Unsupervised texture segmentation using Gabor filters

This paper presents a texture segmentation algorithm inspired by the multi-channel filtering theory for visual information processing in the early stages of human visual system. The channels are characterized by a bank of Gabor filters that nearly uniformly covers the spatial-frequency domain, and a systematic filter selection scheme is proposed, which is based on reconstruction of the input image from the filtered images. Texture features are obtained by subjecting each (selected) filtered image to a nonlinear transformation and computing a measure of “energy” in a window around each pixel. A square-error clustering algorithm is then used to integrate the feature images and produce a segmentation. A simple procedure to incorporate spatial information in the clustering process is proposed. A relative index is used to estimate the “true” number of texture categories.     

An automated inspection system for textile fabrics based on Gabor filters

This paper studies the application of advanced computer image processing techniques for solving the problem of automated defect detection for textile fabrics. A new defect detection scheme is proposed, which consists of an odd symmetric real-valued Gabor filter, an even symmetric real-valued Gabor filter and one smoothing filter. In developing the scheme, the Gabor filters are designed on the basis of the texture features extracted optimally from a non-defective fabric image by using a Gabor wavelet network (GWN). The performance of the proposed defect detection scheme is evaluated off-line by using a set of fabric images taken from a database consisting of a wide variety of homogeneous fabric images. The results exhibit accurate defect detection with low false alarms, thus showing the effectiveness and robustness of the proposed scheme. To evaluate the performance of the proposed defect detection scheme further, real-time tests are conducted by using a prototyped automated defect detection system. The experimental results obtained further confirm the efficiency, effectiveness and robustness of the proposed detection scheme.     

Stability and dimensionality of Karhunen-Loêve multispectral image expansions

The Karhunen-Loêve (K.L.) expansion is a useful tool for the representation, pre-processing and orthogonal coding of multispectral imagery: Each spatial pixel is analysed independently as the K.L. transform is taken in the spectral dimension, i.e. along the various N spectral channels. The eigenvectors are those of the covariance matrix. The (principal) eigenimages are thus “false color” images, which can be viewed without decoding as the spatial topology is unchanged, and the higher order principal images present a strong contrast enhancement.⁽¹⁾ These principal images are also uncorrelated, a very desirable feature for many applications including clustering.⁽²⁾

The source dependency of the eigenvectors, however, introduces “instability” in the form of pronounced statistical noise on some principal images. This paper gives the results of a numerical study carried out on a 7 channel Daedalus Multispectral Scene. The uncertainties of the eigenvalues and eigenvectors are evaluated from two “drawings” of the pixels of the raw data.

Both the numerical results of the study and the direct viewing of the principal images show that three out of the seven have so much noise that they do not yield any useful information. Only the first two principal images have excellent stability, and they contain most of the total contrast variance of the scene. Two other principal images of lower order are also stable, but, contribute very little to the total contrast variance. These images carry texture information rather than homogeneous zone clustering information.     

Filter-based models for pattern classification

In this paper we consider a technique for pattern classification based upon the development of prototypes which capture the distinguishing features (“disjunctive prototypes”) of each pattern class and, via cross-correlation with incoming test images, enable efficient pattern classification. We evaluate such a classification procedure with prototypes based on the images per se (direct code), Gabor scheme (multiple fixed filter representation) and an edge (scale space-based) coding scheme. Our analyses, and comparisons with human pattern classification performance, indicate that the edge-only disjunctive prototypes provide the most discriminating classification performance and are the more representative of human behaviour.     

硅太阳能电池纹理缺陷检测

为实现硅太阳能电池纹理缺陷检测,提出一种采用方向可变滤波器组并结合Hough变换的检测方法。通过方向可变滤波器提取图像边缘并采用Hough变换确定纹理方向,采用角度与纹理方向一致的方向可变滤波器滤波,实现消除规则直线纹理,保留纹理缺陷特征。对滤波后的纹理缺陷结果图像采用双阈值法,以确定纹理缺陷所在的位置。和Gabor滤波器及小波滤波器的比较实验结果表明：该方法比前两种方法能更有效地进行硅太阳能电池纹理缺陷检测。     

Texture descriptor based on partially self-avoiding deterministic walker on networks

Texture image analysis is an important field of investigation that has attracted the attention from computer vision community in the last decades. In this paper, a novel approach for texture image analysis is proposed by using a combination of graph theory and partially self-avoiding deterministic walks. From the image, we build a regular graph where each vertex represents a pixel and it is connected to neighboring pixels (pixels whose spatial distance is less than a given radius). Transformations on the regular graph are applied to emphasize different image features. To characterize the transformed graphs, partially self-avoiding deterministic walks are performed to compose the feature vector. Experimental results on three databases indicate that the proposed method significantly improves correct classification rate compared to the state-of-the-art, e.g. from 89.37% (original tourist walk) to 94.32% on the Brodatz database, from 84.86% (Gabor filter) to 85.07% on the Vistex database and from 92.60% (original tourist walk) to 98.00% on the plant leaves database. In view of these results, it is expected that this method could provide good results in other applications such as texture synthesis and texture segmentation.     

