Search

Software Project Management (SPM) is one of the primary factors to software success or failure. Software projects often fail because the mangers do not know true project status. Software project planning can be one of the most critical activities in the SPM process. Without a realistic and objective software project plan, the software development process cannot be managed in an effective way. This paper presents a metric-based multi-agent system, Software Project Planning Associate (SPPA), to assist managers in understanding and visualizing SPM process defined in a software project plan. SPPA consists of Intelligent Agents developed in the Java programming language and JESS (Java Expert System Shell) to assist a software project manager in objectively initializing a software project plan, refining/improving a plan, organizing, staffing, scheduling, measuring, visualizing, controlling, tracking, predicting, and data collecting. The resources, tasks, schedules, and milestones of the software project are described in a generic metric-based software project plan. As software development process evolves, metrics are unobtrusively gathered and compliance to the plan is reported by intelligent agents. Software process effectiveness predictions are made and recommendations are dynamically reported by multi intelligent agents suggesting the software development that should be executed to best comply with the software project plan.

This paper formulates the automated tagging of media as a multilabel classification problem. An induction method for creating a multilabel decision tree is presented, then applied to the problem of identifying emotions associated with music clips. The results are compared to two other multilabel classification approaches (CLUS and RAKEL), and the proposed approach is shown to produce better results using a variety of performance measures.

The decision tree-based classification is a popular approach for pattern recognition and data mining. Most decision tree induction methods assume training data being present at one central location. Given the growth in distributed databases at geographically dispersed locations, the methods for decision tree induction in distributed settings are gaining importance. This paper describes one distributed learning algorithm which extends the original(centralized) CHAID algorithm to its distributed version. This distributed algorithm generates exactly the same results as its centralized counterpart. For completeness, a distributed quantization method is proposed so that continuous data can be processed by our algorithm. Experimental results for several well known data sets are presented and compared with decision trees generated using CHAID with centrally stored data.

CASMIL aims to develop a cost-effective and efficient approach to monitor and predict deformation during surgery, allowing accurate, and real-time intra-operative information to be provided reliably to the surgeon.CASMIL is a comprehensive Image-guided Neurosurgery System with extensive novel features. It is an integration of various modules including rigid and non-rigid body co-registration (image-image, image-atlas, and image-patient), automated 3D segmentation, brain shift predictor, knowledge based query tools, intelligent planning, and augmented reality. One of the vital and unique modules is the Intelligent Planning module, which displays the best surgical corridor on the computer screen based on tumor location, captured surgeon knowledge, and predicted brain shift using patient specific Finite Element Model. Also, it has multi-level parallel computing to provide near real-time interaction with iMRI (Intra-operative MRI). In addition, it has been securely web-enabled and optimized for remote web and PDA access.A version of this system is being used and tested using real patient data and is expected to be in use in the operating room at the Detroit Medical Center in the first half of 2006.CASMIL is currently under development and is targeted for minimally invasive surgeries. With minimal changes to the design, it can be easily extended and made available for other surgical procedures.

This paper describes a method for detecting and locating objects in images. The presented approach relies on finding general landmark candidates (glc) in an image. A glc is a closed region that can be either an object landmark (ol) or a non-object landmark (nol). The entire ol's are then grouped into object clusters (oc's). Given a set of training images, the method builds a database of ol and nol regions and oc's. When a query image is presented, we detect all of the ol's and group them into oc candidates. These cluster candidates are then classified using the oc's from the training database. This method can be used to detect and locate objects from images in many different unconstrained environments, such as detecting vehicles, speed signs, etc... The method is tested on two different cases and is shown to yield a high success rate.

This paper discusses the use of a combination of support vector machine and decision tree learning for recognizing four emotions in speech, which are neutral, angry, lombard, and loud. The base features selected were pitch, derivative of pitch, energy, speaking rate, formants, band-widths, and Mel frequency cepstral coefficients. Three methods of combining learned support vector machine and decision tree classifiers were proposed, namely, minimum misclassification, maximum accuracy, and dominant class. Using the Speech Under Simulated and Actual Stress database, the average accuracy from the minimum misclassification, maximum accuracy, and dominant class methods were 72.4%, 70.8%, 71.3% respectively as opposed to 63.9% and 67.4% which were obtained by using support vector machine and decision tree learning alone.

