scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Two dimensional synthetic face generation and verification using set estimation technique

01 Sep 2012-Computer Vision and Image Understanding (Academic Press)-Vol. 116, Iss: 9, pp 1022-1031
TL;DR: In this paper set estimation technique is applied for generation of 2D face images on the basis of inheriting features from inter and intra face classes in face space using nearest neighbor classifier.
Abstract: In this paper set estimation technique is applied for generation of 2D face images. The synthesis is done on the basis of inheriting features from inter and intra face classes in face space. Face images without artifacts and expressions are transformed to images with artifacts and expressions with the help of the developed methods. Most of the test images are generated using the proposed method. The measured PSNR values for the generated faces with respect to the training faces reflect the well accepted quality of the generated images. The generated faces are also classified properly to their respective face classes using nearest neighbor classifier. Validation of the method is demonstrated on AR and FIA datasets. Classification accuracy is increased when the new generated faces are added to the training set.
Citations
More filters
Proceedings ArticleDOI
TL;DR: An algorithm selection approach that permits to always use the most appropriate algorithm for the given input image by at first selecting an algorithm based on low level features such as color intensity, histograms, spectral coefficients.
Abstract: Natural Image processing and understanding encompasses hundreds or even thousands of different algorithms. Each algorithm has a certain peak performance for a particular set of input features and configurations of the objects/regions of the input image (environment). To obtain the best possible result of processing, we propose an algorithm selection approach that permits to always use the most appropriate algorithm for the given input image. This is obtained by at first selecting an algorithm based on low level features such as color intensity, histograms, spectral coefficients. The resulting high level image description is then analyzed for logical inconsistencies (contradictions) that are then used to refine the selection of the processing elements. The feedback created from the contradiction information is executed by a Bayesian Network that integrates both the features and a higher level information selection processes. The selection stops when the high level inconsistencies are all resolved or no more different algorithms can be selected.

12 citations

Journal ArticleDOI
01 Feb 2014
TL;DR: Fusion at feature level is considered here for the purpose of recognition, and new face images along with iris images are generated, and they are included in the training set.
Abstract: Multimodal biometrics has gained interest in the recent past due to its improved recognition rate over unibiometric and unimodal systems. Fusion at feature level is considered here for the purpose of recognition. The biometrics considered for fusion are face and iris. Here, new face images along with iris images are generated, and they are included in the training set. Feature-level fusion is incorporated. The recognition rates of the classification algorithm thus obtained are statistically found to be significantly better than the existing feature-level fusion and classification techniques.

10 citations

Journal ArticleDOI
TL;DR: This work proposes an algorithm selection approach that selects the best algorithm for a each input image and shows that the algorithm selected approach is ideally suited for either a hybrid type VLSI processor or for a Logic-In-Memory processing platform.
Abstract: Natural image processing and understanding encompasses hundreds of different algorithms Each algorithm generates best results for a particular set of input features and configurations of the objects/regions in the input image (environment) To obtain the best possible result of processing in a reliable manner, we propose an algorithm selection approach that selects the best algorithm for a each input image The proposed algorithm selection starts by first selecting an algorithm using low level features such as color intensity, histograms, spectral coefficients or so and a user given context if available The resulting high-level image description is analyzed for logical inconsistencies (contradictions) and image regions that must be processed using a different algorithm are selected The high-level description and the optional user-given context are used by a Bayesian Network to estimate the cause of the error in the processing The same Bayesian Network also generates new candidate algorithm for each region containing the contradiction in an iterative manner This iterative selection stops when the high-level inconsistencies are all resolved or no more different algorithms can be selected We also show that when inconsistencies can be detected, our framework is able to improve high-level description when compared with single algorithms In order for such complex and iterative processing being computationally tractable we also introduce a hardware platform based on reconfigurable VLSI that is well suited as the platform of the proposed approach We show that the algorithm selected approach is ideally suited for either a hybrid type VLSI processor or for a Logic-In-Memory processing platform

