92.21%.