Evaluating object DBMSs for multimedia

We describe functionality for determining an object database management system's suitability for developing multimedia applications. We discuss all levels of hardware and software support, as even the most ideal database software cannot operate independent of operating systems, networks and hardware. A review of the multimedia support provided by current commercial and research object database management systems is also included     

Local maximum edge binary patterns: A new descriptor for image retrieval and object tracking

A new algorithm meant for content based image retrieval (CBIR) and object tracking applications is presented in this paper. The local region of image is represented by local maximum edge binary patterns (LMEBP), which are evaluated by taking into consideration the magnitude of local difference between the center pixel and its neighbors. This LMEBP differs from the existing LBP in a manner that it extracts the information based on distribution of edges in an image. Further, the effectiveness of our algorithm is confirmed by combining it with Gabor transform. Four experiments have been carried out for proving the worth of our algorithm. Out of which three are meant for CBIR and one for object tracking. It is further mentioned that the database considered for first three experiments are Brodatz texture database (DB1), MIT VisTex database (DB2), rotated Brodatz database (DB3) and the fourth contains three observations. The results after being investigated show a significant improvement in terms of their evaluation measures as compared to LBP and other existing transform domain techniques.     

Retinal vessel centerline extraction using multiscale matched filters, confidence and edge measures

Motivated by the goals of improving detection of low-contrast and narrow vessels and eliminating false detections at nonvascular structures, a new technique is presented for extracting vessels in retinal images. The core of the technique is a new likelihood ratio test that combines matched-filter responses, confidence measures and vessel boundary measures. Matched filter responses are derived in scale-space to extract vessels of widely varying widths. A vessel confidence measure is defined as a projection of a vector formed from a normalized pixel neighborhood onto a normalized ideal vessel profile. Vessel boundary measures and associated confidences are computed at potential vessel boundaries. Combined, these responses form a six-dimensional measurement vector at each pixel. A training technique is used to develop a mapping of this vector to a likelihood ratio that measures the "vesselness" at each pixel. Results comparing this vesselness measure to matched filters alone and to measures based on the Hessian of intensities show substantial improvements, both qualitatively and quantitatively. The Hessian can be used in place of the matched filter to obtain similar but less-substantial improvements or to steer the matched filter by preselecting kernel orientations. Finally, the new vesselness likelihood ratio is embedded into a vessel tracing framework, resulting in an efficient and effective vessel centerline extraction algorithm.     

基于标记提取的GrowCut自动分割算法

Grow Cut算法是基于细胞自动机的交互式图像分割方法,针对该算法要求用户标记初始种子需要较多工作量,且带有一定的主观性和不确定性,导致分割结果出现较大误差的问题,文中提出了简化标记,自动生成初始种子模板的基于标记提取的Grow Cut分割算法。该算法在Grow Cut算法基础上通过阈值和形态学方法预处理生成初始种子模板,运用细胞自动机迭代算法完成目标的提取。算法避免了用户人工交互约束的繁琐操作,实现了完全自动分割。通过实验对彩色图像进行自动分割,实验结果证明该算法简便、用时少,分割结果比较精确。     

Knowledge-assisted content based retrieval for multimedia databases

Unlike conventional databases, which manage only text and numerical data, multimedia databases must evaluate audio and visual properties of data. We propose a system of querying and content-based retrieval that considers audio or visual properties of multimedia data     

Combining static and dynamic features using neural networks and edge fusion for video object extraction

Semantic object representation is an important step for digital multimedia applications such as object-based coding, content-based access and manipulations. The authors propose an image sequence segmentation scheme which provides region information for the semantic object representation of those applications. The objective is to develop a hardware-friendly segmentation algorithm by combining static and dynamic features simultaneously in one scheme. In the initial stage, a multiple feature space is transformed to one-dimensional label space by using self-organising feature map (SOFM) neural networks. The next stage is an edge fusion process in which edge information is incorporated into the neural network outputs to generate more precisely located boundaries of segmentation. The proposed algorithm differs from existing methods as follows: it can segment textured images with low-dimensional features; leads to more meaningful segmentation region boundaries; and is easier to map into hardware than existing methods. Experimental results are compared with an existing segmentation method using evaluation metrics to clarify the advantages of the proposed algorithm objectively.     

