Polar Fourier Descriptor(PFD) and Spherical Fourier Descriptor(SFD) are rotation invariant feature descriptors for two dimensional(2D) and three dimensional(3D) image retrieval and pattern recognition tasks. They are demonstrated to show superiorities compared with other methods on describing rotation invariant features of 2D and 3D images. However in order to increase the computation speed, fast computation method is needed especially for machine vision applications like realtime systems, limited computing environments and large image databases. This paper presents fast computation method for PFD and SFD that are deduced based on mathematical properties of trigonometric functions and associated Legendre polynomials. Proposed fast PFD and SFD are 8 and 16 times faster than direct calculation that significantly boost computation process. Furthermore, the proposed methods are also compact for memory requirements for storing PFD and SFD basis in lookup tables. The experimental results on both synthetic and real data are given to illustrate the efficiency of the proposed method.

In this study, we propose a simple, yet general and powerful framework of integrating multiple global and local features by Product Sparse Coding (PSC) for image retrieval. In our framework, multiple global and local features are extracted from images and then are transformed to Trimmed-Root (TR)-features. After that, the features are encoded into compact codes by PSC. Finally, a two-stage ranking strategy is proposed for indexing in retrieval. We make three major contributions in this study. First, we propose TR representation of multiple image features and show that the TR representation offers better performance than the original features. Second, the integrated features by PSC is very compact and effective with lower complexity than by the standard sparse coding. Finally, the two-stage ranking strategy can balance the efficiency and memory usage in storage. Experiments demonstrate that our compact image representation is superior to the state-of-the-art alternatives for large-scale image retrieval.

This paper presents a color-based method for medicine package recognition, called a linear manifold color descriptor (LMCD). It describes a color distribution (a set of color pixels) of a color package image as a linear manifold (an affine subspace) in the color space, and recognizes an anonymous package by linear manifold matching. Mainly due to low dimensionality of color spaces, LMCD can provide more compact description and faster computation than description styles based on histogram and dominant-color. This paper also proposes distance-based dissimilarities for linear manifold matching. Specially designed for color distribution matching, the proposed dissimilarities are theoretically appropriate more than J-divergence and canonical angles. Experiments on medicine package recognition validates that LMCD outperforms competitors including MPEG-7 color descriptors in terms of description size, computational cost and recognition rate.

This paper proposes an improved color barycenter model (CBM) and its separation for automatic road sign (RS) detection. The previous version of CBM can find out the colors of RS, but the accuracy is not high enough for separating the magenta and blue regions and the influence of number with the same color are not considered. In this paper, the improved CBM expands the barycenter distribution to cylindrical coordinate system (CCS) and takes the number of colors at each position into account for clustering. Under this distribution, the color information can be represented more clearly for analyzing. Then aim to the characteristic of barycenter distribution in CBM (CBM-BD), a constrained clustering method is presented to cluster the CBM-BD in CCS. Although the proposed clustering method looks like conventional K-means in some part, it can solve some limitations of K-means in our research. The experimental results show that the proposed method is able to detect RS with high robustness.

We are interested in retrieving video shots or videos containing particular people from a video dataset. Owing to the large variations in pose, illumination conditions, occlusions, hairstyles and facial expressions, face tracks have recently been researched in the fields of face recognition, face retrieval and name labeling from videos. However, when the number of face tracks is very large, conventional methods, which match all or some pairs of faces in face tracks, will not be effective. Therefore, in this paper, an efficient method for finding a given person from a video dataset is presented. In our study, in according to performing research on face tracks in a single video, we also consider how to organize all the faces in videos in a dataset and how to improve the search quality in the query process. Different videos may include the same person; thus, the management of individuals in different videos will be useful for their retrieval. The proposed method includes the following three points. (i) Face tracks of the same person appearing for a period in each video are first connected on the basis of scene information with a time constriction, then all the people in one video are organized by a proposed hierarchical clustering method. (ii) After obtaining the organizational structure of all the people in one video, the people are organized into an upper layer by affinity propagation. (iii) Finally, in the process of querying, a remeasuring method based on the index structure of videos is performed to improve the retrieval accuracy. We also build a video dataset that contains six types of videos: films, TV shows, educational videos, interviews, press conferences and domestic activities. The formation of face tracks in the six types of videos is first researched, then experiments are performed on this video dataset containing more than 1 million faces and 218,786 face tracks. The results show that the proposed approach has high search quality and a short search time.

