In this paper, the design of a parallel architecture for on-line face recognition using weighted modular principal component analysis (WMPCA) and its system-on-programmable-chip (SoPC) implementation are discussed. Th...
详细信息
In this paper, the design of a parallel architecture for on-line face recognition using weighted modular principal component analysis (WMPCA) and its system-on-programmable-chip (SoPC) implementation are discussed. The WMPCA methodology, proposed by us earlier, is based on the assumption that the rates of variation of the different regions of a face are different due to variations in expression and illumination. Given a database of sample faces for training and a query face for recognizing, the WMPCA methodology involves division of the face into horizontal regions. Each of these regions are analyzed independently by computing the eigenfeatures and comparing the same with the corresponding eigenfeatures of the faces stored in the sample database to calculate the corresponding error. The final decision of the face recognizer is based on the weighted sum of the errors computed from each of the regions. These weights are calculated based on the extent to which the various samples of the subject are spread in the eigenspace. The WMPCA methodology has a better recognition rate compared to the modular PCA approach developed by Rajkiran and Vijayan [Rajkiran, G., Vijayan, K., 2004. An improved face recognition technique based on modular PCA approach. Pattern Recognition Letters, 25(4), 429-436]. The methodology also has a wide scope for parallelism. We present an architecture that exploits this parallelism and implement the same as a system-on-programmable-chip on an ALTERA based field programmable gate array (FPGA) platform. The implementation has achieved a processing speed of about 26 frames per second at an operating frequency of 33.33 MHz. (c) 2006 Elsevier B.V. All rights reserved.
In this paper the concept of pixel wise feature extraction for texture segmentation has been extended to block wise feature extraction with the addition of contextual information. A comparative study has been made amo...
详细信息
ISBN:
(纸本)9781601320438
In this paper the concept of pixel wise feature extraction for texture segmentation has been extended to block wise feature extraction with the addition of contextual information. A comparative study has been made among different texture feature extraction techniques with this concept. Computational burden is small due to processing in non overlapping blocks. It has been observed that Circular Gabor filter followed by DCT gives the best performance. The results have been validated in presence of noise.
It is not a surprise that imageprocessing is a growing research field. vision in general and images in particular have always played an important and essential role in human life. Not only as a way to communicate, bu...
详细信息
ISBN:
(纸本)9783540770459
It is not a surprise that imageprocessing is a growing research field. vision in general and images in particular have always played an important and essential role in human life. Not only as a way to communicate, but also for commercial, scientific, industrial and military applications. Many techniques have been introduced and developed to deal with all the challenges involved with imageprocessing. In this paper, we will focus on techniques that find their origin in fuzzy set theory and fuzzy logic. We will show the possibilities of fuzzy logic in applications such as image retrieval, morphology and noise reduction by discussing some examples. Combined with other state-of-the-art techniques they deliver a useful contribution to current research.
image fusion is the process whereby images or some of their features from various modalities are merged to provide a more complete picture of a scene or object under identification. Fusion of images obtained from two ...
详细信息
ISBN:
(纸本)9781601320438
image fusion is the process whereby images or some of their features from various modalities are merged to provide a more complete picture of a scene or object under identification. Fusion of images obtained from two different modalities of a real world object has been reported in this paper. In the first case, the images are taken while the object is subjected to scanning by a laser beam. In the second case, the image is taken while the object is under ambient illumination. Edge maps are extracted in both the cases by appropriate techniques. Fusion of both the edge maps is achieved with the help of affine transformation. Combined visualization has the potential to provide more information than the individual data sets as it takes the advantage of individual strength of each mode.
Because of increase in biometric authentication, it is important to maintain the security of the biometrie samples. It is here where watermarking comes in play, empowering the biometrie authentication system and secur...
