Unconstrained environments with variable ambient illumination and changes of head pose are still challenging
for many face recognition systems. To recognize a person independent of pose, we separate shape from texture
information using an active appearance model. We do not directly use the texture information from the
active appearance model for recognition. Instead we extract local texture features from a shape and pose free
representation of facial images. We use a smooth warp function to transform the images. We compensate also
the shape information for head pose changes and fuse the results of separate classiers for shape features and
local texture features. We analyze the inuence of the individual contributions of shape and texture information
on the recognition performance. We show that fusing shape and texture information can boost the recognition
performance in an access control scenario.
Unconstrained environments with variable ambient illumination and changes of head pose are still challenging for many face recognition systems. To recognize a person independent of pose, we first fit an active appearance model to a given facial image. Shape information is used to transform the face into a pose-normalized representation. We decompose the transformed face into local regions and extract texture features from these not necessarily rectangular regions using a shape-adapted discrete cosine transform. We show that these features contain sufficient discriminative information to recognize persons across changes in pose. Furthermore, our experimental results show a significant improvement in face recognition performance on faces with pose variations when compared with a block-DCT based feature extraction technique in an access control scenario.
Active near-infrared illumination may be used in a face recognition system to achieve invariance to changes of
the visible illumination. Another benefit of active near-infrared illumination is the bright pupil effect which can
be used to assist eye detection. But long time exposure to
near-infrared radiation is hazardous to the eyes.
The level of illumination is therefore limited by potentially harmful effects to the eyes. Image sensors for face
recognition under active near-infrared illumination have therefore to be carefully selected to provide optimal
image quality in the desired field of application. A model of the active illumination source is introduced. Safety
issues with regard to near-infrared illumination are addressed using this model and a radiometric analysis. From
the illumination model requirements on suitable imaging sensors are formulated. Standard image quality metrics
are used to assess the imaging device performance under application typical conditions. The characterization
of image quality is based on measurements of the Opto-Electronic Conversion Function, Modulation Transfer
Function and noise. A methodology to select an image sensor for the desired field of application is given. Two
cameras with low-cost image sensors are characterized using the key parameters that influence the image quality
for face recognition.