Video-Based Face Recognition Using Identity Surfaces

Yongmin Li , Shaogang Gong and Heather Liddell
  1. Identity Surfaces
  2. Video-Based Face Recognition
  3. Constructing Identity Surfaces of Faces
  4. Pattern Distances and Trajectory Distances to Identity Surfaces
  5. Relavant Publications

Identity Surfaces

Assuming that only the appearance variation caused by rotation in depth is concerned, i.e. the variation from expression, illumination and facial make-up is excluded, each face class can be represented by a unique hyper surface based on the pose information. For each pose (tilt and yaw angles), there is one unique ``point'' for a face class. We call this surface an identity surface. Then face recognition can be performed by computing and comparing the distances between a given pattern and a set of identity surfaces.
Figure 1: Identity surfaces for face recognition

Video-Based Face Recognition

Psychological and physiological research suggests that modelling and recognising moving faces dynamically are potential to achieve a superior performance against that on static images. As shown in Figure 1, when a face is detected and tracked in an input video sequence, one obtains the object trajectory of the face in the feature space. Also, its projection on each of the identity surface with the same poses and temporal order forms a model trajectory of the specific face class. Then face recognition can be carried out by matching the object trajectory with a set of model trajectories. Compared to face recognition on static images, this approach can be more robust and accurate. For example, it is difficult to decide whether the pattern X in Figure 1 belongs to subject A or B for a single pattern, however, if we know that X is tracked along the object trajectory, it is much clear that it is more likely to be subject A than B.

Constructing Identity Surfaces of Faces

If sufficient patterns of a face class in different views are available, the identity surface of this face class can be constructed precisely. However, we do not presume such a strict condition. In this work, we develop a method to synthesise the identity surface of a face class from a small sample of face patterns which sparsely cover the view sphere. The basic idea is to approximate the identity surface using a set of Np planes separated by a number of Nv predefined views. The problem can be finally defined as a quadratic optimisation problem which can be solved using the interior point method.

Figure 2 shows real identity surface of a face class from all 45 views and the synthesised identity surface from only 15 views. Note that a sparse sample of face patterns can provide satisfactory results.

Figure 2: The identity surface constructed from all 45 views (first row) and that synthesised from 15 prototype patterns (second row). Only the first three KDA components are shown here.
\includegraphics[width=.30\columnwidth]{figures/idsurf_ori1.eps} \includegraphics[width=.30\columnwidth]{figures/idsurf_ori2.eps} \includegraphics[width=.30\columnwidth]{figures/idsurf_ori3.eps}
\includegraphics[width=.30\columnwidth]{figures/idsurf_syn1.eps} \includegraphics[width=.30\columnwidth]{figures/idsurf_syn2.eps} \includegraphics[width=.30\columnwidth]{figures/idsurf_syn3.eps}

Pattern Distances and Trajectory Distances to Identity Surfaces

The pattern distance of an unknown face pattern to one of the identity surfaces can be computed as the Euclidean distance between the pattern and the corresponding point on the identity surface. It is important to note that the Euclidean distance may be more appropriate for LDA (Linear Discriminant Analysis) or KDA (Kernel Discriminant Analysis) while the Mahalanobis distance is more efficient when PCA (Principal Component Analysis) or KPCA (Kernel Principal Component Analysis) is adopted, since the discriminant feature is crucial in the former case while the general variation of all patterns is concerned in the latter.

Figure 3 shows the pattern distances of a set of 45 face patterns from a same subject to 12 identity surfaces. The results from the ground-truth face class are highlighted with solid line and circles. In this experiment, KDA was adopted to represent the face pattern. All the 45 faces were correctly recognised.

Figure 3: Recognising multi-view faces using distances to the identity surfaces. The solid line denotes the results of the ground-truth subject.

When a face is tracked continuously from a video sequence, face recognition can be performed by computing and matching the object and model trajectories. These trajectories encode the spatio-temporal information of a moving face. A preliminary realisation of this approach is implemented by computing the weighted summation of the pattern distances in all frames up to the current time.