The topic of retrieving videos containing a desired person from a dataset just using the content of faces without any help of textual information has many interesting applications like video surveillance, social network, video mining, etc. However, traditional face matching against a huge number of detected faces leads to an unacceptable response time and may also reduce the accuracy due to the large variations in facial expressions, poses, lighting, etc. Therefore, in this paper we propose a novel method to generate discriminative “signatures” for efficiently retrieving the videos containing the same person with a query. In this research, the signature is defined as a compact, discriminative and reduced dimensionality representation, which is generated from a set of high-dimensional feature vectors of an individual. The desired videos are retrieved based on the similarities between the signature of the query and those of individuals in the database. In particular, we make the following contributions. Firstly, we give an algorithm of two directional linear discriminant analysis with maximum correntropy criterion (2DLDA-MCC) as an extension to our recently proposed maximum correntropy criterion based linear discriminant analysis (LDA-MCC). Both algorithms are robust to outliers and noise. Secondly, we present an approach for transferring a set of exemplars to a fixed-length signature using LDA-MCC and 2DLDA-MCC, resulting in two kinds of signatures that are called 1D signature and 2D signature. Finally, a novel video retrieval scheme is given based on the signatures, which has low storage requirement and can achieve a fast search. Evaluations on a large dataset of videos show reliable measurement of similarities by using the proposed signatures to represent the identities generated from videos. Experimental results also demonstrate that the proposed video retrieval scheme has the potential to substantially reduce the response time and slightly increase the mean average precision of retrieval.

The classification of remotely sensed multispectral data using classical statistical methods has been worked on for several decades. Recently there have been many new developments in neural network (NN) research, and many new applications have been studied. It is well known that NN approaches have the ability to classify without assuming a distribution. We have proposed an NN model to combine the spectral and spacial information of a LANDSAT TM image. In this paper, we apply the NN approach with a normalization method to classify multi-temporal LANDSAT TM images in order to investigate the robustness of our approach. From our experiments, we have confirmed that our approach is more effective for the classification of multi-temporal data than the original NN approach and maximum likelihood approach.

Recently applications of Hilbert curves are studied in the area of image processing, image compression, computer hologram, etc. We have proposed a fast Hilbert scanning algorithm using lookup tables in N dimensional space. However, this scan is different from the one of previously proposed scanning algorithms. Making the lookup tables is a problem for the generation of several Hilbert scans. In this note, we describe a method of making lookup tables from a given Hilbert scan which is obtained by other scanning methods.

The influence of noise is an important problem on image acquisition and transmission stages. The traditional image denoising approaches only analyzing the pixels of local region with a moving window, which calculated by neighbor pixels to denoise. Recently, this research has been focused on the transform domain and feature space. Compare with the traditional approaches, the global multi-scale analyzing and unchangeable noise distribution is the advantage. Apparently, the estimation based methods can be used in transform domain and get better effect. This paper proposed a new approach to image denoising in orthonormal wavelet domain. In this paper, we adopt Stein's unbiased risk estimate (SURE) based method to denoise the low-frequency bands and the feature patches distance constraint (FPDC) method also be proposed to estimate the noise free bands in Wavelet domain. The key point is that how to divide the lower frequency sub-bands and the higher frequency sub-bands, and do interscale SURE and intrascale FPDC, respectively. We compared our denoising method with some well-known and new denoising algorithms, the experimental results show that the proposed method can give better performance and keep more detail information in most objective and subjective criteria than other methods.

Polar and Spherical Fourier analysis can be used to extract rotation invariant features for image retrieval and pattern recognition tasks. They are demonstrated to show superiorities comparing with other methods on describing rotation invariant features of two and three dimensional images. Based on mathematical properties of trigonometric functions and associated Legendre polynomials, fast algorithms are proposed for multimedia applications like real time systems and large multimedia databases in order to increase the computation speed. The symmetric points are computed simultaneously. Inspired by relative prime number theory, systematic analysis are given in this paper. Novel algorithm is deduced that provide even faster speed. Proposed method are 9–15% faster than previous work. The experimental results on two and three dimensional images are given to illustrate the effectiveness of the proposed method. Multimedia signal processing applications that need real time polar and spherical Fourier analysis can be benefit from this work.