To reason about the meaning of an image, useful information should be provided with that image; however, images often contain little to no textual information about the objects they are depicting, which is the precise reason why there is a need for CBIR systems that exploit only the correlations present in the raw pixel data. In this paper, we proposed a new type of image feature, which consists of patterns of colors and intensities that capture the latent associations among images and primitive features in such a way that the noise and redundancy are eliminated. We introduced the synobin, a new term for content-based image retrieval literature, which is the equivalent of a synonym word from text retrieval, to name the bin that is synonymous with other bins of a color feature, in the sense that they are similarly used across the image database. In a formal definition, a group of synobins is given by the most important bins participating in forming of a useful pattern, that is, the bins having the highest coefficients in the linear combination defining that pattern. Incorporating our feature model into a CBIR system moves the research in image retrieval beyond simple matching of images based on their primitive features and creates a ground for learning image semantics from visual content. A system developed using our proposed feature model will have the capability of learning associations not only between semantic concepts and images, but also between semantic concepts and patterns. We evaluated the performance of our system based on the retrieval accuracy and on the perceptual similarity order among retrieved images. When compared to standard image retrieval methods, our preliminary results show that even if the feature space was reduced to only 3%–5% of the initial space, the accuracy and perceptual similarity for our system remain the same or better depending on the category of images.

In this paper, we present a computer-assisted image browsing system based on pathfinder networks. Similarity of images to one another is determined through a proposed method of automatic shape feature discovery. Local features are generated by clustering small (on the order of 10 by 10 pixels) binary image blocks culled from the edge analysis of images in the database and using the cluster means as the local feature detectors. The clustering method for the binary image blocks is based on the Hausdorff metric of distance between sets of points. Relationships between local features then determine the similarity between images. Pathfinder networks are then used to visually represent similarity between images. The results are presented on a database containing three categories of images.

This paper presents a shape-based retrieval system and its application to infrared satellite images. A complete system is presented, from region extraction of a full hemisphere scan to the actual retrieval mechanism. After region extraction, polygonal approximation is applied to the region shape, and local features of the polygons are hashed to provide an association space. This space becomes the indexing structure through which retrieval takes place. Although the indexing stage, containing region extraction and polygonal approximation, is slow, the actual retrieval is very fast. On average, retrieval of a query shape from a database of 1965 shapes takes 0.7 seconds for the more reduced representation, and 2.8 seconds for the less reduced representation consisting of 1914 shapes. The overall design is good for a moderately sized database, and extensions could be made to apply the method to a massive database. The results show that the approach performs well, and that there is a substantial speed benefit for using the local association hashing method.

We present the preliminary results of a data mining study of a production line involving hundreds of variables related to mechanical, chemical, electrical and magnetic processes involved in manufacturing coated glass. The study was performed using two nonlinear, nonparametric approaches, namely neural network and CART, to model the relationship between the qualities of the coating and machine readings. Furthermore, neural network sensitivity analysis and CART variable rankings were used to gain insight into the coating process. Our initial results show the promise of data mining techniques to improve the production.

This paper describes a method for creating agents for locating images of specific categories such as sky, vegetation, fire, and smoke. The method uses only color information, and is based on vector quantization to build a category specific codebook from a set of training images. The method is shown to yield categorization of images collected from several web sites on Internet with a high success rate. The method can be used as an aid to image annotation or as a way to filter images in a content-based image retrieval system.

The automatic recognition of video clips is an important capability with applications in broadcast monitoring for content theft and adherence to advertisement campaign. We present an approach for video clip recognition based on HMM and Gaussian mixture modeling for modeling video and audio streams respectively. The approach is used to model TV commercials. The recognition results of using single stream and joint models are compared The error rate of 0.01% is achieved when the joint audiovisual processing model is employed.

