基于GPGPU的数字图像并行化预处理

首先简要介绍了统一设备架构CUDA(Compute Unified Device Architecture)技术的背景、特点、内存模型,利用通用计算图形处理单元GPGPU(General Purpose GPU)及CUDA技术,实现了图像直方图均衡化和薄云去除的并行化处理,与传统的基于CPU的方法相比,两个基于GPGPU的图像预处理操作的执行效率分别提高了40倍与80倍左右,在大规模实时性图像处理操作中,有很大的实用价值。     

Revisiting Multiple Pattern Matching Algorithms for Multi-Core Architecture

Due to the huge size of patterns to be searched,multiple pattern searching remains a challenge to several newly-arising applications like network intrusion detection.In this paper,we present an attempt to design efficient multiple pattern searching algorithms on multi-core architectures.We observe an important feature which indicates that the multiple pattern matching time mainly depends on the number and minimal length of patterns.The multi-core algorithm proposed in this paper leverages this feature to decompose pattern set so that the parallel execution time is minimized.We formulate the problem as an optimal decomposition and scheduling of a pattern set,then propose a heuristic algorithm,which takes advantage of dynamic programming and greedy algorithmic techniques,to solve the optimization problem.Experimental results suggest that our decomposition approach can increase the searching speed by more than 200% on a 4-core AMD Barcelona system.     

SIMPLIcity: semantics-sensitive integrated matching for picturelibraries

We present here SIMPLIcity (semantics-sensitive integrated matching for picture libraries), an image retrieval system, which uses semantics classification methods, a wavelet-based approach for feature extraction, and integrated region matching based upon image segmentation. An image is represented by a set of regions, roughly corresponding to objects, which are characterized by color, texture, shape, and location. The system classifies images into semantic categories. Potentially, the categorization enhances retrieval by permitting semantically-adaptive searching methods and narrowing down the searching range in a database. A measure for the overall similarity between images is developed using a region-matching scheme that integrates properties of all the regions in the images. The application of SIMPLIcity to several databases has demonstrated that our system performs significantly better and faster than existing ones. The system is fairly robust to image alterations     

Texture-based pattern retrieval from image databases

Recent technological advances have made it possible to process and store large amounts of image data. Perhaps the most impressive example is the accumulation of image data in scientific applications such as medical or satellite imagery. However, in order to realize their full potential, tools for efficient extraction of information and for intelligent searches in image databases need to be developed. This paper describes a new approach to image data retrieval which allows queries to be composed of local intensity patterns. The intensity pattern is converted into a feature representation of reduced dimensionality which can be used for searching similar-looking patterns in the database. This representation is obtained by filtering the pattern with a bank of scale and orientation selective filters modeled using Gabor functions. Experimental results are presented which illustrate that the proposed representation preserves the perceptual similarities, and provides a powerful tool for content-based image retrieval.     

基于先验置信传播的图像修复改进算法

先验置信传播(priority-BP)算法很难在实际中达到实时处理的要求,计算效率也有很大的提升空间。针对先验BP算法在图像修复上的应用,改进算法主要在信息传递以及标签搜索方面提出改进措施。在信息传递方面,改进的算法在初次迭代前利用图像的稀疏表示,快速更新目标区域的初始图像信息,为首次迭代提供更为准确的先验值,加速信息传递的收敛速度,并提高标签裁减和传递消息的准确度;在搜索策略方面,改进的先验BP算法舍弃了单一的全局搜索方法,在全局搜索中结合局部搜索方式,提高了标签集的组建效率。最后,将改进算法用于实例验证,待修复图像尺寸越大,改进算法优势越明显,即使在较小的图像尺寸(120×126)下,改进算法修复效果的峰值信噪比(PSNR)相对原算法平均提高了1.1 dB, 修复时间减少了接近1.2 s。实例验证结果表明该算法不但可以有效地提高图像修复的精度,而且提高了图像修复的效率。     

Supporting image retrieval framework with rule base system

The present paper introduces an image retrieval framework based on a rule base system. The proposed framework makes use of color and texture features, respectively called color co-occurrence matrix (CCM) and difference between pixels of scan pattern (DBPSP). These features are used to perform the image mining for acquiring clustering knowledge from a large empirical images database. Irrelevance between images of the same cluster is precisely considered in the proposed framework through a relevance feedback phase followed by a novel clustering refinement model. The images and their corresponding classes pass to a rule base system for extracting a set of accurate rules. These rules are pruning and may reduce the dimensionality of the extracted features. The advantage of the proposed framework is reflected in the retrieval process, which is limited to the images in the class of rule matched with the query image features. Experiments show that the proposed model achieves a very good performance in terms of the average precision, recall and retrieval time compared with other models.     

