The Experts below are selected from a list of 306 Experts worldwide ranked by ideXlab platform
Xiaoyan Sun - One of the best experts on this subject based on the ideXlab platform.
-
image compression by visual Pattern Vector quantization vpvq
Data Compression Conference, 2008Co-Authors: Xiaoyan SunAbstract:This paper proposes a new image compression scheme by introducing visual Patterns to nonlinear interpolative Vector quantization (IVQ). Input images are first distorted by a generic down-sampling so that some details are removed before compression. Then, the distorted images are compressed lossly by traditional image coding scheme and transmitted to the decoder. In the decoder side, VQ indices are extracted from the decoded images to reproduce the removed details from a pre-trained codebook. One of main contributions in this paper is, we introduce visual Patterns on designing the codebook, where only removed details that contain visual Patterns and their original counterparts as pairs are trained. Experimental results show: (1) visual Pattern blocks are easy to form clusters than original blocks; (2) the proposed scheme achieves much better performance over JPEG in terms of visual quality and PSNR.
-
DCC - Image Compression by Visual Pattern Vector Quantization (VPVQ)
Data Compression Conference (dcc 2008), 2008Co-Authors: Xiaoyan SunAbstract:This paper proposes a new image compression scheme by introducing visual Patterns to nonlinear interpolative Vector quantization (IVQ). Input images are first distorted by a generic down-sampling so that some details are removed before compression. Then, the distorted images are compressed lossly by traditional image coding scheme and transmitted to the decoder. In the decoder side, VQ indices are extracted from the decoded images to reproduce the removed details from a pre-trained codebook. One of main contributions in this paper is, we introduce visual Patterns on designing the codebook, where only removed details that contain visual Patterns and their original counterparts as pairs are trained. Experimental results show: (1) visual Pattern blocks are easy to form clusters than original blocks; (2) the proposed scheme achieves much better performance over JPEG in terms of visual quality and PSNR.
Khan M. Iftekharuddin - One of the best experts on this subject based on the ideXlab platform.
-
Statistical Pattern Recognition Using Gaussian Copula
Journal of Statistical Theory and Practice, 2015Co-Authors: Sumen Sen, Norou Diawara, Khan M. IftekharuddinAbstract:Statistical Pattern recognition has attracted great interest due to its applicability and to the advances in technology and computing. Significant research has been done in areas such as automatic character recognition, medical diagnostics, and data mining. The classical discrimination rule for Pattern recognition assumes normality. However, in real life this assumption is often questionable. In some situations, the Pattern Vector is a mixture of discrete and continuous random variables. In this article, we use copula densities to model class conditional distribution for Pattern recognition with Bayes’ decision rule. These types of densities are useful when the marginal densities of a Pattern Vector are not normally distributed. Those models are also useful for mixed Pattern Vectors. We also did simulations to compare the performance of the copula-based classifier with classical normal distribution based model and the independent-assumption-based model.
-
CIMSIVP - Recurrent network-based face recognition using image sequences
2009 IEEE Symposium on Computational Intelligence for Multimedia Signal and Vision Processing, 2009Co-Authors: Yong Ren, Khan M. Iftekharuddin, William E. WhiteAbstract:In this work, we propose a novel method for face recognition with large pose variations in image sequences using a Cellular Simultaneous Recurrent Network (CSRN).The pose problem is still a daunting challenge in face recognition. If the image sequences are obtained from different viewpoints in a surveillance type of application, the face recognition rate drops significantly. We formulate the recognition problem for face image sequences with large pose variation as an implicit temporal prediction task for CSRN. Further, to reduce the computational cost, we obtain eigenfaces for a set of image sequences for each person and use these reduced Pattern Vectors as the input to the CSRN. The CSRN is trained by this Pattern Vector, and each CSRN learns how to associate each face class/person in the training phase. When a new face is encountered, the corresponding image sequence is projected to each eigenface space to obtain the test Pattern Vectors. The Euclidian distances between successive frames of test and output Pattern Vectors indicate either a match or mismatch between the two corresponding face classes. We extensively evaluate our CSRN-based face recognition technique with 5 persons using publicly available VidTIMIT Audio-Video face dataset [1].In order to verify the performance of the CSRN, we also implement an Elman neural network for comparison. Our simulation shows that for this VidTIMIT Audio-Video face dataset with large pose variation, we can obtain an overall 65% (for rank 1) or 75% (for rank 2) face recognition accuracy better than the 55%(rank 1) recognition accuracy of Elman neural network.
