Results 11 - 20
of
68
Sketch Based Face Recognition: Forensic vs. Composite Sketches
"... Facial sketches are widely used by law enforcement agencies to assist in the identification and apprehension of suspects involved in criminal activities. Sketches used in forensic investigations are either drawn by forensic artists (forensic sketches) or created with computer software (composite ske ..."
Abstract
-
Cited by 6 (4 self)
- Add to MetaCart
(Show Context)
Facial sketches are widely used by law enforcement agencies to assist in the identification and apprehension of suspects involved in criminal activities. Sketches used in forensic investigations are either drawn by forensic artists (forensic sketches) or created with computer software (composite sketches) following the verbal description provided by an eyewitness or the victim. These sketches are posted in public places and in media in hopes that some viewers will provide tips about the identity of the suspect. This method of identifying suspects is slow and tedious and may not lead to apprehension of the suspect. Hence, there is a need for a method that can automatically and quickly match facial sketches to large police mugshot databases. We address the problem of automatic facial sketch to mugshot matching and, for the first time, compare the effectiveness of forensic sketches and composite sketches. The contributions of this paper include: (i) a database containing mugshots and corresponding forensic and composite sketches that will be made available to interested researchers; (ii) a comparison of holistic facial representations versus component based representations for sketch to mugshot matching; and (iii) an analysis of the effect of filtering a mugshot gallery using three sources of demographic information (age, gender and race/ethnicity). Our experimental results show that composite sketches are matched with higher accuracy than forensic sketches to the corresponding mugshots. Both of the face representations studied here yield higher sketch to photo matching accuracy compared to a commercial face matcher. 1.
Portrait Painting Using Active Templates
"... Figure 1: Three portrait paintings rendered with different templates using our method. Their corresponding source photograph is in Fig.5. Notice: all painting images in this paper are best viewed on a color display at 400 % zoom unless annotated otherwise. Portraiture plays a substantial role in tra ..."
Abstract
-
Cited by 6 (2 self)
- Add to MetaCart
Figure 1: Three portrait paintings rendered with different templates using our method. Their corresponding source photograph is in Fig.5. Notice: all painting images in this paper are best viewed on a color display at 400 % zoom unless annotated otherwise. Portraiture plays a substantial role in traditional painting, yet it has not been studied in depth in painterly rendering research. The difficulty in rendering human portraits is due to our acute visual perception to the structure of human face. To achieve satisfactory results, a portrait rendering algorithm should account for facial structure. In this paper, we present an example-based method to render portrait paintings from photographs, by transferring brush strokes from previously painted portrait templates by artists. These strokes carry rich information about not only the facial structure but also how artists depict the structure with large and decisive brush strokes and vibrant colors. With a dictionary of portrait painting templates for different types of faces, we show that this method can produce satisfactory results.
Image Transformation based on Learning Dictionaries across Image Spaces
, 2012
"... In this paper, we propose a framework of transforming images from a source image space to a target image space, based on learning coupled dictionaries from a training set of paired images. The framework can be used for applications such as image super-resolution, and estimation of image intrinsic c ..."
Abstract
-
Cited by 6 (0 self)
- Add to MetaCart
(Show Context)
In this paper, we propose a framework of transforming images from a source image space to a target image space, based on learning coupled dictionaries from a training set of paired images. The framework can be used for applications such as image super-resolution, and estimation of image intrinsic components (shading and albedo). It is based on a local parametric regression approach, using sparse feature representations over learned coupled dictionaries across the source and target image spaces. After coupled dictionary learning, sparse coefficient vectors of training image patch pairs are partitioned into easily retrievable local clusters. For any test image patch, we can fast index into its closest local cluster and perform a local parametric regression between the learned sparse feature spaces. Obtained sparse representation (together with the learned target space dictionary) provides multiple constraints for each pixel of the target image to be estimated. The final target image is reconstructed based on these constraints. The contributions of our proposed framework are three-fold. (1) We propose a concept of coupled dictionary learning based on coupled sparse coding, which requires the sparse coefficient vectors of a pair of corresponding source and target image patches have the same support, i.e., the same indices of nonzero elements. (2) We devise a space partitioning scheme to divide the high-dimensional but sparse feature space into local clusters. The partitioning facilitates extremely fast retrieval of closest local clusters for query patches. (3) Benefiting from sparse feature based image transformation, our method is more robust to corrupted input data, and can be considered as a simultaneous image restoration and transformation process. Experiments on intrinsic image estimation and super-resolution demonstrate the effectiveness and efficiency of our proposed method.