详细信息
ISBN:
(纸本)9781601320438
Because of increase in biometric authentication, it is important to maintain the security of the biometrie samples. It is here where watermarking comes in play, empowering the biometrie authentication system and securing biometrie data stored in the databases. In this paper, an application of watermarking is presented i.e. to secure electronic biometrie signatures using digital watermarking techniques. The performance of the schemes is compared in terms of bit embedding capacity and detector's performance. The first two schemes are a based on least significant bit plane watermarking. The third watermarking scheme is the based on the Fourier descriptor watermarking technique (FDWM). Here, we also propose and analyze a generic biometrie authentication system using watermarking security. In our work we found that the receiver operating characteristic (ROC) of the verification algorithm is very slightly or not perturbed due to watermarking of input and the template signatures stored in the database.
The mean shift algorithm has been proved to be efficient for tracking 2D blobs through a video sequence. Even so, this algorithm has certain inherent disadvantages. In this paper, we propose a robust tracking algorith...
详细信息
This paper proposes a new method for using implicit user feedback from clickthrough data to provide personalized ranking of results in a video retrieval system. The annotation based search is complemented with a featu...
详细信息
ISBN:
(纸本)9781595937827
This paper proposes a new method for using implicit user feedback from clickthrough data to provide personalized ranking of results in a video retrieval system. The annotation based search is complemented with a feature based ranking in our approach. The ranking algorithm uses belief revision in a Bayesian Network, which is derived from a multimedia ontology that captures the probabilistic association of a concept with expected video features. We have developed a content model for videos using discrete feature states to enable Bayesian reasoning and to alleviate on-line feature processing overheads. We propose a reinforcement learning algorithm for the parameters of the Bayesian Network with the implicit feedback obtained from the clickthrough data. Copyright 2007 ACM.
image and video filtering is a key image-processing task in computervision especially in noisy environment. In most of the cases the noise source is unknown and hence posses a major difficulty in the filtering operat...
详细信息
ISBN:
(纸本)9781424404759
image and video filtering is a key image-processing task in computervision especially in noisy environment. In most of the cases the noise source is unknown and hence posses a major difficulty in the filtering operation. In this paper we present an error-correction based learning approach for iterative filtering. A new FIR filter is designed in which the filter coefficients are updated based on Widrow-Hoff rule. Unlike the standard filter the proposed filter has the ability to remove noise without the a priori knowledge of the noise. Experimental result shows that the proposed filter efficiently removes the noise and preserves the edges in the image. We demonstrate the capability of the proposed algorithm by testing it on standard images infected by Gaussian noise and on a real time video containing inherent noise. Experimental result shows that the proposed filter is better than some of the existing standard filters.
The shapes of many natural and man-made objects have planar and curvilinear surfaces. The images of such curves usually do not have sufficient distinctive features to apply conventional feature-based reconstruction al...
详细信息
ISBN:
(纸本)0819461067
The shapes of many natural and man-made objects have planar and curvilinear surfaces. The images of such curves usually do not have sufficient distinctive features to apply conventional feature-based reconstruction algorithms. In this paper, we describe a method of reconstruction of a quadratic curve in 3-D space as an intersection of two cones containing the respective projected curve images. The correspondence between this pair of projections of the curve is assumed to be established in this work. Using least-square curve fitting, the parameters of a curve in 2-D space are found. From this we are reconstructing the 3-D quadratic curve. Relevant mathematical formulations and analytical solutions for obtaining the equation of reconstructed curve are given. The result of the described reconstruction methodology are studied by simulation studies. This reconstruction methodology is applicable to LBW decision in cricket. path of the missile. Robotic vision, path planning etc.
In this paper a novel method for learning based image super resolution (SR) is presented. The basic idea is to bridge the gap between a set of low resolution (LR) images and the corresponding high resolution (HR) imag...
详细信息
ISBN:
(纸本)076952334X
In this paper a novel method for learning based image super resolution (SR) is presented. The basic idea is to bridge the gap between a set of low resolution (LR) images and the corresponding high resolution (HR) image using both the SR reconstruction constraint and a patch based image synthesis constraint in a general probabilistic framework. We show that in this framework, the estimation of the LR image formation parameters is straightforward. The whole framework is implemented via an annealed Gibbs sampling method. Experiments on SR on both single image and image sequence input show that the proposed method provides an automatic and stable way to compute super-resolution and the achieved result is encouraging for both synthetic and real LR images.
暂无评论