The paper presents a modularization method for the design of MPEG decoding software. Compared to the traditional MPEG decoder architecture, the architecture obtained from the modularization method can effectively improve the flexibility and reusability of MPEG decoding software without affecting the speed performance. Using this design approach, the paper presents MPEG Developing Classes (MDC), a software tool for developing MPEG video applications. The feedback from users of MDC shows that MDC is flexible in use and easy to understand. It allows users to develop their specific decoders without going into details of MPEG.

One major drawback of the decision-tree-based inductive knowledge acquisition methodology is its inability to form high-level features from raw attributes. While neural learning has no such problem, its difficulty is in the opaqueness of the acquired knowledge. The authors address both these issues and present a neural learning methodology that yields production rules formed on the basis of high-level features that are also learned during the learning phase. Furthermore, the competitive component of the learning in the proposed methodology automatically determines the number of rules for a given learning situation. Two examples are presented to illustrate the methodology. >

A neural learning methodology is presented that is capable of providing rules from learned weights. An application of this methodology to systematic lupus erythematosus is demonstrated. It is shown that the proposed approach can disregard irrelevant features in the data and can generate different criteria combinations indicating the presence of systemic lupus erythematosus in a patient. >

Three dimensional computed tomography is a computationally intensive procedure, requiring large amounts of RAM and processing power. Parallel methods for two dimensional computed tomography have been studied, but not extended or applied to 3D cone beam tomography. A discussion on how the 3D cone beam tomography problem can be implemented in parallel using MPI is given. We show an improvement in performance from 58.2% to 81.8% processor utilization in a heterogeneous cluster of workstations by load balancing. A 96.8% efficiency was seen using a 2 processor SMP.

Cone beam geometries are increasingly of interest for X-ray CT applications to improve imaging efficiency. In this paper, we describe our practical experience implementing circular orbit cone beam backprojection on workstation clusters. The reconstruction problem is computationally intensive, particularly for arrays of 512 voxels in each direction. A voxel driven approach is described where the reconstruction volume is partitioned into variable width slabs and each slab given to a workstation. Each projection is filtered by one workstation and then sent to the others for backprojection. While most computation is done in the backprojection step, a significant amount of time must be spent in sending projectional data. A method is detailed to further reduce the communication overhead by restricting the amount of projection sent to only what is required by each backprojecting workstation. Furthermore, if the shape of the backprojection slabs is made as square as possible, the total communication requirement can be minimized. By reduction of the communication requirement, an overall improvement in processor utilization was observed, and the crossover point where communication dominates was improved.

With cone beam CT long computation and a large amount of memory is required. The majority of the computation is in the backprojection step. We have investigated the use of parallel methods on workstation clusters using MPI to overcome both the long processing time and lessen memory requirements on individual workstations. We used the asynchronous MPI implementation to reconstruct a 256/sup 3/ volume from 256/sup 2/ projection views with 6 workstations. Our previous efforts in load balancing resulted in processor utilization of 81.8%. Use of asynchronous communication in the cone beam CT problem has improved processor utilization to 91.9%.

Interacting with a multimedia information system is different from interacting with a standard text-based information system. In this paper, we present the design of a system called Content-Based Hypermedia (CBH), which allows a user to utilize metadata to intelligently browse through a collection of media objects. We describe the approach we use to model data in order to make it browsable, explore browsing (data and metadata), indicate how metadata is used in the concept of similarity, present the architecture of our system, and discuss indexing techniques for similarity browsing using content-based metadata. >

In this paper we propose an efficient and flexible method, using the CMAC, to find the nearest neighbor of an input pattern. By searching for the nearest neighbor among a small set of probable candidates, we reduce the number of distance computations compared to the traditional approach. Unlike many other efficient techniques, this system can be trained on additional design patterns at a later time without affecting the previous learning. Experimental results are presented to demonstrate the efficiency of the proposed approach. >

