A new approach for face recognition by sketches in photos
Introduction
As one of the personal identification methods with the most potential, face recognition [1], [2], [3] has drawn increasing attention of researchers and played an important role in many application areas, one of which is retrieving a suspect's images from the existing photo database automatically for identifying the suspect so as to prevent terrorist activities and ensure public security. An automated retrieval of suspects’ images would not only save many person-hours, but also reduce the effect of a subjective assessment. Actually, we acquire no photos of suspects but witnesses’ verbal description of them sometimes; thereby simulated sketches are generated by the cooperation of artists and witnesses instead of photos, and identity of suspects has to be determined by searching the existing photo database based on sketches. The problem of recognizing sketches from photo database automatically and effectively has attracted researchers. Since the research of face recognition sprang up in 1960s, many significant achievements have been made [1], [2], [3] and most recently [4], [5], [6], [7], [8], [9], and most of them are only available for face photos. Sketches and photos are generated and expressed in different mechanism; therefore have great geometrical deformations and large difference of texture. In other words, the sketch and photo for a person may be similar in geometry, but the texture of them is always very different, which makes the existing face recognition algorithms inactive. Sketch–photo recognition becomes a challenging research focus of face recognition and deserves further research.
The key of sketch–photo recognition method is transforming photos and sketches into the same modality to reduce difference between them, and then face recognition by sketches in pseudo-sketches or by pseudo-photos in photos is performed using classical approaches [10], [11]. The initial research is presented in [12], [13], which rely on human intervention heavily. Robert et al. proposed the method for automatic match of sketches and photos firstly [14]. As shown in Fig. 1, up to now, face sketches referred to in sketch–photo recognition focus on line-drawing sketch and complex sketch which depicts the face information by lighting and shading besides lines. In line-drawing sketch–photo recognition, photos have to be converted into line-drawing sketches, with which the line-drawing sketch to be recognized is compared. For complex sketch–photo recognition, on the one hand, photos are converted into pseudo-sketches based on which identification of complex sketch is performed. Tang et al. have made large contribution to convert photos into pseudo-sketches. They proposed a method based on principal components analysis (PCA) [15], [16], [17], and then introduced manifold in the pseudo-sketch synthesis [18] in which nonlinearity between photos and sketches is approximated by local linearity. Extending these ideas, Gao et al. proposed sketch synthesis algorithms [19], [20], [21] based on embedded hidden Markov model (EHMM) so that complex nonlinear relationship between photos and sketches is learnt exactly. Pseudo-sketch synthesis is developed from linear method, nonlinear method approximated by local linearity to real nonlinear method. On the other hand, in view of much information useful for recognition may be lost if all face photos are transformed into sketches, the complex sketch is transformed into a pseudo-photo which is recognized in photo databases. Facial pseudo-photo synthesis are achieved by photometrically standardizing sketch images [14], [22], using a hybrid subspace method [23], and based on Bayesian tensor inference [24]. The trend in development of these methods is from the method based on basic pixels to the statistical one through the method with subspace. Our aim is the recognition of complex sketch in photo database and in the following, complex sketch is abbreviated to sketch.
The research of sketch–photo recognition based on synthesizing pseudo-photos from the corresponding sketches is still at an elementary stage. The existing methods require a large set of training samples; however, the training set is usually restricted within a small size because of the high cost of sketch acquisition. The application of this kind of methods is limited. Aiming at this problem, a novel face pseudo-photo synthesis algorithm is proposed based on machine learning and recognition of pseudo-photo in photos is performed in this paper so as to implement sketch–photo recognition with small set of training samples. The nonlinear relationship of each sketch–photo pair in training set is learnt by a pair of EHMMs [25]. Given a face sketch, several intermediate pseudo-photos for it are generated based on the selected trained EHMM pairs according to the idea of selective ensemble and the expected pseudo-photo is resulted by fusing these intermediate pseudo-photos. Each intermediate pseudo-photo is generated with a training sketch–photo pair and it is a pseudo-photo for the given sketch to a certain extent, that is to say, one pair of training sketch and photo is sufficient for obtaining a pseudo-photo. Several training sketch–photo pairs are chosen to synthesize more intermediate pseudo-photos for the given sketch, so that they can be fused to generate a much better pseudo-photo. Accordingly, it is unnecessary to collect a great many of training samples. In addition, compared with the whole face, local facial features can provide more specific information, which are in favor of state estimation of EHMMs, and then we add local strategy to the synthesis of pseudo-photo. When the pseudo-photo is synthesized, eigenface recognition [10], [26] is performed between pseudo-photo and photos. It can be proved that the proposed method leads to high recognition rate of sketch–photo recognition with a set of experiments.
The remainder of this paper is organized as follows. Section 2 gives an overview to the proposed algorithm. In Section 3, the idea of EHMM is introduced briefly, and an EHMM pair is modeled for a pair of sketch patch and photo patch. The procedure of synthesizing and identifying pseudo-photos is described in detail in Section 4. The experimental results are presented in Section 5, and the final section gives the conclusions.