Y.C.F.: Coupled dictionary and feature space learning with applications to cross-domain image synthesis and recognition
- In: ICCV. (2013
"... Cross-domain image synthesis and recognition are typi-cally considered as two distinct tasks in the areas of com-puter vision and pattern recognition. Therefore, it is not clear whether approaches addressing one task can be eas-ily generalized or extended for solving the other. In this paper, we pro ..."
Abstract
-
Cited by 6 (0 self)
- Add to MetaCart
(Show Context)
Cross-domain image synthesis and recognition are typi-cally considered as two distinct tasks in the areas of com-puter vision and pattern recognition. Therefore, it is not clear whether approaches addressing one task can be eas-ily generalized or extended for solving the other. In this paper, we propose a unified model for coupled dictionary and feature space learning. The proposed learning model not only observes a common feature space for associating cross-domain image data for recognition purposes, the de-rived feature space is able to jointly update the dictionaries in each image domain for improved representation. This is why our method can be applied to both cross-domain image synthesis and recognition problems. Experiments on a vari-ety of synthesis and recognition tasks such as single image super-resolution, cross-view action recognition, and sketch-to-photo face recognition would verify the effectiveness of our proposed learning model. 1.
Artistic Minimal Rendering with Lines and Blocks
"... Many non-photorealistic rendering techniques exist to produce artistic effects from given images. Inspired by various artists, interesting effects can be produced by using a minimal rendering, where the minimum refers to the number of tones as well as the number and complexity of the primitives used ..."
Abstract
-
Cited by 5 (3 self)
- Add to MetaCart
(Show Context)
Many non-photorealistic rendering techniques exist to produce artistic effects from given images. Inspired by various artists, interesting effects can be produced by using a minimal rendering, where the minimum refers to the number of tones as well as the number and complexity of the primitives used for rendering. Our method is based on various computer vision techniques, and uses a combination of refined lines and blocks (potentially simplified), as well as a small number of tones, to produce abstracted artistic rendering with sufficient elements from the original image. We also considered a variety of methods to produce different artistic styles, such as colour and two-tone drawings, and use semantic information to improve renderings for faces. By changing some intuitive parameters a wide range of visually pleasing results can be produced. Our method is fully automatic. We demonstrate the effectiveness of our method with extensive experiments and a user study. Key words: non-photorealistic rendering, line drawing, tonal blocks, image abstraction 1
Open Source Biometric Recognition
"... The biometrics community enjoys an active research field that has produced algorithms for several modalities suitable for real-world applications. Despite these developments, there exist few open source implementations of complete algorithms that are maintained by the community or deployed outside a ..."
Abstract
-
Cited by 5 (3 self)
- Add to MetaCart
(Show Context)
The biometrics community enjoys an active research field that has produced algorithms for several modalities suitable for real-world applications. Despite these developments, there exist few open source implementations of complete algorithms that are maintained by the community or deployed outside a laboratory environment. In this paper we motivate the need for more community-driven open source software in the field of biometrics and present OpenBR as a candidate to address this deficiency. We overview the OpenBR software architecture and consider still-image frontal face recognition as a case study to illustrate its strengths and capabilities. All of our work is available at www.openbiometrics.org. 1.
Face recognition in the virtual world: recognizing avatar faces
- In Proc. of SPIE, Biometric Technology for Human Identification IX
, 2012
"... Criminal activity in virtual worlds is becoming a major problem for law enforcement agencies. Forensic investigators are becoming interested in being able to accurately and automatically track people in virtual communities. In this paper a set of algorithms capable of verification and recognition of ..."