Real-time view-based pose recognition and interpolation for tracking initialization

In this paper we propose a new approach to real-time view-based pose recognition and interpolation. Pose recognition is particularly useful for identifying camera views in databases, video sequences, video streams, and live recordings. All of these applications require a fast pose recognition process, in many cases video real-time. It should further be possible to extend the database with new material, i.e., to update the recognition system online. The method that we propose is based on P-channels, a special kind of information representation which combines advantages of histograms and local linear models. Our approach is motivated by its similarity to information representation in biological systems but its main advantage is its robustness against common distortions such as clutter and occlusion. The recognition algorithm consists of three steps: (1) low-level image features for color and local orientation are extracted in each point of the image; (2) these features are encoded into P-channels by combining similar features within local image regions; (3) the query P-channels are compared to a set of prototype P-channels in a database using a least-squares approach. The algorithm is applied in two scene registration experiments with fisheye camera data, one for pose interpolation from synthetic images and one for finding the nearest view in a set of real images. The method compares favorable to SIFT-based methods, in particular concerning interpolation. The method can be used for initializing pose-tracking systems, either when starting the tracking or when the tracking has failed and the system needs to re-initialize. Due to its real-time performance, the method can also be embedded directly into the tracking system, allowing a sensor fusion unit choosing dynamically between the frame-by-frame tracking and the pose recognition.     

面向无载体信息隐藏的映射关系智能搜索方法

传统的搜索式无载体信息隐藏技术建立在固定的映射规则与庞大的图像库基础上,依赖于复杂的人工特征提取并且需要进行大量搜索来构建合适的图像库。针对这些问题,本文提出了一种面向无载体信息隐藏的基于深度学习映射关系智能搜索方法,该方法从已有图像库出发,基于深度神经网络,自动搜索一套高容量、高覆盖率的映射关系,从而解决传统人工方法存在的传输开销大、图像库建立困难的问题。除此以外,实验表明我们的方法相较于传统无载体方法有更强的鲁棒性。     

GAISP:一种GPU加速的天文图像相减测光算法*

为了解决天文图像相减测光存在的性能问题,满足特殊条件下天文观测的实时性要求,在充分分析原始测光算法整体性能的基础上,结合CUDA并行编程模型,并行优化测光算法中模板图像降晰的计算,提出并实现了一种GPU加速的测光算法GAISP。实验结果表明,GAISP在处理较大规模天文图像时,图像相减部分耗时较原始算法降低2/3。     

A fractal-based clustering approach in large visual database systems

Large visual database systems require effective and efficient ways of indexing and accessing visual data on the basis of content. In this process, significant features must first be extracted from image data in their pixel format. These features must then be classified and indexed to assist efficient access to image content. With the large volume of visual data stored in a visual database, image classification is a critical step to achieve efficient indexing and retrieval. In this paper, we investigate an effective approach to the clustering of image data based on the technique of fractal image coding, a method first introduced in conjunction with fractal image compression technique. A joint fractal coding technique, applicable to pairs of images, is used to determine the degree of their similarity. Images in a visual database can be categorized in clusters on the basis of their similarity to a set of iconic images. Classification metrics are proposed for the measurement of the extent of similarity among images. By experimenting on a large set of texture and natural images, we demonstrate the applicability of these metrics and the proposed clustering technique to various visual database applications.     

GPU近实时线性双目立体代价聚合

目的 近年来双目视觉领域的研究重点逐步转而关注其“实时化”策略的研究,而立体代价聚合是双目视觉中最为复杂且最为耗时的步骤,为此,提出一种基于GPU通用计算(GPGPU)技术的近实时双目立体代价聚合算法。方法 选用一种匹配精度接近于全局匹配算法的局部算法——线性立体匹配算法(linear stereo matching)作为代价聚合策略;结合线性代价聚合的原理,对其主要步骤(代价计算、均值滤波及系数求解等)的计算流程进行有针对性地并行优化。结果 对于相同的实验样本,用本文方法在NVIDA GTX780 实验平台上能在更短的时间计算出代价矩阵,与原有的CPU实现方法相比,代价聚合的效率平均有了数十倍的提升。结论 实时双目立体代价聚合方法,为在个人通用PC平台上实时获取高质量双目视觉深度信息提供了一个高效可靠的途径。     

Soft-computing based diagnostic tool for analyzing demyelination in magnetic resonance images

This paper proposes a soft-computing based diagnostic tool for analyzing (white matter changes) demyelination due to radiation therapy given to brain tumor cases. The tool exploits the pattern of changes in gray level distribution using a temporal sequence of magnetic resonance (MR) images. Appearance of white matter changes due to demyelination varies from patient to patient. Further, there exists inherent impreciseness in the white matter change patterns. These characteristics make use of fuzzy features well suited for describing image based temporal patterns. Correlation between these temporal patterns and actual onset of demyelination can be captured by fuzzy rules because of the inherent uncertainty associated with changes in gray level pattern in the image and occurrence of the disease. The tool is based on hybrid approach of two popular approaches of genetic algorithm based machine learning (GBML) techniques namely Michigan and Pittsburgh approach. The genetic algorithm (GA) based machine learning tool generates an optimized rule set to indicate positive (P), negative (N) or doubtful (D) cases of demyelination.     

