A Hybrid Multiresolution Texture Segmentation and its Application to Ikonos Satellite Imagery

In this thesis a method for segmenting textured images using Gabor filters is presented. One of the most recent approaches for texture segmentation and analysis is multi-channel filtering. There are several applicable choices as filter banks which are used for textured images. Gaussian filters modulated by exponential or by sinusoidal filters, known as Gabor filters, have been proven to be very usefyl for texture analysis for the images containing specific frequency and orientation characteristics. Resembling the human visual cortical cells, Gabor function is a popular sub-band filter for multi-channel decompositon. Optimum joint spatial/spatial frequency uncertainty principle and its ability to recognize and pass specific frequencies and orientations are attributes of Gabor filter that make it more attractive. Gabor function with these attributes could simulate the task of simple visual cells in the cortex. Gabor function has several parameters that determine the sub-band Gabor filter and must be determined accurately to extract the features precisely for texture discrimination. A wide selection range for each parameter exists and many combinations of these parameters are possible. Accurate selection and combination of values for the parameters are of crucial importance. Hence a difficult goal is minimizing the number of filters. On the other hand a variety of approaches of texture analysis and recognition have been presented in remote sensing applications, including land cover/land use classification and urban scene segmentation. With the avaiability of very high-resolution commercial satellite imagery such as IKONOS, it is possible to obtain detailed information on urban land use and change detection that are of particular interest to urban and regional planners. In this thesis considering the attributes of human visual system, a hybrid algorithm is implemented using multi-channel decomposition by Gabor filter bank for feature extraction in conjunction with Artificial Neural Networks for both feature reduction and texture segmentation. Three approaches are implemented to optimize Gabor filter bank for image segmentation. Eventually the proposed method is successfully applied for segmentation of IKONOS satellite images.

A Hybrid Multiresolution Texture Segmentation and its Application to Ikonos Satellite Imagery

In this thesis a method for segmenting textured images using Gabor filters is presented. One of the most recent approaches for texture segmentation and analysis is multi-channel filtering. There are several applicable choices as filter banks which are used for textured images. Gaussian filters modulated by exponential or by sinusoidal filters, known as Gabor filters, have been proven to be very usefyl for texture analysis for the images containing specific frequency and orientation characteristics. Resembling the human visual cortical cells, Gabor function is a popular sub-band filter for multi-channel decompositon. Optimum joint spatial/spatial frequency uncertainty principle and its ability to recognize and pass specific frequencies and orientations are attributes of Gabor filter that make it more attractive. Gabor function with these attributes could simulate the task of simple visual cells in the cortex. Gabor function has several parameters that determine the sub-band Gabor filter and must be determined accurately to extract the features precisely for texture discrimination. A wide selection range for each parameter exists and many combinations of these parameters are possible. Accurate selection and combination of values for the parameters are of crucial importance. Hence a difficult goal is minimizing the number of filters. On the other hand a variety of approaches of texture analysis and recognition have been presented in remote sensing applications, including land cover/land use classification and urban scene segmentation. With the avaiability of very high-resolution commercial satellite imagery such as IKONOS, it is possible to obtain detailed information on urban land use and change detection that are of particular interest to urban and regional planners. In this thesis considering the attributes of human visual system, a hybrid algorithm is implemented using multi-channel decomposition by Gabor filter bank for feature extraction in conjunction with Artificial Neural Networks for both feature reduction and texture segmentation. Three approaches are implemented to optimize Gabor filter bank for image segmentation. Eventually the proposed method is successfully applied for segmentation of IKONOS satellite images.

Spatial receptive field structure of double-opponent cells in macaque V1

The spatial processing of color is important for visual perception. Double-opponent (DO) cells likely contribute to this processing by virtue of their spatially opponent and cone-opponent receptive fields (RFs). However, the representation of visual features by DO cells in the primary visual cortex of primates is unclear because the spatial structure of their RFs has not been fully characterized. To fill this gap, we mapped the RFs of DO cells in awake macaques with colorful, dynamic white noise patterns. The spatial RF of each neuron was fitted with a Gabor function and three versions of the Difference of Gaussians (DoG) function. The Gabor function provided the more accurate description for most DO cells, a result that is incompatible with the traditionally assumed center-surround RF organization. A non-concentric version of the DoG function, in which the RFs have a circular center and a crescent-shaped surround, performed nearly as well as the Gabor model thus reconciling results from previous reports. For comparison, we also measured the RFs of simple cells. We found that the superiority of the Gabor fits over DoG fits was slightly more decisive for simple cells than for DO cells. The implications of these results on biological image processing and visual perception are discussed.

