Human gender recognition in the wild is a challenging task due to complex face variations, such as poses, lighting, occlusions, etc. In this letter, learnable Gabor convolutional network (LGCN), a new neural network computing framework for gender recognition was proposed. In LGCN, a learnable Gabor filter (LGF) is introduced and combined with the convolutional neural network (CNN). Specifically, the proposed framework is constructed by replacing some first layer convolutional kernels of a standard CNN with LGFs. Here, LGFs learn intrinsic parameters by using standard back propagation method, so that the values of those parameters are no longer fixed by experience as traditional methods, but can be modified by self-learning automatically. In addition, the performance of LGCN in gender recognition is further improved by applying a proposed feature combination strategy. The experimental results demonstrate that, compared to the standard CNNs with identical network architecture, our approach achieves better performance on three challenging public datasets without introducing any sacrifice in parameter size.

Case studies have reported that pedestrian detection methods using vehicle radar are not complete systems because each system has specific limitations at the cost of the calculating amounts, the system complexity or the range resolution. In this letter, we proposed a novel pedestrian detection method by template matching using Gabor filter bank, which was evaluated based on the data observed by 24GHz UWB radar.

In this Letter, a new iris recognition approach based on local Gabor orientation feature is proposed. On one hand, the iris feature extraction method using the traditional Gabor filters can cause time-consuming and high-feature dimension. On the other hand, we can find that the changes of original iris texture in angle and radial directions are more obvious than the other directions by observing the iris images. These changes in the preprocessed iris images are mainly reflected in vertical and horizontal directions. Therefore, the local directional Gabor filters are constructed to extract the horizontal and vertical texture characteristics of iris. First, the iris images are preprocessed by iris and eyelash location, iris segmentation, normalization and zooming. After analyzing the variety of iris texture and 2D-Gabor filters, we construct the local directional Gabor filters to extract the local Gabor features of iris. Then, the Gabor & Fisher features are obtained by Linear Discriminant Analysis (LDA). Finally, the nearest neighbor method is used to recognize the iris. Experimental results show that the proposed method has better iris recognition performance with less feature dimension and calculation time.

Estimating a proper location of vanishing point from a single road image without any prior known camera parameters is a challenging problem due to limited information from the input image. Most edge-based methods for vanishing point detection only work well for structured roads with clear painted lines or distinct boundaries, while they usually fail in unstructured roads lacking sharply defined, smoothly curving edges. In order to overcome this limitation, texture-based methods for vanishing point detection have been widely published. Authors of these methods often calculate the texture orientation at every pixel of the road image by using directional filter banks such as Gabor wavelet filter, and seek the vanishing point by a voting scheme. A local adaptive soft voting method for obtaining the vanishing point was proposed in a previous study. Although this method is more effective and faster than prior texture-based methods, the associated computational cost is still high due to a large number of scanning pixels. On the other hand, this method leads to an estimation error in some images, in which the radius of the proposed half-disk voting region is not large enough. The goal of this paper is to reduce the computational cost and improve the performance of the algorithm. Therefore, we propose a novel local soft voting method, in which the number of scanning pixels is much reduced, and a new vanishing point candidate region is introduced to improve the estimation accuracy. The proposed method has been implemented and tested on 1000 road images which contain large variations in color, texture, lighting condition and surrounding environment. The experimental results demonstrate that this new voting method is both efficient and effective in detecting the vanishing point from a single road image and requires much less computational cost when compared to the previous voting method.

To obtain text information included in a scene image, we first need to extract text regions from the image before recognizing the text. In this paper, we examine human vision and propose a novel method to extract text regions by evaluating textural variation. Human beings are often attracted by textural variation in scenes, which causes foveation. We frame a hypothesis that texts also have similar property that distinguishes them from the natural background. In our method, we calculate spatial variation of texture to obtain the distribution of the degree of likelihood of text region. Here we evaluate the changes in local spatial spectrum as the textural variation. We investigate two options to evaluate the spectrum, that is, those based on one- and two-dimensional Fourier transforms. In particular, in this paper, we put emphasis on the one-dimensional transform, which functions like the Gabor filter. The proposal can be applied to a wide range of characters mainly because it employs neither templates nor heuristics concerning character size, aspect ratio, specific direction, alignment, and so on. We demonstrate that the method effectively extracts text regions contained in various general scene images. We present quantitative evaluation of the method by using databases open to the public.

In this paper, we address the problem of the rotation-invariant texture analysis. For this purpose, we first present a modified version of the discrete Radon transform whose performance, including accuracy and processing time, is significantly better than the conventional transform in direction estimation and categorization of textural images. We then utilize this transform with a rotated version of Gabor filters to propose a new scheme for texture classification. Experimental results on a set of images from the Brodatz album indicate that the proposed scheme outperforms previous works.

This paper proposes a new method of retrieving images from large image databases. The method is based on VQ (Vector Quantization) of local texture features at interest points automatically detected in an image. The texture features are extracted by Gabor wavelet filter bank, and rearranged for rotation. These features are classified by VQ and then construct a pattern histogram. Retrievals are performed by just comparing pattern histograms between images.

This paper presents a novel approach to water pollution detection from remotely sensed low-platform mounted visible band camera images. We examine the feasibility of unsupervised segmentation for slick (oily spills on the water surface) region labelling. Adaptive and non adaptive filtering is combined with density modeling of the obtained textural features. A particular effort is concentrated on the textural feature extraction from raw intensity images using filter banks and adaptive feature extraction from the obtained output coefficients. Segmentation in the extracted feature space is achieved using Gaussian mixture models (GMM).

A framework is proposed for segmenting image textures by using Gabor filters to detect boundaries between adjacent textured regions. By performing a multi-channel filtering of the input image with a small set of adaptively selected Gabor filters, tuned to underlying textures, feature images are obtained. To reduce the variance of the filter output for better texture boundary detection, a Gaussian post-filter is applied to the Gabor filter response over each channel. Significant local variations in each channel response are detected using a gradient operator, and combined through channel grouping to produce the texture gradient. A subsequent post-processing produces expected texture boundaries. The effectiveness of the proposed technique is demonstrated through experiments on synthetic and natural textures.

A novel neural network architecture for image texture classification is introduced. The proposed model (Kernel Modifying Neural Network: KM Net) which incorporates the convolution filter kernel and the classifier in one, enables an automated texture feature extraction in multichannel texture classification through the modification of the kernel and the connection weights by the backpropagation-based training rule. The first layer units working as the convolution kernels are constrained to be an array of Gabor filters, which achieves a most efficient texture feature localization. The following layers work as a classifier of the extracted texture feature vectors. The capability of the KM Net and its training rule is verified using a basic problem on a synthetic texture image. In addition, the possibilities of applying the KM Net to natural texture classification and biological tissue classification using an ultrasonic echo image have been tried.

This paper presents a modified disparity measurement to recover the depth and a robust method to estimate motion parameters. First, this paper considers phase correspondence for the computation of disparity. It has less computation for disparity than previous methods that use the disparity from correspondence and from correlation. This modified disparity measurement uses the Gabor filter to analyze the local phase property and the exponential filter to analyze the global phase property. These two phases are added to make quasi-linear phases of the stereo image channels which are used for the stereo disparity finding and the structure recovery of scene. Then, we use feature-based correspondence to find the corresponding feature points in temporal image pair. Finally, we combine the depth map and use disparity motion stereo to estimate 3-D motion parameters.