Abstract
-
Cited by 4 (4 self)
- Add to MetaCart
Criminal activity in virtual worlds is becoming a major problem for law enforcement agencies. Forensic investigators are becoming interested in being able to accurately and automatically track people in virtual communities. In this paper a set of algorithms capable of verification and recognition of avatar faces with high degree of accuracy are described. Results of experiments aimed at within-virtual-world avatar authentication and inter-reality-based scenarios of tracking a person between real and virtual worlds are reported. In the FERET-to-Avatar face dataset, where an avatar face was generated from every photo in the FERET database, a COTS FR algorithm achieved a near perfect 99.58 % accuracy on 725 subjects. On a dataset of avatars from Second Life, the proposed avatar-to-avatar matching algorithm (which uses a fusion of local structural and appearance descriptors) achieved average true accept rates of (i) 96.33 % using manual eye detection, and (ii) 86.5 % in a fully automated mode at a false accept rate of 1.0%. A combination of the proposed face matcher and a state-of-the art commercial matcher (FaceVACS) resulted in further improvement on the inter-realitybased scenario.
Towards automated caricature recognition
- In Proc. Int. Conference on Biometrics
, 2012
"... This paper addresses the problem of identifying a subject from a caricature. A caricature is a facial sketch of a subject’s face that exaggerates identifiable facial features beyond realism, while still conveying his identity. To enable this task, we propose a set of qualitative facial features that ..."
Abstract
-
Cited by 4 (2 self)
- Add to MetaCart
(Show Context)
This paper addresses the problem of identifying a subject from a caricature. A caricature is a facial sketch of a subject’s face that exaggerates identifiable facial features beyond realism, while still conveying his identity. To enable this task, we propose a set of qualitative facial features that encodes the appearance of both caricatures and photographs. We utilized crowdsourcing, through Amazon’s Mechanical Turk service, to assist in the labeling of the qualitative features. Using these features, we combine logistic regression, multiple kernel learning, and support vector machines to generate a similarity score between a caricature and a facial photograph. Experiments are conducted on a dataset of 196 pairs of caricatures and photographs, which we have made publicly available. Through the development of novel feature representations and matching algorithms, this research seeks to help leverage the ability of humans to recognize caricatures to improve automatic face recognition methods. 1.
1 Coupled Discriminant Analysis for Heterogeneous Face Recognition
"... Abstract—Coupled space learning is an effective framework for heterogeneous face recognition. In this paper, we propose a novel coupled discriminant analysis method to improve the heterogeneous face recognition performance. There are two main advantages of the proposed method. First, all samples fro ..."
Abstract
-
Cited by 4 (1 self)
- Add to MetaCart
(Show Context)
Abstract—Coupled space learning is an effective framework for heterogeneous face recognition. In this paper, we propose a novel coupled discriminant analysis method to improve the heterogeneous face recognition performance. There are two main advantages of the proposed method. First, all samples from different modalities are used to represent the coupled projections, so that sufficient discriminative information could be extracted. Second, the locality information in kernel space is incorporated into the coupled discriminant analysis as a constraint to improve the generalization ability. In particular, two implementations of locality constraint in kernel space (LCKS) based coupled discriminant analysis methods, namely LCKS- coupled discriminant analysis (LCKS-CDA) and LCKS- coupled spectral regression (LCKS-CSR) are presented. Extensive experiments on three cases of heterogeneous face matching (high vs. low image resolution, digital photo vs. video image and visible light vs. near infrared) validate the efficacy of the proposed method. Index Terms—Face recognition, heterogeneous face recognition, coupled discriminant analysis, coupled spectral regression, locality constraint in kernel space I.
2012b. Inter-modality Face Sketch Recognition
- In ICME
"... Abstract-Automatic face sketch recognition plays an important role in law enforcement. Recently, various methods have been proposed to address the problem of face sketch recognition by matching face photos and sketches, which are of different modalities. However, their performance is strongly affec ..."
Abstract
-
Cited by 3 (1 self)
- Add to MetaCart
(Show Context)
Abstract-Automatic face sketch recognition plays an important role in law enforcement. Recently, various methods have been proposed to address the problem of face sketch recognition by matching face photos and sketches, which are of different modalities. However, their performance is strongly affected by the modality difference between sketches and photos. In this paper, we propose a new face descriptor based on gradient orientations to reduce the modality difference in feature extraction stage, called Histogram of Averaged Oriented Gradients (HAOG). Experiments on CUFS database show that the new descriptor outperforms the state-of-the-art approaches.