Textural features are often consider as one of the most powerful features in describing the intrinsic physical properties of object surfaces in a scene. In this paper, we propose characterizing image textures by a least-squares hyperplane fitting of their image multidimensional primitives. The adaptive implementation of the hyperplane fitting process is carried out by a newly proposed nonlinear supervised neural unit trained by a constrained form of anti-Hebbian learning. Experimental results are presented to demonstrate the performance of the proposed texture characterization model in image classification and segmentation applications. >

It is pointed out that the most attractive feature of artificial neural networks is the procedural nature of learning that allows the capturing of the mapping present in the input-output data without the need for extensive model building. The authors exploit this feature to solve the task of robot localization using ultrasonic sensors. The localization problem is casted as a regression problem which is then solved by using a feedforward-type multiple-layer neural network. The network design and training are done following the entropy net model that uses a tree to network mapping to obtain the network of appropriate size. A representation layer is added to improve output accuracy. Experimental results for the simulated and real data are presented to demonstrate the performance of the proposed approach. >

Closed-loop video rendering implies generating video streams in compressed form given as input video streams that are in compressed form such as JPEG or MPEG bit streams. Closed-loop video rendering has significant advantages over open-loop schemes including reduced storage requirements which in turn reduces memory disk swapping time that constitutes a large portion of the time spent in the desktop editing of massive video material. Processing in the compressed domain also offers faster processing speeds due to the smaller data size present in the compressed domain. This approach also improves image quality since multiple decompression and compression processes are avoided during the editing process. Based on MPEG, a standard video compression scheme, the authors discuss fundamental techniques, analyze pros and cons, implications and preferences for a compressed domain video rendering system. A software-based system for real-time video rendering is proposed with preliminary results demonstrating the feasibility of their closed-loop MPEG video rendering approach.

A neural network-based road-following system is proposed to take vision sensor input (road boundary images) and generate steering control output while maintaining the vehicle moving within road boundaries. Unlike many existing neural network-based systems that only use the supervised mode of neural learning, the proposed system also uses a reinforcement learning mode to eliminate the need for external supervision and at the same time provides the system with continuous learning ability similar to human driving practice. The simulation results demonstrate the system's good road-following and continuous learning capability. The future plans include a full scale simulation and the construction of a real system.

A radial basis function (RBF) neural network is considered as one of the universal input-output functional mapping learning systems. Important issues in designing an efficient RBF neural network are the number of neurons and the shape and location of neurons to define local receptive fields in feature space. This paper presents a solution to these problems using decision tree partitioning. A conversion algorithm from decision tree to RBF neural network is described. Two examples are presented to illustrate the proposed approach.

Establishing the identify of a signature by automatic search through a database of signatures is of interest in several areas. This paper describes a system for this purpose. The proposed identification system uses a set of geometric and topologic features to characterize each signature. By considering the spatial distribution of these features, the system maps each signature into two strings of finite symbols. A local associative indexing scheme is then used on these strings to organize the collection of signatures of known identity. When presented with a signature of unknown identity, the system uses the same indexing scheme to retrieve a candidate set of signatures. A verification process is then carried out to find the best match from the candidate set. The performance of the proposed system has been tested with a moderate database. The results obtained indicate that the proposed system is able to identify signatures with great accuracy even when a part of a signature is missing.

The last few years have seen a remarkable growth of information in digital form due to a combination of several technological factors that include the availability of high speed electronic networks and affordable yet powerful desktop computing. This coupled with advances in scientific and consumer imaging technology-digital radiography, digital still cameras, desktop scanners, video capture boards, has created an environment where a large fraction of digital information is being created and disseminated in visual form-graphics, images, and video. This trend towards information in visual form is not surprising considering that we use vision more than any other sense to acquire and communicate information. >

The production of multimedia content has grown overwhelmingly in recent years due to decreasing hardware costs, inexpensive storage and ubiquitous high-bandwidth networks. In addition, the introduction of digital video is completely changing the landscape of the entire video value chain. The easy access and increased availability of multimedia is posing new challenges to manage the data. Image and video archives in broadcast studios, corporate archives of multimedia collaborative sessions, video conferencing sessions and educational videos all require tools for quickly locating video segments of desired content with transparent access. The market for such tools, known as media asset-management tools, has been growing rapidly. In this chapter we will discuss the general architecture and the tools for media content management. We will survey some of the techniques that employ methods of data management beyond traditional databases. We will discuss existing research prototypes and some commercially available systems. These systems enable applications that facilitate effective access, interaction, browsing and display of complex and inhomogeneous information consisting of images, video and audio.