5 citations

Journal ArticleDOI
TL;DR: An intra-class threshold for multimodal biometric recognition procedure has been developed and is found to perform better than traditional ROC curve based threshold technique.
Abstract: Biometric recognition techniques attracted the researchers for the last two decades due to their many applications in the field of security. In recent times multimodal biometrics have been found to perform better, in several aspects, over unimodal biometrics. The classical approach for recognition is based on dissimilarity measure and for the sake of proper classification one needs to put a threshold on the dissimilarity value. In this paper an intra-class threshold for multimodal biometric recognition procedure has been developed. The authors' selection method of threshold is based on statistical set estimation technique which is applied on a minimal spanning tree and consisting of fused face and iris images. The fusion is performed here on feature level using face and iris biometrics. The proposed method, applied on several multimodal datasets, found to perform better than traditional ROC curve based threshold technique.

4 citations

Patent
28 Dec 2017
TL;DR: In this paper, the authors proposed a method for modifying the affective visual information in the field of vision of a user of the device. But the method is limited to a single image sensor (14) and one display (2).
Abstract: The invention relates to a method and to a device for modifying the affective visual information in the field of vision of a user of the device. Said device comprises at least one image sensor (14) and at least one display (2). The method comprises the following steps: Detecting an image in the field of vision of the device using an image sensor (14), carrying out a face recognition using the detected image for recognising at least one face, determining the position of the eyes and mouth of the detected face, calculating a superimposition area in the display (2) of the device in accordance with the determined positions of the eyes and mouth, superimposing the field of vision of a user of the device with alternative image data in the calculated superimposition of the display (2).
References
More filters
Journal ArticleDOI
Abstract: We describe a new method of matching statistical models of appearance to images. A set of model parameters control modes of shape and gray-level variation learned from a training set. We construct an efficient iterative matching algorithm by learning the relationship between perturbations in the model parameters and the induced image errors.

6,200 citations

01 Jan 1998

3,650 citations


"Two dimensional synthetic face gene..." refers methods in this paper

  • ...The face data bases used for experiment are AR [21] and FIA [22] databases....

    [...]

Journal Article

2,952 citations

Journal ArticleDOI
TL;DR: This paper presents a method for face recognition across variations in pose, ranging from frontal to profile views, and across a wide range of illuminations, including cast shadows and specular reflections, using computer graphics.
Abstract: This paper presents a method for face recognition across variations in pose, ranging from frontal to profile views, and across a wide range of illuminations, including cast shadows and specular reflections. To account for these variations, the algorithm simulates the process of image formation in 3D space, using computer graphics, and it estimates 3D shape and texture of faces from single images. The estimate is achieved by fitting a statistical, morphable model of 3D faces to images. The model is learned from a set of textured 3D scans of heads. We describe the construction of the morphable model, an algorithm to fit the model to images, and a framework for face identification. In this framework, faces are represented by model parameters for 3D shape and texture. We present results obtained with 4,488 images from the publicly available CMU-PIE database and 1,940 images from the FERET database.

2,187 citations


"Two dimensional synthetic face gene..." refers background in this paper

  • ...[3] proposed face recognition based on fitting a 3D morphable model with statistical texture....

    [...]

Journal ArticleDOI
TL;DR: A generalization of the convex hull of a finite set of points in the plane leads to a family of straight-line graphs, "alpha -shapes," which seem to capture the intuitive notions of "fine shape" and "crude shape" of point sets.
Abstract: A generalization of the convex hull of a finite set of points in the plane is introduced and analyzed. This generalization leads to a family of straight-line graphs, " \alpha -shapes," which seem to capture the intuitive notions of "fine shape" and "crude shape" of point sets. It is shown that a-shapes are subgraphs of the closest point or furthest point Delaunay triangulation. Relying on this result an optimal O(n \log n) algorithm that constructs \alpha -shapes is developed.

1,648 citations