We demonstrate the performance of this approach on a small scale multi-view face recognition problem. Twelve sequences, each from a set of 12 subjects, were used as training sequences to construct the identity surfaces. The number of frames contained in each sequence varies from 40 to 140. Only 10 KDA dimensions were used to construct the identity surfaces. Then recognition was performed on new test sequences of these subjects. Figure 4 shows the sample images fitted by our multi-view dynamic model and the warped shape-and-pose-free texture patterns from a test sequence.

Figure 4: Video-base multi-view face recognition. From top to bottom, sample images from a test sequence with an interval of 10 frames, images fitted by the multi-view dynamic face model, and the shape-and-pose-free texture patterns.
\includegraphics[width=.08\textwidth]{figures/fitOrig000.eps} \includegraphics[width=.08\textwidth]{figures/fitOrig010.eps} \includegraphics[width=.08\textwidth]{figures/fitOrig020.eps} \includegraphics[width=.08\textwidth]{figures/fitOrig030.eps} \includegraphics[width=.08\textwidth]{figures/fitOrig040.eps} \includegraphics[width=.08\textwidth]{figures/fitOrig050.eps} \includegraphics[width=.08\textwidth]{figures/fitOrig060.eps} \includegraphics[width=.08\textwidth]{figures/fitOrig070.eps} \includegraphics[width=.08\textwidth]{figures/fitOrig080.eps}
\includegraphics[width=.08\textwidth]{figures/fitMark000.eps} \includegraphics[width=.08\textwidth]{figures/fitMark010.eps} \includegraphics[width=.08\textwidth]{figures/fitMark020.eps} \includegraphics[width=.08\textwidth]{figures/fitMark030.eps} \includegraphics[width=.08\textwidth]{figures/fitMark040.eps} \includegraphics[width=.08\textwidth]{figures/fitMark050.eps} \includegraphics[width=.08\textwidth]{figures/fitMark060.eps} \includegraphics[width=.08\textwidth]{figures/fitMark070.eps} \includegraphics[width=.08\textwidth]{figures/fitMark080.eps}
\includegraphics[width=.08\textwidth]{figures/fitText000.eps} \includegraphics[width=.08\textwidth]{figures/fitText010.eps} \includegraphics[width=.08\textwidth]{figures/fitText020.eps} \includegraphics[width=.08\textwidth]{figures/fitText030.eps} \includegraphics[width=.08\textwidth]{figures/fitText040.eps} \includegraphics[width=.08\textwidth]{figures/fitText050.eps} \includegraphics[width=.08\textwidth]{figures/fitText060.eps} \includegraphics[width=.08\textwidth]{figures/fitText070.eps} \includegraphics[width=.08\textwidth]{figures/fitText080.eps}

The object and model trajectories (in the first two KDA dimensions) are shown in Figure 5.
Figure 5: The object and model trajectories in the first two KDA dimensions. The object trajectories are the solid lines with dots denoting the face patterns in each frame. The others are model trajectories where the ones from the ground-truth subject highlighted with solid curves.
\includegraphics[width=.45\textwidth]{figures/trajkda1.eps} \includegraphics[width=.45\textwidth]{figures/trajkda2.eps}

The pattern distances from the identity surfaces in each individual frame are shown in the left side of Figure 6, while the trajectory distances shown in the right side. These results depict that a more robust performance is achieved when recognition is carried out using the trajectory distances which include the accumulated evidence over time though the pattern distances to the identity surfaces in each individual frame already provides a sufficient recognition accuracy.
Figure 6: Pattern distances and trajectory distances. The ground-truth subject is highlighted with solid lines. By using KDA and identity surfaces, the pattern distances can already give an accurate result. However, the trajectory distances provide a more robust performance, especially its accumulated effects (i.e. discriminating ability) over time.
\includegraphics[width=.45\textwidth]{figures/patndist.eps} \includegraphics[width=.45\textwidth]{figures/trajdist.eps}

Relavant Publications

  1. Y. Li, S. Gong, and H. Liddell.
    Video-based online face recognition using identity surfaces.
    Technical report, Queen Mary, University of London, 2001.
  2. Y. Li, S. Gong, and H. Liddell.
    Modelling faces dynamically across views and over time.
    Technical report, Queen Mary, University of London, 2001.
  3. Y. Li, S. Gong, and H. Liddell.
    Recognising the dynamics of faces across multiple views.
    In British Machine Vision Conference, pages 242-251, Bristol, England, 9 2000.