This chapter provides an introductory overview of data mining. Data mining, also referred to as knowledge discovery in databases, is concerned with nontrivial extraction of implicit, previously unknown and potentially useful information from data in databases. The main focus of the chapter is on different data mining methodologies and their relative strengths and weaknesses.

We proposed an omni-face tracking system for video annotation in this paper, which is designed to find faces from arbitrary views in complex scenes. The face detector first locates potential faces in the input by performing skin-tone detection. The subsequent processing consists of two largely independent components, the frontal face module and the side- view face module, responsible for finding frontal-view and side-view faces, respectively. The frontal face module uses a region-based approach wherein regions of skin-tone pixels are analyzed for gross oval shape and the presence of facial features. In contrast, the side-view face module follows an edge-based approach to look for curves similar to a side-view profile. To extract the trajectories of faces, the temporal continuity between consecutive frames within the video shots is considered to speed up the tracking process. The main contribution of this work is being able to find faces irrespective of their poses, whereas contemporary systems deal with frontal-view faces only. Information regarding to human faces is encoded in XML format for semantic video content representation. The effectiveness of human face for video annotation is demonstrated in a TV program classification system that categories the input video clip into predefined types. It is shown that the classification accuracy is improved saliently by the employment of face information.© (2000) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Currently, most approaches for object tracking are under spatial domain using optical flow and depth, or some model- based methods which need to uncompress those video sequences then do further disposal. The computation for uncompressing is expensive and not good for real time control. Although there are also some researchers doing object tracking under compressed domain, they only use part of DCT values of I frames in a video sequence, which doesn't take advantage of the information under compressed domain. In this paper we consider a new method for object tracking which uses the information only supplied in compressed domain through the MPEG encoder. The main scheme we have performed is to get the motion vectors of P and B frames directly from the MPEG video without decompressing it then cluster objects based on the motion vectors. In particular, camera motion is also taken into account since camera's motion can influence the objects' motion and segmentation results dramatically. Experiments based on the method mentioned above have been carried out in several videos. The results obtained indicate that tracking object in compressed domain is very promising.

In this paper, we do some pre-processing on the input data to remove some noise before putting them into the network and some post-processing before outputting the results. Different neural networks such as back-propagation, radias basis network with different architecture are tested. We choose the one with the best performance among them. From the experiments we can see that the results of the neural network are similar to those given by the experienced doctors and better than those of previous research, indicating that this approach is very practical and beneficial to doctors comparing with some other methods currently existing.

The purpose of this chapter is to describe the application of the problem solving ontology component of HCVM in the area of face detection and annotation. computer-based aspects of an embedded feature-based multi-agent face detection and annotation system are described in this chapter. Unlike similar feature-based systems that start from searching for facial organs in the images and group them to find faces, the system solves the problem using the problem solving agents of the HCVM in a top-down fashion. The embedded mtilti-agent face detection system makes hypotheses of face locations and seeks evidences to verify them. The five problem solving agents follow a coarse grain to fine grain methodology and work on various features of color images. The coarse to fine top-down methodology is more akin to human perceptions than a bottom-up approach. The higher level problem solving agents like decomposition work as background knowledge for the control and decision agents resulting in improvement of the accuracy and speed of detection. It is also distinct from many other top-down systems in that no re-scaling of the images is needed in the searching process. To improve the detection rate, a unique iterative region-partitioning algorithm is developed in this multi-agent system. The problem solving agents model aspects related to skin-tone region segmentation, noise reduction, candidate face regions location and facial feature extraction/face detection, and annotation. The detection algorithm is invariant to scale and rotation to some degree. The performance of the multi-agent system has been tested with a large number of images and the results obtained thus far are very encouraging.