Zygmunt Kuś - One of the best experts on this subject based on the ideXlab platform.
-
Weighted Pattern Vector for Object Tracking with the Use of Thermal Images
Advanced Technologies in Practical Applications for National Security, 2017Co-Authors: Zygmunt Kuś, Joanna Radziszewska, Aleksander NawratAbstract:The goal of the following paper was to devise a method of object tracking in a case when we have preliminary knowledge of an object. Tracking the object which state or some properties are known may be conducted with the Pattern Vector modification basing on this knowledge. The object which has the same visual images and different thermal images, depending on the time the object was moving, may be an example of the abovementioned case. One of such situations, presented as an example in the paper, was the change of the car engine temperature which modified the thermal image whereas the visual image was the same for different engine temperatures. In each moment during object tracking image processing system used thermal and visible images. The authors assumed that we acquire the visual and thermal images in each moment of object tracking. The Pattern Vectors of the tracked object based on the visual and thermal images were computed separately. The Pattern Vector and current feature Vector for an image of a given type were used to compute the distance between the object Pattern Vector and feature Vector calculated for a given location of the aperture. It was calculated for both: the visual and thermal images. The crux of the proposed method is the algorithm of setting the correct value of the weight with which the visual and thermal Pattern Vectors are used to calculate the distance. The authors proposed the method based on the knowledge about the object location in its initial position. The Pattern Vector calculated in this position was treated as a correct and unchangeable one. Assuming that the thermal Pattern Vector was more useful for object recognition, we proposed the method of increasing weight for a part of the Pattern Vector which part was based on a thermal image. Finally, this study presented the examples of the object recognition by means of the developed method.
-
Applying Colour Image-Based Indicator for Object Tracking
Advanced Technologies in Practical Applications for National Security, 2017Co-Authors: Zygmunt Kuś, Joanna Radziszewska, Jarosław Cymerski, Aleksander NawratAbstract:The goal of the following paper was to devise a method of object tracking with the application of the tracked objects’ coloured images. The proposed solution was based on the calculation of an indicator which described the colour features of the object. The ratio between the red and green components as well as the ratio between red and blue components were the indicators which defined these features. Moreover, the proposed approach was particularly useful in the cases when the object and terrain colours were significantly different. The abovementioned ratios were used to create the Pattern Vector. Such a defined Pattern Vector was used to calculate the error function and the minimum of this function indicated the object location. This paper presented the examples of object tracking for both: the different object colour from the terrain colour and the similar object colour to the terrain colour.
-
Dynamical Pattern Vector in Pattern Recognition with the Use of Thermal Images
MATEC Web of Conferences, 2016Co-Authors: Zygmunt KuśAbstract:The goal of the following paper was to develop the methodology of object tracking in adverse conditions. Suddenly appearing clouds, fog or smoke could be the examples of atmospheric conditions. We used thermal and visible images in each moment during object tracking. We computed the Pattern Vectors of the tracked object on the basis of the visual and thermal images separately. The Pattern Vector and current feature Vector for an image of a given type are used to compute the distance between the object Pattern Vector and feature Vector calculated for a given location of the aperture. It is calculated for both: the visual and thermal image. The crux of the proposed method was the algorithm of selection which distance (for visual or thermal image) was used for object tracking. It was obtained by multiplying the values of the distances between a Pattern Vector and current feature Vector by some coefficients (different for thermal and visual images). The values of these coefficients depended on the usefulness of a given type of an image for Pattern recognition. This usefulness was defined by the variability of the particular pixels in the image which is represented by calculating gradient in the image. On top of that, this study presented the examples of the object recognition by means of the developed method.