DEVELOPMENT OF MACHINE LEARNING METHOD WITH BIOMETRIC PROTECTION WITH NEW FILTRATION METHODS

Biometric images were processed and filtered by a newly developed Ateb-Gabor wavelet filter. Identification of biometric images was performed by machine learning methods. The Gabor filter based on Ateb functions is effective for filtering because it contains generalizations of trigonometric functions. Developed wavelet transform of Ateb-Gabor function. It is shown that the function depends on seven parameters, each of which makes significant changes in the results of filtering biometric images. A study of the wavelet Ateb-Gabor function was performed. The graphical dependences of the Gabor filter wavelet and the Ateb-Gabor filter wavelet are constructed. The introduction of wavelet transforms reduces the complexity of Ateb-Gabor filter calculations by simplifying function calculations and reducing filtering time. The complexity of the algorithms for calculating the Gabor filter wavelet and the Ateb-Gabor filter wavelet is evaluated. Ateb-Gabor filtering allows you to change the intensity of the entire image, and to change certain ranges, and thus change certain areas of the image. It is this property that biometric images should have, in which the minions should be contrasting and clear. Ateb functions have the ability to change two rational parameters, which, in turn, will allow more flexible control of filtering. The properties of the Ateb function are investigated, as well as the possibility of changing the amplitude of the function, the oscillation frequency to the numerical values ​​of the Ateb-Gabor filter. By using the parameters of the Ateb function, you can get a much wider range of shapes and sizes, which expands the number of possible filtering options. You can also implement once filtering, taking into account the direction of the minutes and reliably determine the sharpness of the edges, rather than filtering batocrates. The reliability results were tested on the basis of NIST Special Database 302, and good filtration results were shown. This was confirmed by a comparison experiment between the Wavelet-Gabor filtering and the Ateb-Gabor wavelet function based on the measurement of the PSNR signal-to-noise ratio.

A sub-Riemannian model of the visual cortex with frequency and phase

In this paper, we present a novel model of the primary visual cortex (V1) based on orientation, frequency, and phase selective behavior of V1 simple cells. We start from the first-level mechanisms of visual perception, receptive profiles. The model interprets V1 as a fiber bundle over the two-dimensional retinal plane by introducing orientation, frequency, and phase as intrinsic variables. Each receptive profile on the fiber is mathematically interpreted as rotated, frequency modulated, and phase shifted Gabor function. We start from the Gabor function and show that it induces in a natural way the model geometry and the associated horizontal connectivity modeling of the neural connectivity patterns in V1. We provide an image enhancement algorithm employing the model framework. The algorithm is capable of exploiting not only orientation but also frequency and phase information existing intrinsically in a two-dimensional input image. We provide the experimental results corresponding to the enhancement algorithm.

Spatial receptive field structure of double-opponent cells in macaque V1

ABSTRACTThe spatial processing of color is important for visual perception. Double-opponent (DO) cells likely contribute to this processing by virtue of their spatially opponent and cone-opponent receptive fields (RFs). However, the representation of visual features by DO cells in the primary visual cortex of primates is unclear because the spatial structure of their RFs has not been fully characterized. To fill this gap, we mapped the RFs of DO cells in awake macaques with colorful, dynamic white noise patterns. The spatial RF of each neuron was fitted with a Gabor function and a Difference of Gaussians (DoG) function. The Gabor function provided the more accurate description for most DO cells, a result that is incompatible with the traditionally assumed center-surround RF organization. A slightly modified (non-concentric) DoG function, in which the RFs have a circular center and a crescent-shaped surround, performed nearly as well as the Gabor model. For comparison, we also measured the RFs of simple cells. We found that the superiority of the Gabor fits over DoG fits was slightly more decisive for simple cells than for DO cells. The implications of these results on biological image processing and visual perception are discussed.