This chapter builds on the foundations laid down in the previous chapter. It describes the human-centered system development framework for intelligent multimedia multiagent systems based on human-centered criteria outlined in the first chapter and the pragmatic considerations and theories discussed in chapter 3, which contribute towards realization of those criteria. The human-centered framework is described in terms of four components, namely, activity-centered analysis, problem solving ontology, transformation agents, and multimedia interpretation, respectively. The three human-centered criteria are used as guidelines for development of the human-centered framework. The pragmatic considerations and contributing theories are used to develop the structure and content, or knowledge base, of the four components. The structure and content are described at the conceptual and computational (transformation agents) level. We start this chapter by describing the external and internal planes of action which underpin the development of the human-centered framework. We follow it with the description of two components human-centered system development framework, namely, activity-centered analysis and problem solving ontology. In the next chapter we continue with the description of the problem solving ontology component and describe the transformation agent and multimedia interpretation component. These four components have been used to define the external and internal planes of human interaction with the environment.

In the last two chapters we have looked into the application of four components of the HCVM. In this chapter we wish to demonstrate two other facets of the human-centered virtual machine, which have not been specifically looked at until now. These are the role of computer-based intermediaries (for back up support in problem solving), distributed communication in human-centered multi-agent systems and using computer-based artifacts to model breakdowns in human decision making. The role of intermediaries and distributed communication is illustrated by way of an intelligent distributed multi-agent multimedia euchre application on the net. In addition, aspects of a sales recruitment and benchmarking application are described to illustrate how computer-based artifact is used to overcome breakdowns in the sales, customer service and telesales recruitment decision making. In fact the modeling of the breakdowns is the prime motivator for the sales managers and sales personnel to use the computerized system for management of recruitment and benchmarking. The sales recruitment system described in this chapter (and developed by the first author) has been used in the industry for approximately the past three years.

In the last three chapters we have described applications of HCVM in medical informatics, image processing, internet games and sales recruitment. In these applications we have looked at multimedia artifacts in terms of how they can be used for improving the representational efficiency, effectiveness and interpretation of computer-based artifacts and also to some extent how they can be used for perceptual problem solving. However, there are interesting research issues and problems associated with management and retrieval of text, image, video, audio artifacts from single and multimedia databases. The area of multimedia information management and retrieval has in recent times become important due to the advent of the internet and World Wide Web (WWW). The solution to a number of issues in this area today lies with traditional solutions used for conventional databases. Recently, intelligent agents and human-centered information retrieval models are being proposed by researchers to address the problems in this area. In order to gain a proper understanding of the various problems and issues involved, we start this chapter by outlining the three evolution stages of this time honored area. We then describe these evolution stages in some detail. We include in this description applications and solutions proposed for multimedia information management and retrieval. We conclude the chapter by outlining open research problems in this area.

Human-centered system development is not a revolutionary concept in computer science and information systems but an evolutionary and enabling one. In this chapter we look at how some areas in computer science and information systems are evolving or moving towards human-centeredness. These areas include intelligent systems, electronic commerce, software engineering, multimedia databases, data mining, enterprise modeling and human-computer interaction. This evolution is based on the need for addressing pragmatic issues in these areas. We follow these pragmatic issues with enabling theories in philosophy, cognitive science, psychology and work-oriented design for human-centered system development framework. These theories are described and discussed in terms of their contributions toward human-centered system development framework. We conclude the chapter with a discussion section that outlines the foundations of the human-centered system development framework described in the chapter.

Electronic commerce (EC) can be broadly seen as the application of information technology and telecommunications to create trading networks where goods and services are sold and purchased, thus increasing the efficiency and the effectiveness of traditional commerce.

The objective of this chapter is to show the application of the conceptual and computational facets of the HCVM in a clinical drug prescription monitoring activity. The application is in the area of infectious diseases (Gorbach et al. 1998; Barrows et al. 1991) and addresses problems related to the gathering of patient symptomatic data, providing diagnostic assistance, and finding inconsistencies in practitioner prescribed treatments compared to those recommended by therapeutic guidelines (TG 1998).