-
Adjusting the Thresholds to the Recognised Pattern in Order to Improve the Separation Between the Recognised Patterns
Studies in Systems Decision and Control, 2015Co-Authors: Zygmunt Kuś, Aleksander NawratAbstract:The aim of the following study was to examine the influence of image thresholding on the correctness of the Pattern recognition in the grey scale images. The method based on moment invariants, which were the elements of feature Vectors defining the features of the recognised object, was used by authors in order to recognise the objects. The paper presents the influence of image thresholding with histogram equalisation for exemplary images on the distribution of the distance between Pattern Vector and feature Vector for every pixel of an image. The authors have paid a great attention to the fact that proper selection of the thresholds is significant for distinguishing given object classes. One could conclude from the results that adjusting the value of the thresholds to grey levels, which were in a searched object, could considerably improve object recognition. The proposed method was based on the analysis of the part of the image obtained from a camera. We assumed that the camera was mounted on the UAV and it watched the objects moving on the ground. This part of the image was selected in this way that it contained only a tracked object. We computed the histogram of this part of the image, equalised this histogram and computed new thresholds on the basis of the equalised histogram. Next step was to threshold the abovementioned part of an image and then to compute a Pattern Vector for this thresholded image of the object. In this way we obtained Pattern Vector which was used to recognize the object in the whole image. Since we wanted to use the Pattern Vector obtained on the basis of thresholded object image, we had to threshold the whole image (a terrain with moving objects) with the same thresholds. The examples presented in the paper showed that image pre-processing based on thresholding might improve the accuracy of the Pattern recognition. It was achieved thanks to the thresholding which was conducted in a manner that guaranteed to distinguish features of the recognised object. In order to calculate the distance (ρ) between an object Pattern Vector and Pattern Vector obtained for a given point of the whole image, we used the Euclidean metric. We compared the values of the ρ obtained during recognition process which was conducted for both: the thresholded and original—not-thresholded image. The lower values of the ρ for the thresholded image meant that in this case the Pattern Vector described the features of the object better.
Sumen Sen - One of the best experts on this subject based on the ideXlab platform.
-
Statistical Pattern Recognition Using Gaussian Copula
Journal of Statistical Theory and Practice, 2015Co-Authors: Sumen Sen, Norou Diawara, Khan M. IftekharuddinAbstract:Statistical Pattern recognition has attracted great interest due to its applicability and to the advances in technology and computing. Significant research has been done in areas such as automatic character recognition, medical diagnostics, and data mining. The classical discrimination rule for Pattern recognition assumes normality. However, in real life this assumption is often questionable. In some situations, the Pattern Vector is a mixture of discrete and continuous random variables. In this article, we use copula densities to model class conditional distribution for Pattern recognition with Bayes’ decision rule. These types of densities are useful when the marginal densities of a Pattern Vector are not normally distributed. Those models are also useful for mixed Pattern Vectors. We also did simulations to compare the performance of the copula-based classifier with classical normal distribution based model and the independent-assumption-based model.
B. Awad - One of the best experts on this subject based on the ideXlab platform.
-
ICRA - A vision system for monitoring weld pool
Proceedings 1992 IEEE International Conference on Robotics and Automation, 1Co-Authors: D. Brzakovic, D.t. Khani, B. AwadAbstract:The authors describe a vision system that can monitor a weld pool in multipass arc-tungsten-gas welding. The system uses sequences of images acquired by a coaxial viewing where the optical axis coincides with the axis of the welding electrode. First, the system detects the weld pool edge by transforming an image such a way that a weld pool edge maps into a vertical curve that can easily be detected. Next, a weld pool is characterized by a Pattern Vector containing measurements pertaining to weld pool shape, size, and symmetry. The measurements were performed by using the detected weld pool edge. An analysis of a limited number of Pattern Vectors corresponding to normal and abnormal welding conditions indicates that such measurements have potential to be used in real-time weld pool monitoring and welding control. >
