Automatic localization of craniofacial landmarks for assisted cephalometry

In this paper we propose a system for localization of cephalometric landmarks. The process of localization is carried out in two steps: deriving a smaller expectation window for each landmark using a trained neuro-fuzzy system (NFS) then applying a template-matching algorithm to pin point the exact location of the landmark. Four points are located on each image using edge detection. The four points are used to extract more features such as distances, shifts and rotation angles of the skull. Limited numbers of representative groups that will be used for training are selected based on k-means clustering. The most effective features are selected based on a Fisher discriminant for each feature set. Using fuzzy linguistics if-then rules, membership degree is assigned to each of the selected features and fed to the FNS. The FNS is trained, utilizing gradient descent, to learn the relation between the sizes, rotations and translations of landmarks and their locations. The data for training is obtained manually from one image from each cluster. Images whose features are located closer to the center of their cluster are used for extracting data for the training set. The expected locations on target images can then be predicted using the trained FNS. For each landmark a parametric template space is constructed from a set of templates extracted from several images based on the clarity of the landmark in that image. The template is matched to the search windows to find the exact location of the landmark. Decomposition of landmark shapes is used to desensitize the algorithm to size differences. The system is trained to locate 20 landmarks on a database of 565 images. Preliminary results show a recognition rate of more than 90%.     

Pattern codification strategies in structured light systems

Coded structured light is considered one of the most reliable techniques for recovering the surface of objects. This technique is based on projecting a light pattern and viewing the illuminated scene from one or more points of view. Since the pattern is coded, correspondences between image points and points of the projected pattern can be easily found. The decoded points can be triangulated and 3D information is obtained. We present an overview of the existing techniques, as well as a new and definitive classification of patterns for structured light sensors. We have implemented a set of representative techniques in this field and present some comparative results. The advantages and constraints of the different patterns are also discussed.     

A single solution method for converting 2D assembly drawings to 3D part drawings

Although solid models play a central role in modern CAD systems, 2D CAD systems are still commonly used for designing products without complex curved faces. Therefore, an important task is to convert 2D drawings to solid models, and this is usually carried out manually even in present CAD systems. Many methods have been proposed to automatically convert orthographic part drawings of solid objects to solid models. Unfortunately, products are usually drawn as 2D assembly drawings, and therefore, these methods cannot be applied. A further problem is the difficult and time-consuming task of decomposing 2D assembly drawings into 2D part drawings. In previous work, the authors proposed a method to automatically decompose 2D assembly drawings into 3D part drawings, from which 2D part drawings can be easily generated. However, one problem with the proposed method was that the number of solutions could easily explode if the 2D assembly drawings became complex. Building on this work, here we describe a new method to automatically convert 2D assembly drawings to 3D part drawings, generating a unique solution for designers regardless of the complexity of the original 2D assembly drawings. The only requirement for the approach is that the assembly drawings consist of standard parts such as bars and plates. In 2D assembly drawings, the dimensions, part numbers and parts lists are usually drawn, and the proposed method utilizes these to obtain a unique solution.     

A hierarchically structured and constraint-based data model for intuitive and precise solid modeling in a virtual reality environment

This article proposes a hierarchically structured and constraint-based data model for intuitive and precise solid modeling in a virtual reality (VR) environment. The data model integrates a high level constraint-based model for intuitive and precise manipulation, a middle level solid model for complete and precise representation and a low-level polygon mesh model for real-time interactions and visualization in a VR environment. The solid model is based on a hybrid B-rep/CSG data structure. Constraints are embedded in the solid model and are organized at hierarchical levels as feature constraints among internal feature elements, part constraints among internal features and assembly constraints between individual parts. In addition to providing a complete and precise model representation and the support for real-time visualization, the proposed data model permits intuitive and precise interaction through constraint-based manipulations for solid modeling in a VR environment. This is a critical issue for product design in a VR environment due to the limited resolutions of today's VR input and output devices.     