WAVELET TRANSFORMATION ATEB-GABOR FILTERS TO BIOMETRIC IMAGES

Biometric images were pre-processed and filtered in two ways, by wavelet- Gabor and wavelet Ateb-gabor filtration. Ateb-based Gabor filter is effective for filtration because it contains generalizations of trigonometric functions. The wavelet transform of Ateb-Gabor function was developed. The function dependence on seven parameters was shown, each of them significantly changes the filtering results of biometric images. The Ateb-Gabor wavelet research was performed. Graphic dependencies of the wavelet Gabor filter and the wavelet Ateb-Gabor filter were constructed. The appliance of wavelet transform makes it possible to reduce the complexity of calculating an Ateb-Gabor filter by simplifying function calculations and reducing filtering time. The complexities of algorithms for calculating the wavelet Gabor filter and the wavelet Ateb-Gabor filter have been evaluated. Ateb-Gabor filtration allows you to adjust the intensity of the entire image, and to change certain ranges, thereby changing certain areas of the image. Biometric images should have this property, on which the minucius should be contrasting and clear. Ateb functions have the property of changing two rational parameters, which will allow to make more flexible control of filtration. The properties of the Ateb function, as well as the possibility of changing the amplitude of the function, the oscillation frequency by the numerical values of the Ateb-Gabor filter, were investigated. By using the parameters of the Ateb function, you can get a much larger range of shapes and sizes, which expands the number of possible filtration options. You can also perform filtration once, taking into account the direction of the minucius and reliably determine the sharpness of the edges, rather than perform filtration many times. The reliability of results were tested using NIST Special Database 302 and good filtration results were shown. This is confirmed by the comparison experiment between the wavelet-Gabor filter and the wavelet Ateb-Gabor function based on the PSNR signal-to-noise ratio measurement.

The Two-Dimensional Gabor Function Adapted to Natural Image Statistics: A Model of Simple-Cell Receptive Fields and Sparse Structure in Images

The two-dimensional Gabor function is adapted to natural image statistics, leading to a tractable probabilistic generative model that can be used to model simple cell receptive field profiles, or generate basis functions for sparse coding applications. Learning is found to be most pronounced in three Gabor function parameters representing the size and spatial frequency of the two-dimensional Gabor function and characterized by a nonuniform probability distribution with heavy tails. All three parameters are found to be strongly correlated, resulting in a basis of multiscale Gabor functions with similar aspect ratios and size-dependent spatial frequencies. A key finding is that the distribution of receptive-field sizes is scale invariant over a wide range of values, so there is no characteristic receptive field size selected by natural image statistics. The Gabor function aspect ratio is found to be approximately conserved by the learning rules and is therefore not well determined by natural image statistics. This allows for three distinct solutions: a basis of Gabor functions with sharp orientation resolution at the expense of spatial-frequency resolution, a basis of Gabor functions with sharp spatial-frequency resolution at the expense of orientation resolution, or a basis with unit aspect ratio. Arbitrary mixtures of all three cases are also possible. Two parameters controlling the shape of the marginal distributions in a probabilistic generative model fully account for all three solutions. The best-performing probabilistic generative model for sparse coding applications is found to be a gaussian copula with Pareto marginal probability density functions.

Image Intelligent Detection Based on the Gabor Wavelet and the Neural Network Combined Neural Network

This paper first analyzes the one-dimensional Gabor function and expands it to a two-dimensional one. The two-dimensional Gabor function generates the two-dimensional Gabor wavelet through measure stretching and rotation. At last, the two-dimensional Gabor wavelet transform is employed to extract the image feature information. Based on the BP neural network model, the image intelligent test model based on the Gabor wavelet and the neural network model is built. The human face image detection is adopted as an example. Results suggest that, when the method combining Gabor wavelet transform and the neural network is used to test the human face, it will not influence the detection results despite of complex textures and illumination variations on face images. Besides, when ORL human face database is used to test the model, the human face detection accuracy can reach above 0.93.