结合Gabor滤波器和扩展LTP算子的无监督纹理图像分割

目的 现实中的纹理往往具有类型多样、形态多变、结构复杂等特点,直接影响到纹理图像分割的准确性。传统的无监督纹理图像分割算法具有一定的局限性,不能很好地提取稳定的纹理特征。本文提出了基于Gabor滤波器和改进的LTP（local ternary pattern）算子的针对复杂纹理图像的纹理特征提取算法。方法 利用Gabor滤波器和扩展LTP算子分别提取相同或相似纹理模式的纹理特征和纹理的差异性特征,并将这些特征融入到水平集框架中对纹理图像进行分割。结果 通过实验表明,对纹理方向及尺度变化较大的图像、复杂背景下的纹理图像以及弱纹理模式的图像,本文方法整体分割结果明显优于传统的Gabor滤波器、结构张量、拓展结构张量、局部相似度因子等纹理分割方法得到的结果。同时,将本文方法与基于LTP的方法进行对比,分割结果依然更优。在量化指标方面,将本文方法与各种无监督的纹理分割方法就分割准确度进行对比,结果表明,在典型的纹理图像上,本文方法准确度达到97%以上,高于其他方法的分割准确度。结论 提出了一种结合Gabor滤波器和扩展LTP算子的无监督多特征的纹理图像分割方法,能够较好地提取相似纹理模式的特征和纹理的差异性特征,且这些纹理特征可以很好地融合到水平集框架中,对真实世界复杂纹理图像能够得到良好的分割效果。     

A comment on “L∞ optimal control of SISO continuous-time systems”

The paper “L_∞ optimal control of SISO continuous-time systems” by Wang and Sznaier (Wang & Sznaier (1997). Automatica, 33 (1), 85–90) studies the problem of designing a controller that optimally minimizes the peak absolute value of system output, due to a fixed input signal. With a newly defined function space A_∞, it was claimed that the set of all L_∞-bounded outputs could be parameterized and that the problem could be transformed to a minimal distance problem on L_∞ space. We believe, however, their formulation has essential flaws.     

A high-quality filtering using forward texture mapping

Texture mapping is a very popular technique used to provide more realism in image synthesis. Texture compression induced by geometric transformations creates serious aliasing artifacts appearing essentially as well-known “Moiré” patterns. A simple and high-quality texture mapping technique using a forward mapping is presented. This new method very efficiently avoids texture aliasing artifacts by using an accurate convolution obtained naturally from forward mapping. In addition to a high-quality texture mapping, antialiasing of the final image contours is directly produced by this method.     

Fast Gabor texture feature extraction with separable filters using GPU

Gabor wavelet transform is one of the most effective texture feature extraction techniques and has resulted in many successful practical applications. However, real-time applications cannot benefit from this technique because of the high computational cost arising from the large number of small-sized convolutions which require over 10 min to process an image of 256 × 256 pixels on a dual core CPU. As the computation in Gabor filtering is parallelizable, it is possible and beneficial to accelerate the feature extraction process using GPU. Conventionally, this can be achieved simply by accelerating the 2D convolution directly, or by expediting the CPU-efficient FFT-based 2D convolution. Indeed, the latter approach, when implemented with small-sized Gabor filters, cannot fully exploit the parallel computation power of GPU due to the architecture of graphics hardware. This paper proposes a novel approach tailored for GPU acceleration of the texture feature extraction algorithm by using separable 1D Gabor filters to approximate the non-separable Gabor filter kernels. Experimental results show that the approach improves the timing performance significantly with minimal error introduced. The method is specifically designed and optimized for computing unified device architecture and is able to achieve a speed of 16 fps on modest graphics hardware for an image of 256² pixels and a filter kernel of 32² pixels. It is potentially applicable for real-time applications in areas such as motion tracking and medical image analysis.