In this paper, we propose a novel approach for presenting the local features of digital image using 1D Local Patterns by Multi-Scans (1DLPMS). We also consider the extentions and simplifications of the proposed approach into facial images analysis. The proposed approach consists of three steps. At the first step, the gray values of pixels in image are represented as a vector giving the local neighborhood intensity distrubutions of the pixels. Then, multi-scans are applied to capture different spatial information on the image with advantage of less computation than other traditional ways, such as Local Binary Patterns (LBP). The second step is encoding the local features based on different encoding rules using 1D local patterns. This transformation is expected to be less sensitive to illumination variations besides preserving the appearance of images embedded in the original gray scale. At the final step, Grouped 1D Local Patterns by Multi-Scans (G1DLPMS) is applied to make the proposed approach computationally simpler and easy to extend. Next, we further formulate boosted algorithm to extract the most discriminant local features. The evaluated results demonstrate that the proposed approach outperforms the conventional approaches in terms of accuracy in applications of face recognition, gender estimation and facial expression.

To find the best transformation between a "model" point set and an "image" point set is the main purpose of point pattern matching. The similarity measure plays a pivotal role and is used to determine the degree of resemblance between two objects. Although some well-known Hausdorff distance measures work well for this task, they are very computationally expensive and suffer from the noise points. In this paper, we propose a novel similarity measure using the Hilbert curve named Hilbert scanning distance (HSD) to resolve the problems. This method computes the distance measure in the one-dimensional (1-D) sequence instead of in the two-dimensional (2-D) space, which greatly reduces the computational complexity. By applying a threshold elimination function, large distance values caused by noise and position errors (e.g. those that occur with feature or edge extraction) are removed. The proposed algorithm has been applied to the task of matching edge maps with noise. The experimental results show that HSD can provide sufficient information for image matching within low computational complexity. We believe this sets a new direction for the research of point pattern recognition.

This paper presents a novel color descriptor based on the proposed Color Barycenter Hexagon (CBH) model for automatic Road-Sign (RS) detection. In the visual Driver Assistance System (DAS), RS detection is one of the most important factors. The system provides drivers with important information on driving safety. Different color combinations of RS indicate different functionalities; hence a robust color detector should be designed to address color changes in natural surroundings. The CBH model is constructed with barycenter distribution in the created color triangle, which represents RS colors in a more compact way. For detecting RS, the CBH model is used to segment color information at the initial step. Furthermore, a judgment process is applied to verify each RS candidate through the size, aspect ratio, and color ratio. Experimental results show that the proposed method is able to detect RS with robust, accurate performance and is invariant to light and scale in more complex surroundings.

The N-dimensional (N-D) Hilbert curve is a one-to-one mapping between N-D space and one-dimensional (1-D) space. It is studied actively in the area of digital image processing as a scan technique (Hilbert scan) because of its property of preserving the spatial relationship of the N-D patterns. Currently there exist several Hilbert scan algorithms. However, these algorithms have two strict restrictions in implementation. First, recursive functions are used to generate a Hilbert curve, which makes the algorithms complex and computationally expensive. Second, all the sides of the scanned region must have the same size and the length must be a power of two, which limits the application of the Hilbert scan greatly. Thus in order to remove these constraints and improve the Hilbert scan for general application, a nonrecursive N-D Pseudo-Hilbert scan algorithm based on two look-up tables is proposed in this paper. The merit of the proposed algorithm is that implementation is much easier than the original one while preserving the original characteristics. The experimental results indicate that the Pseudo-Hilbert scan can preserve point neighborhoods as much as possible and take advantage of the high correlation between neighboring lattice points, and it also shows the competitive performance of the Pseudo-Hilbert scan in comparison with other common scan techniques. We believe that this novel scan technique undoubtedly leads to many new applications in those areas can benefit from reducing the dimensionality of the problem.

With the wide usage of multispectral images, a fast efficient multidimensional clustering method becomes not only meaningful but also necessary. In general, to speed up the multidimensional images' analysis, a multidimensional feature vector should be transformed into a lower dimensional space. The Hilbert curve is a continuous one-to-one mapping from N-dimensional space to one-dimensional space, and can preserves neighborhood as much as possible. However, because the Hilbert curve is generated by a recurve division process, 'Boundary Effects' will happen, which means data that are close in N-dimensional space may not be close in one-dimensional Hilbert order. In this paper, a new efficient approach based on the space-filling curves is proposed for classifying multispectral satellite images. In order to remove 'Boundary Effects' of the Hilbert curve, multiple Hilbert curves, z curves, and the Pseudo-Hilbert curve are used jointly. The proposed method extracts category clusters from one-dimensional data without computing any distance in N-dimensional space. Furthermore, multispectral images can be analyzed hierarchically from coarse data distribution to fine data distribution in accordance with different application. The experimental results performed on LANDSAT data have demonstrated that the proposed method is efficient to manage the multispectral images and can be applied easily.