Feature-based design in a distributed and collaborative environment

In this paper, a client/server framework has been developed to enable a dispersed team to accomplish a feature-based design task collaboratively. A manipulation client+modelling server infrastructure has been proposed to facilitate consistent primary information modelling for multiple users and adaptability of the system. Based on feature-to-feature relationships, a distributed feature manipulation mechanism has been proposed to filter the varied information of a working part during a co-design activity to avoid unnecessary re-transferring of the complete large-size CAD files each time when any interactive operation is imposed on the model by a client. In the distributed environment, a design task and the engaged clients are organised and connected through working sessions generated and maintained dynamically with a collaborative server. The environment is open to downstream manufacturing analysis modules to achieve distributed concurrent engineering.     

Design formalism for collaborative assembly design

Joints in product design are common because of the limitations of component geometric configurations and material properties, and the requirements of inspection, accessibility, repair, and portability. Collaborative product design is emerging as a viable alternative to the traditional design process. The collaborative assembly design (AsD) methodologies are needed for distributed product development. Existing AsD methodologies have limitations in capturing the non-geometric aspects of designer's intent on joining and are not efficient for a collaborative design environment. This paper introduces an AsD formalism and associated AsD tools to capture joining relations and spatial relationship implications. This AsD formalism allows the joining relations to be modeled symbolically for computer interpretation, and the model can be used for inferring mathematical and physical implications. An AsD model generated from the AsD formalism is used to exchange AsD information transparently in a collaborative AsD environment. An assembly relation model and a generic assembly relationship diagram are to capture assembly and joining information concisely and persistently. As a demonstration, the developed AsD formalism and AsD tools are applied on a connector assembly with arc weld and rivet joints.     

Multi-agent segmentation of IVUS images

A novel multi-agent image interpretation system has been developed which is markedly different from previous approaches in especially its elaborate high-level knowledge-based control over low-level image segmentation algorithms. Agents dynamically adapt segmentation algorithms based on knowledge about global constraints, contextual knowledge, local image information and personal beliefs. Generally agent control allows the underlying segmentation algorithms to be simpler and be applied to a wider range of problems with a higher reliability.The agent knowledge model is general and modular to support easy construction and addition of agents to any image processing task. Each agent in the system is further responsible for one type of high-level object and cooperates with other agents to come to a consistent overall image interpretation. Cooperation involves communicating hypotheses and resolving conflicts between the interpretations of individual agents.The system has been applied to IntraVascular UltraSound (IVUS) images which are segmented by five agents, specialized in lumen, vessel, calcified-plaque, shadow and sidebranch detection. IVUS image sequences from 7 patients were processed and vessel and lumen contours were detected fully automatically. These were compared with expert-corrected semiautomatically detected contours. Results show good correlations between agents and expert with r=0.84 for the lumen and r=0.92 for the vessel cross-sectional areas, respectively.     

Distributed intelligence for multi-camera visual surveillance

Latest advances in hardware technology and state of the art of computer vision and artificial intelligence research can be employed to develop autonomous and distributed monitoring systems. The paper proposes a multi-agent architecture for the understanding of scene dynamics merging the information streamed by multiple cameras. A typical application would be the monitoring of a secure site, or any visual surveillance application deploying a network of cameras. Modular software (the agents) within such architecture controls the different components of the system and incrementally builds a model of the scene by merging the information gathered over extended periods of time. The role of distributed artificial intelligence composed of separate and autonomous modules is justified by the need for scalable designs capable of co-operating to infer an optimal interpretation of the scene. Decentralizing intelligence means creating more robust and reliable sources of interpretation, but also allows easy maintenance and updating of the system. Results are presented to support the choice of a distributed architecture, and to prove that scene interpretation can be incrementally and efficiently built by modular software.     

Two realizations of a general feature extraction framework

A general feature extraction framework is proposed as an extension of conventional linear discriminant analysis. Two nonlinear feature extraction algorithms based on this framework are investigated. The first is a kernel function feature extraction (KFFE) algorithm. A disturbance term is introduced to regularize the algorithm. Moreover, it is revealed that some existing nonlinear feature extraction algorithms are the special cases of this KFFE algorithm. The second feature extraction algorithm, mean-STD¹-norm feature extraction algorithm, is also derived from the framework. Experiments based on both synthetic and real data are presented to demonstrate the performance of both feature extraction algorithms.