Automatic cardiac LV boundary detection and tracking using hybrid fuzzy temporal and fuzzy multiscale edge detection

This paper describes a new fully automatic fuzzy multiresolution-based algorithm for cardiac left ventricular (LV) epicardial and endocardial boundary detection and tracking on a sequence of short axis (SA) echocardiographic images of a complete cardiac cycle. This is a necessary step for automatic quantification of cardiac function using echo images. The proposed method is a "center-based" approach in which epicardial and endocardial boundary edge points are searched for on radial lines emanating from the LV center point. The central point of the LV cavity is estimated using a fuzzy-based technique in which the "uncertain" spatial, morphological, and intensity information of the image are represented as fuzzy sets and then combined by fuzzy operators. Edge-detection stage uses multiscale spatial and temporal information in a fuzzy multiresolution framework to identify a single moving edge point for each one of the epicardial and endocardial boundaries over the M radii in the N frames of a complete cardiac cycle. The raw extracted edge points are then processed in the wavelet domain to reduce the effects of noise from the boundaries and papillary muscles from the endocardial boundary extraction process. Finally, a uniform cubic B-spline approximation method is used to define the closed LV boundaries. Experiments with simulated and real echocardiographic images are presented.     

The use of network delay estimation for multimedia data retrieval

Multimedia data have specific temporal presentation requirements. For example in video conferencing applications the voice and images of the participants must be delivered and presented synchronously. These requirements can be achieved by scheduling or managing system resources. We present a technique called limited a priori scheduling (LAP) to manage the delivery channel from source to destination for digital multimedia data. By using delay estimation a LAP scheduler can retrieve stored digital media spanning arbitrary networks with unspecified delays. The use of delay estimation also facilitates selective degradation of service in bandwidth and buffer limited situations. Such degradation enables the continuous real-time playout and synchronization of various media arriving from different sources. The performance of the LAP scheduler is described based on implementation and experimentation using Ethernet     

Automatic gradient threshold determination for edge detection

We describe a method to automatically find gradient thresholds to separate edge from nonedge pixels. A statistical model that is the weighted sum of two gamma densities corresponding to edge and nonedge pixels is used to identify a threshold. Results closely match human perceptual thresholds even under low signal-to-noise ratio (SNR) levels.     

An edge extraction technique for noisy images

We present an algorithm for extracting edges from noisy images. Our method uses an unsupervised learning approach for local threshold computation by means of Pearson's method for mixture density identification. We tested the technique by applying it to computer-generated images corrupted with artificial noise and to an actual Thallium-201 heart image and it is shown that the technique has potential use for noisy images.     

A multiscale random field model for Bayesian image segmentation

Many approaches to Bayesian image segmentation have used maximum a posteriori (MAP) estimation in conjunction with Markov random fields (MRF). Although this approach performs well, it has a number of disadvantages. In particular, exact MAP estimates cannot be computed, approximate MAP estimates are computationally expensive to compute, and unsupervised parameter estimation of the MRF is difficult. The authors propose a new approach to Bayesian image segmentation that directly addresses these problems. The new method replaces the MRF model with a novel multiscale random field (MSRF) and replaces the MAP estimator with a sequential MAP (SMAP) estimator derived from a novel estimation criteria. Together, the proposed estimator and model result in a segmentation algorithm that is not iterative and can be computed in time proportional to MN where M is the number of classes and N is the number of pixels. The also develop a computationally efficient method for unsupervised estimation of model parameters. Simulations on synthetic images indicate that the new algorithm performs better and requires much less computation than MAP estimation using simulated annealing. The algorithm is also found to improve classification accuracy when applied to the segmentation of multispectral remotely sensed images with ground truth data.     

Nonlinear multiscale wavelet diffusion for speckle suppression and edge enhancement in ultrasound images

This paper introduces a novel nonlinear multiscale wavelet diffusion method for ultrasound speckle suppression and edge enhancement. This method is designed to utilize the favorable denoising properties of two frequently used techniques: the sparsity and multiresolution properties of the wavelet, and the iterative edge enhancement feature of nonlinear diffusion. With fully exploited knowledge of speckle image models, the edges of images are detected using normalized wavelet modulus. Relying on this feature, both the envelope-detected speckle image and the log-compressed ultrasonic image can be directly processed by the algorithm without need for additional preprocessing. Speckle is suppressed by employing the iterative multiscale diffusion on the wavelet coefficients. With a tuning diffusion threshold strategy, the proposed method can improve the image quality for both visualization and auto-segmentation applications. We validate our method using synthetic speckle images and real ultrasonic images. Performance improvement over other despeckling filters is quantified in terms of noise suppression and edge preservation indices.     

