Model of Frequency Analysis in the Visual Cortex and the Shape from Texture Problem

Fractional Wavelet Scattering Network and Applications

OBJECTIVE

This study introduces a fractional wavelet scattering network (FrScatNet), which is a generalized translation invariant version of the classical wavelet scattering network.

METHODS

In our approach, the FrScatNet is constructed based on the fractional wavelet transform (FRWT). The fractional scattering coefficients are iteratively computed using FRWTs and modulus operators. The feature vectors constructed by fractional scattering coefficients are usually used for signal classification. In this paper, an application example of the FrScatNet is provided in order to assess its performance on pathological images. First, the FrScatNet extracts feature vectors from patches of the original histological images under different orders. Then we classify those patches into target (benign or malignant) and background groups. And the FrScatNet property is analyzed by comparing error rates computed from different fractional orders, respectively. Based on the above pathological image classification, a gland segmentation algorithm is proposed by combining the boundary information and the gland location.

RESULTS

The error rates for different fractional orders of FrScatNet are examined and show that the classification accuracy is improved in fractional scattering domain. We also compare the FrScatNet-based gland segmentation method with those proposed in the 2015 MICCAI Gland Segmentation Challenge and our method achieves comparable results.

CONCLUSION

The FrScatNet is shown to achieve accurate and robust results. More stable and discriminative fractional scattering coefficients are obtained by the FrScatNet in this paper.

SIGNIFICANCE

The added fractional order parameter is able to analyze the image in the fractional scattering domain.

The lawful imprecision of human surface tilt estimation in natural scenes

Estimating local surface orientation (slant and tilt) is fundamental to recovering the three-dimensional structure of the environment. It is unknown how well humans perform this task in natural scenes. Here, with a database of natural stereo-images having groundtruth surface orientation at each pixel, we find dramatic differences in human tilt estimation with natural and artificial stimuli. Estimates are precise and unbiased with artificial stimuli and imprecise and strongly biased with natural stimuli. An image-computable Bayes optimal model grounded in natural scene statistics predicts human bias, precision, and trial-by-trial errors without fitting parameters to the human data. The similarities between human and model performance suggest that the complex human performance patterns with natural stimuli are lawful, and that human visual systems have internalized local image and scene statistics to optimally infer the three-dimensional structure of the environment. These results generalize our understanding of vision from the lab to the real world.

Band-Reweighed Gabor Kernel Embedding for Face Image Representation and Recognition

Face recognition with illumination or pose variation is a challenging problem in image processing and pattern recognition. A novel algorithm using band-reweighed Gabor kernel embedding to deal with the problem is proposed in this paper. For a given image, it is first transformed by a group of Gabor filters, which output Gabor features using different orientation and scale parameters. Fisher scoring function is used to measure the importance of features in each band, and then, the features with the largest scores are preserved for saving memory requirements. The reduced bands are combined by a vector, which is determined by a weighted kernel discriminant criterion and solved by a constrained quadratic programming method, and then, the weighted sum of these nonlinear bands is defined as the similarity between two images. Compared with existing concatenation-based Gabor feature representation and the uniformly weighted similarity calculation approaches, our method provides a new way to use Gabor features for face recognition and presents a reasonable interpretation for highlighting discriminant orientations and scales. The minimum Mahalanobis distance considering the spatial correlations within the data is exploited for feature matching, and the graphical lasso is used therein for directly estimating the sparse inverse covariance matrix. Experiments using benchmark databases show that our new algorithm improves the recognition results and obtains competitive performance.

Dominance of orientation over frequency in the perception of 3-D slant and shape

In images of textured three-dimensional surfaces, pattern changes can be characterized as changes in orientation and spatial frequency, features for which neurons in primary visual cortex are classically selective. Previously, we have demonstrated that correct 3-D shape perception is contingent on the visibility of orientation flows that run parallel to the surface curvature. We sought to determine the relative contributions of orientation modulations (OMs) and frequency modulations (FMs) for the detection of slant and shape from 3-D surfaces. Results show that 1) when OM and FM indicate inconsistent degrees of surface slant or curvature, observer responses were consistent with the slant or curvature specified by OM even if the FM indicated a slant or curvature in the opposite direction to the same degree. 2) For slanted surfaces, OM information dictates slant perception at both shallow and steep slants while FM information is effective only for steep slants. Together these results point to a dominant role of OM information in the perception of 3-D slant and shape.