Chroma-keying or blue screen matting is an important video editing operational. In blue screen matting, everything in the image that has the 'user specified level for the blue channel' is 'keyed' out and replaced by either another image or a color from a color generator. We develop a technique for blue screen matting that manipulates the image when the information for the image is available only in compressed form such as a JPEG or MPEG bitstream. Specifically, for the compressed domain approach, we show that the matting process is a convolution operation; hence, we develop a DCT convolution theorem. The DCT convolution theorem can be used to show that the compressed domain approach proposed in this paper provides a significant reduction in computation complexity compared to previously developed approaches which were mostly adhoc techniques. The convolution theorem exploits the sparseness as well as the orthogonality of the data available in the DCT domain and thus yields an efficient algorithm for he chroma-keying or blue screen matting. The algorithm extends to the DCT domain concepts such as alpha channel and premultiplied alpha. The method is also extended to MPEG video domain wherein we explore the efficiency of the matting process when interframe coding is used.© (1997) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

The scanline algorithms are popular in a computer graphics for complex geometric manipulations. The main characteristic of the scanline algorithms is that a geometric transformation is decomposed into multiples transforms with each pass operating only along row or column scanlines. This leads to conversion of 2D image manipulation problems to straightforward 1D problems resulting in simple and systematic methods. The goal of this work is to examine the scanline approach for manipulation of transform-compressed images without decompressing them. We show how the scanline algorithms for rotation and projective mapping can be developed for JPEG/DCT images. The performance of the proposed scanline algorithms is evaluated with respect to quality, speed, and control and memory overhead.

Multiple layer feedforward neural networks are often viewed as black boxes as the knowledge stored in the connection weights of these networks is generally considered incomprehensible. This paper suggests a solution to this deficiency of neural networks by proposing a backtracking tree search procedure for converting the weights of a neuron into a symbolic representation and demonstrating its use for understanding and symbolic approximation of feedforward neural networks. Several examples are presented to illustrate the proposed symbolic mapping of neurons.

Spatial image filtering is a method by which an image can be enhanced. The method involves computing correlation of a mask and input image to produce desired image. This requires a number of computations consisting of addition and division operations. Such operations are repeated multiple times for common areas of overlapping masks as we shift the mask over consecutive pixels. As a result, there is a significant number of redundant operations that slows down the spatial filtering process. In this paper, we propose a new method to eliminate redundant operations and we apply it to volumetric MRI images using mean filter. We analyse the complexity of the proposed method and compare its processing speed to that of the conventional implementation of the mean filter. Our method shows up to one order of magnitude improvement in processing speed over the conventional method especially on 3D images with large filter masks.

Many target tracking methods rely on the use of centroids as features points. In several applications such as the tracking of vehicles on roadways, the appropriate target paths are known a priori. Based on this observation, an efficient centroid computation method is presented and analyzed in this paper.

This paper presents a generalization of the correspondence approach of Sethi and Jain by extending the path coherence criterion to high dimensional vector space. This allows the same correspondence procedure to be used for a variety of tokens including points, lines, planes and regions. To demonstrate the generalized approach, we apply it to track lines and present experimental results.

The problem of determining the position and orientation of a mobile robot has been addressed by several researchers using sensors of different modalities, including video cameras. Invariably, all the vision-based approaches for robot localization consider that the camera is mounted on the robot and that the robot working environment is assumed to contain prominent landmarks at known locations. In this paper we propose a robot localization scheme where the robot itself serves as the landmark for cameras that are positioned in the environment to cover the entire work area of the robot. Although the proposed approach is applicable for the robots of any regular shape, we develop the solution to the localization problem by assuming a cylindrical shape for the robot. A compete mathematical analysis of the localization problem is given by extending the three-dimensional structure-from-rotational motion approach to the present task. We also examine the implementation issue of the proposed approach and present experimental results to show its effectiveness.