Protocol architecture for multimedia applications over ATM networks

At the data-link layer, ATM offers a number of features, such as high-bandwidth and per-session quality-of-service (QoS) guarantees, making it particularly attractive to multimedia applications. Unfortunately, many of these features are not visible to applications because of the inadequacies of existing higher-level protocol architectures. Although there is considerable effort underway to tune these protocols for ATM networks, we believe that a new ATM-specific protocol stack is essential to effectively exploit all the benefits of ATM. We describe the semantics of such a protocol stack, and discuss its advantages over traditional protocol architectures from the perspective of multimedia applications. The performance impact of the new protocol architecture is experimentally demonstrated on a video conferencing testbed built around IBM RS/6000's equipped with prototype hardware for video/audio processing, and connected via ATM links     

High-bandwidth interface for multimedia communications over fixedwireless systems

Over the past two decades, cable television has largely supplanted over-the-air broadcast as a TV distribution medium. Several years ago, enterprising companies concluded that they could leverage the extremely wide bandwidth of cable TV systems required to deliver broadcast-quality television as a high-speed conduit for broadband data communications. This led to the birth of the cable modem. Early cable-modem equipment was vendor proprietary, so interoperability between different vendors' products was largely nonexistent. To promote interoperability, Cable Labs (the cable TV industry research arm) developed the Data Over Cable Service Interface Specification (DOCSIS 1.0), an IP-centric, point-to-multipoint standard that quickly replaced the proprietary solutions that preceded it. DOCSIS has now become the accepted cable standard. The newly released DOCSIS 1.1 is destined to play an important role in the delivery of high-quality multimedia across fixed wireless communications networks. With this approach, we can take advantage of all the DOCSIS technology modules that exist in the market today, allowing the wireless platform to migrate toward emerging services such as Internet protocol multicasting and voice over IP (VoIP). We describe the state of current technologies that have made fixed-wireless access a viable and compelling choice. We also discuss some emerging technologies that will bring exciting new fixed-wireless services and capabilities into homes and small businesses in the near future     

一种提取单像素边缘的方法

在对图像进行边缘提取时,水平和垂直的边缘一般通过简单的Soble算子就能够提取出它的单像素边缘,但是对于倾斜的或其他形状的边缘用简单的Sobel算法就很难提取出它的单像素边缘。本文提出了一种基于新的Soble算子改进算法来提取倾斜一定角度的单像素边缘。首先,通过引入衰减因子对原灰度图像进行处理,先后利用8个模板的Sobel算子得到一个边缘图,然后利用统计学的方法,统计边缘图像每一行的灰度最大值,最大值所在的位置就是单像素的位置。通过实验验证,利用本文的算法能够将倾斜一定角度的边缘提取出其单像素点。     

Automatic centerline extraction for virtual colonoscopy

In this paper, we introduce a concise and concrete definition of an accurate colon centerline and provide an efficient automatic means to extract the centerline and its associated branches (caused by a forceful touching of colon and small bowel or a deep fold in twisted colon lumen). We further discuss its applications on fly-through path planning and endoscopic simulation, as well as its potential to solve the challenging touching and colon collapse problems in virtual colonoscopy. Experimental results demonstrated its centeredness, robustness, and efficiency.     

Statistical modeling and many-to-many matching for view-based 3D object retrieval

We address the task of view-based 3D object retrieval, in which each object is represented by a set of views taken from different positions, rather than a geometrical model based on polygonal meshes. As the number of views and the view point setting cannot always be the same for different objects, the retrieval task is more challenging and the existing methods for 3D model retrieval are infeasible. In this paper, the information in the sets of views is exploited from two aspects. On the one hand, the form of histogram is converted from vector to state sequence, and Markov chain (MC) is utilized for modeling the statistical characteristics of all the views representing the same object. On the other hand, the earth mover's distance (EMD) is involved to achieve many-to-many matching between two sets of views. For 3D object retrieval, by combining the above two aspects together, a new distance measure is defined, and a novel approach to automatically determine the edge weights in graph-based semi-supervised learning is proposed. Experimental results on different databases demonstrate the effectiveness of our proposal.     

Generative probabilistic models for multimedia retrieval: query generation against document generation

This paper presents the use of generative probabilistic models for multimedia retrieval. Gaussian mixture models are estimated to describe the visual content of images (or video) and are explored in different ways of using them for retrieval. So-called query generation (how likely is the query given the document model) and document generation (how likely is the document given the query model) approaches are considered and how both fit in a common probabilistic framework is explained. Query generation is shown to be theoretically superior, and confirmed experimentally on the Trecvid search task. However, it is found that in some cases a document generation approach gives better results. Especially in the cases where queries are narrow and visual results are combined with textual results, the document generation approach seems to be better at setting a visual context than the query generation variant.