基于改进的排序学习的图片检索算法研究

图片检索是图片共享社会网络中的重要研究内容之一。传统的图片检索方法往往通过对用户输入的关键字和图片的文本描述加以匹配来进行图片检索。由于文本信息存在歧义性,图片的文本描述十分困难,因此检索结果的准确性低。为了提高图片检索的准确性,提出了基于排序学习的图片检索方法。将每幅图片通过多种特征描述符进行描述,当用户的输入为图片时,通过对比查询图片和图片库中图片的相似性进行图片检索。采用支持向量机和关联规则两种学习方法对特征描述符的权重组合进行学习,并提出了相应的学习算法。实验表明,提出的基于学习的图片检索方法与相关图片检索方法相比具有更高的准确性。此外,应用支持向量机和关联规则两种方法对分类函数进行学习时,由于两种算法通过相同的数据实例对图片描述符的权重进行学习,因此得到的结果是相关的。     

基于GPU的血管造影图像增强方法*

血管增强扩散算法遵循多尺度方法,利用非线性各向异性扩散方法进行血管增强,该方法在可视化不同半径的血管和增强血管外观上比现存的大部分方法都要好,但医学图像数据分辨率和灰度级都很高,多尺度选择和求解非线性各向异性扩散的偏微分方程时运算量很大,执行速率低,不适合实际应用。提出一种基于GPU(graphic processing unit)的血管造影图像增强方法,采用计算统一设备架构(CUDA)技术,利用像素的独立性和偏微分方程求解的并发性,实现了并行血管增强扩散算法。实验结果表明,该方法在保持血管增强效果一样的同时降低了处理时间,加速比达到27倍以上。     

A study on vulnerability and presentation attack detection in palmprint verification system

As biometric systems become ubiquitous in the domain of personal authentication, it is of utmost importance that these systems are secured against attacks. Among various types of attacks on biometric systems, the presentation attack, which involves presenting a fake copy (artefact) of the real biometric to the biometric sensor to gain illegitimate access, is the most common one. Despite the serious threat posed by these attacks, not much work has been done to address this vulnerability in palmprint-based biometric systems. This paper demonstrates the vulnerability of a palmprint verification system to presentation attacks and proposes a novel presentation attack detection (PAD) approach to discriminating between real biometric samples and artefacts. The proposed PAD approach is inspired by a work that established relationship between the surface reflectance and a set of statistical features extracted from the image. Specifically, statistical features computed from the distributions of pixel intensities, sub-band wavelet coefficients and the grey-level co-occurrence matrix form the original feature set, and CFS-based feature selection approach selects the most discriminating feature subset. A trained binary classifier utilizes the selected feature subset to determine whether the acquired image is of real hand or an artefact. For performance evaluation, an antispoofing database—PALMspoof has been developed. This database comprises left- and right-hand images of 104 subjects, and three kinds of artefacts generated from these images. In addition to PALMspoof database, the biometric system’s vulnerability has been assessed on display and print artefacts generated from two publicly available palmprint datasets. Our experimental results show that 1) the palmprint verification system is highly vulnerable with spoof acceptance of 84.56%; 2) the proposed PAD approach is effective against both print and display attacks, in both same-device and cross-device scenarios; and 3) the proposed approach for PAD provides an average improvement of 12.73 percentage points in classification error rate over local binary pattern (LBP)-based PAD approach.     

A binary partitioning approach to image compression using weighted finite automata for large images

Fractal-based image compression techniques give efficient decoding time with primitive hardware requirements, and favor real-time communication purposes. One such technique, the weighted finite automata (WFA), is studied on grayscale images. An improved image partitioning technique—the binary or bintree partitioning—is tested on the WFA encoding method. Experimental results show that binary partitioning consistently gives higher compression ratios than the conventional quadtree partitioning method for large images. Moreover, the ability to decode images progressively rendering finer and finer details can be used to display the image over a congested and loss-prone network such as the image transport protocol (ITP) for the Internet, as well as to pave way for multilayered error protection over an often unreliable networking environment. Also, the proposed partitioning approach can be parallelized to reduce its high encoding complexity.     

多姿态人脸照片的姿态估计

提出了一种基于面部图像的新的匹配系统。在这个系统中,输入的图像与各种人脸姿态的数据库图像进行比较,然后,匹配的图像给出了人脸姿态。图像数据库不仅包括各种人脸姿态,而且也包括不同的光照条件,如此,这个人脸姿态评价系统适用于不同的光照条件。对于收集各种不同面部图像,这里是通过计算机自动产生,而不是拍摄实际的照片。特征空间方法被用于寻找与输入面部图像匹配的图像。因为不同的光照图像被收集在面部图像数据库中,故提取的主特征向量主要依靠人脸姿态。由于通过选用主特征向量而减少了向量的维数,故这个匹配过程是很快的。这个姿态评价系统能够继续跟踪在不同的光照条件下不同人的人脸姿态。