A novel feature detector-the Constrained Phase Congruency Transform (CPCT) is introduced. It simultaneously detects interest points as well as their scale in various orientations. The CPCT is especially important in registration applications: the local transformation between interest points can be determined based on their orientational scales. The CPCT detects the features in Mach bands and in sinusoidal waves. This cannot be done simply by looking for local maxima in intensity gradient nor by looking for local energy maxima. I conjecture that constraining the general phase congruency is sufficient for feature detection. The correct detection of features' location and of their scale is demonstrated. The robustness of the CPCT is achieved by constraining the local phase. Only four easy-to-detect phases are used in the computations. They correspond to symmetry and anti-symmetry in their neighborhood. The scale at any location and orientation is determined by the scale of the channel that conforms to the constraints and maximizes energy.

The constrained phase congruency transform (CPCT) is a feature detector which simultaneously detects interest points as well as their scale in various orientations. Features are detected by constraining the local phase in a few scales. Only four easy-to-detect phases are used in the computations. They correspond to symmetry and antisymmetry in their neighborhood. The scale at any location and orientation is determined by the scale for which the focal energy is maximizes. The CPCT detects the features in Mach bands and in sinusoidal waves. This cannot be done simply by looking for local maxima in intensity gradient nor by looking for local energy maxima. I conjecture that constraining the general phase congruency is sufficient for feature detection. The correct detection of features location and of their scale is demonstrated.

Abstract Transformations based on radial basis junctions have proven to be a powerful tool in image warping. In the present work we decompose these transformations into linear and radial terms, and show examples where such a decomposition is advantageous. Locally supported basis functions are introduced. Several applications are demonstrated, and a comparison with other warping techniques is carried out. Finally, some fine points of image warping are discussed.

Face recognition schemes that are applied directly to gray level pixel images are presented. Two methods for reducing the overfitting-a common problem in high dimensional classification schemes-are presented and the superiority of their combination is demonstrated. The classification scheme is preceded by preprocessing devoted to reducing the viewpoint and scale variability in the data.

Presents a procedure for facial normalization which is determined by the translocation of few anchors in two sets. The first set determines the affine part of the transformation and is used for overcoming change in viewpoint and scale. The second set is used for normalization of expression. A generalization of radial basis functions theory is used for generating the appropriate mapping. Only a few (1-3) anchors were used to demonstrate elaborate facial expressions without any face model.

Texture consists of local variance of gray level or edge intensity values. The authors have recently presented a generalized symmetry operator that captures local spatial relations of image patterns. They show that activity differences in the continuous intensity map produced by the local generalized symmetry operator can be efficiently used to detect texture boundaries. Using almost all available quantitative results of human performance in artificial texture discrimination, the authors show that the algorithm favorably compares with other computational approaches. Stressing the necessity of benchmarks for computer vision algorithms, the authors also discuss an exhaustive set of textures that could be used as experimental stimuli for both humans and machines. The performance of the algorithm is demonstrated on some of these artificial textures as well as on natural images.>

Locating facial features is crucial for various face recognition schemes. The authors suggest a robust facial feature detector based on a generalized symmetry interest operator. No special tuning is required if the face occupies 15-60% of the image. The operator was tested on a large face data base with a success rate of over 95%.>

An operator based on the intuitive motion of symmetry, which effectively locates interest points in real time and can be incorporated also in active visual systems, is introduced. The results of its operation agree with some psychophysical evidence concerning symmetry as well as evidence concerning fixation points. The operator can be applied successfully without prior knowledge of the world. Combining the operator with some preconceptions about the image is a powerful tool for feature detection in intricate natural scenes. The localization of faces and facial features in real time is demonstrated on detailed and noisy pictures.>