Section snippets
The overview of the proposed method
The aim of the proposed method is to identify a sketch in a photo set by synthesizing a pseudo-photo for the sketch and performing photo–photo recognition. Hidden Markov model (HMM) is a probability statistics method used to model signals for processing [27]. Because face images have rich two-dimensional spatial information, modeling a face image with the traditional one-dimensional HMM not only loses the spatial information partially, but also increases computational complexity which is still
Embedded HMMs pair of sketch patch and photo patch
EHMM consists of a series of super-states, each of which contains several embedded-states. Similar to the HMM, states of the EHMM are non-observable and only a sequence of instances generated by these states can be observed, T is the number of observation vectors. The model is denoted aswhere includes initial super-state distribution vectors and is for the k-th super-state, is super-state transition probability matrix representing the
The synthesis and recognition of pseudo-photos
The flow chart of synthesizing pseudo-photos and performing recognition of pseudo-photos in photos is shown in Fig. 4. A training set with M pairs of sketches and photos , where , and a sketch S to be recognized are given. Firstly, they are evenly divided into N overlapping patches with the patch size B×B and the overlapped area size , where D is the overlapping degree. Each patch of sketches in the training set is modeled with EHMM , where ; Secondly,
The experimental results and analysis
In this section, the effectiveness of the proposed sketch–photo recognition algorithm is evaluated from the aspect of identifying sketch in photo set. The proposed method is compared with the direct sketch–photo recognition method and the approach based on pseudo-sketch synthesis [21]. In the direct sketch–photo recognition method, the testing sketch is identified based on training photos with eigenface method. According to the approach reported in [21] whose idea is illustrated in Fig. 5,
Conclusion
This paper presents a novel sketch–photo recognition method. The sketch to be recognized is converted into a pseudo-photo by the combination of EHMM and selective ensemble with the local strategy. The nonlinear relationship between sketch and photo patch pairs is modeled using EHMMs, many of which are selected to reconstruct pseudo-photo patches. These pseudo-photo patches are synthesized into the expected pseudo-photo. Then sketch–photo recognition is transformed into recognizing pseudo-photo
Acknowledgements
The authors are grateful to the helpful comments and suggestions from the anonymous reviewers. Thanks must be expressed to the Multimedia Lab of the Chinese University of Hong Kong for providing us with the face photo–sketch images database. This research was supported by National Science Foundation of China (60771068, 60702061, 60832005), the Open-End Fund of National Laboratory of Pattern Recognition in China and National Laboratory of Automatic Target Recognition, Shenzhen University, China,
References (41)
- et al.
Local face sketch synthesis learning
Neurocomputing
(2008) - et al.
Adaptive color quantization based on perceptive edge protection
Pattern Recognition Lett.
(2003) - et al.
Human and machine recognition of faces: a survey
Proc. IEEE
(1995) - et al.
Face recognition: a literature survey
ACM Comput. Surv.
(2003) - P. Phillips, P. Flynn, T. Scruggs, K. Bowyer, J. Chang, K. Hoffman, J. Marques, J. Min, W. Worek, Overview of the face...
- et al.
Binary two-dimensional PCA
IEEE Trans. Syst. Man Cybern. B Cybern.
(2008) - et al.
Bayesian tensor approach for 3-D face modeling
IEEE Trans. Circuits Syst. Video Technol.
(2008) - et al.
Gabor-based region covariance matrices for face recognition
IEEE Trans. Circuits Syst. Video Technol.
(2008) - et al.
General tensor discriminant analysis and Gabor features for gait recognition
IEEE Trans. Pattern Anal. Mach. Intell.
(2007) - et al.
Geometric mean for subspace selection
IEEE Trans. Pattern Anal. Mach. Intell.
(2009)
Face recognition by independent component analysis
IEEE Trans. Neural Networks
An interactive computer system for retrieving faces
Face sketch recognition
IEEE Trans. Circuits Syst. Video Technol.
Cited by (81)
Face image-sketch synthesis via generative adversarial fusion
2022, Neural NetworksCitation Excerpt :Moreover, these existing methods ignore learning and controlling the illumination distribution over the face. It is easy to observe that the face area of generated face images has no illumination highlight (Duan et al., 2021; Wang et al., 2018; Xiao et al., 2009) or has stronger illumination highlight (Sannidhan et al., 2019; Wang & Tang, 2009; Zhu et al., 2019) compared with the ground truth image. The illumination highlight is the key factor that directly affects the visual quality of the generated face image.
Local Force Pattern (LFP): Descriptor for Heterogeneous Face Recognition
2019, Pattern Recognition LettersCitation Excerpt :Similarly, Liu et al. [11] used Locally Linear Embedding (LLE) to synthesise sketches. Xiao et al. [12] stated an approach based on Embedded Hidden Markov Model (E-HMM) for nonlinear transformation of sketches into pseudo-photo, however this approach is computationally expensive because it is an iterative method. In the field of feature representation, Yuen et al. [13] proposed an approach for representing local facial feature and geometrical relationship between facial features as a global representation of face sketch and photos.
Feature fusion with covariance matrix regularization in face recognition
2018, Signal ProcessingFace sketch-photo synthesis and recognition: Dual-scale Markov Network and multi-information fusion
2018, Journal of Visual Communication and Image RepresentationFast alignment for sparse representation based face recognition
2017, Pattern RecognitionA Deep Learning-Based Approach for Identification and Recognition of Criminals
2023, International Journal of Intelligent Systems and Applications in Engineering