Image enhancement plays an important role in many machine vision applications on images captured in low contrast and low illumination conditions. In this study, we propose a new method for image enhancement based on analysis on embedded surfaces of images. The proposed method gives an insight into the relationship between the image intensity and image enhancement. In our method, scaled surface area and the surface volume are proposed and used to reconstruct the image iteratively for contrast enhancement, and the illumination of the reconstructed image can also be adjusted simultaneously. On the other hand, the most common methods for measuring the quality of enhanced images are Mean Square Error (MSE) or Peak Signal-to-Noise-Ratio (PSNR) in conventional works. The two measures have been recognized as inadequate ones because they do not evaluate the result in the way that the human vision system does. This paper also presents a new framework for evaluating image enhancement using both objective and subjective measures. This framework can also be used for other image quality evaluations such as denoising evaluation. We compare our enhancement method with some well-known enhancement algorithms, including wavelet and curvelet methods, using the new evaluation framework. The results show that our method can give better performance in most objective and subjective criteria than the conventional methods.

Hypercomplex polar Fourier analysis treats a signal as a vector field and generalizes the conventional polar Fourier analysis. It can handle signals represented by hypercomplex numbers such as color images. Hypercomplex polar Fourier analysis is reversible that means it can reconstruct image. Its coefficient has rotation invariance property that can be used for feature extraction. However in order to increase the computation speed, fast algorithm is needed especially for image processing applications like realtime systems and limited resource platforms. This paper presents fast hypercomplex polar Fourier analysis based on symmetric properties and mathematical properties of trigonometric functions. Proposed fast hypercomplex polar Fourier analysis computes symmetric points simultaneously, which significantly reduce the computation time.

In recent years, deep learning based approaches have substantially improved the performance of face recognition. Most existing deep learning techniques work well, but neglect effective utilization of face correlation information. The resulting performance loss is noteworthy for personal appearance variations caused by factors such as illumination, pose, occlusion, and misalignment. We believe that face correlation information should be introduced to solve this network performance problem originating from by intra-personal variations. Recently, graph deep learning approaches have emerged for representing structured graph data. A graph is a powerful tool for representing complex information of the face image. In this paper, we survey the recent research related to the graph structure of Convolutional Neural Networks and try to devise a definition of graph structure included in Compressed Sensing and Deep Learning. This paper devoted to the story explain of two properties of our graph - sparse and depth. Sparse can be advantageous since features are more likely to be linearly separable and they are more robust. The depth means that this is a multi-resolution multi-channel learning process. We think that sparse graph based deep neural network can more effectively make similar objects to attract each other, the relative, different objects mutually exclusive, similar to a better sparse multi-resolution clustering. Based on this concept, we propose a sparse graph representation based on the face correlation information that is embedded via the sparse reconstruction and deep learning within an irregular domain. The resulting classification is remarkably robust. The proposed method achieves high recognition rates of 99.61% (94.67%) on the benchmark LFW (YTF) facial evaluation database.

Seed detection or sometimes known as nuclei detection is a prerequisite step of nuclei segmentation which plays a critical role in quantitative cell analysis. The detection result is considered as accurate if each detected seed lies only in one nucleus and is close to the nucleus center. In previous works, voting methods are employed to detect nucleus center by extracting the nucleus saliency features. However, these methods still encounter the risk of false seeding, especially for the heterogeneous intensity images. To overcome the drawbacks of previous works, a novel detection method is proposed, which is called secant normal voting. Secant normal voting achieves good performance with the proposed skipping range. Skipping range avoids over-segmentation by preventing false seeding on the occlusion regions. Nucleus centers are obtained by mean-shift clustering from clouds of voting points. In the experiments, we show that our proposed method outperforms the comparison methods by achieving high detection accuracy without sacrificing the computational efficiency.

Generally, two problems of bag-of-features in image retrieval are still considered unsolved: one is that spatial information about descriptors is not employed well, which affects the accuracy of retrieval; the other is that the trade-off between vocabulary size and good precision, which decides the storage and retrieval performance. In this paper, we propose a novel approach called Hilbert scan based bag-of-features (HS-BoF) for image retrieval. Firstly, Hilbert scan based tree representation (HSBT) is studied, which is built based on the local descriptors while spatial relationships are added into the nodes by a novel grouping rule, resulting of a tree structure for each image. Further, we give two ways of codebook production based on HSBT: multi-layer codebook and multi-size codebook. Owing to the properties of Hilbert scanning and the merits of our grouping method, sub-regions of the tree are not only flexible to the distribution of local patches but also have hierarchical relations. Extensive experiments on caltech-256, 13-scene and 1 million ImageNet images show that HS-BoF obtains higher accuracy with less memory usage.