The Experts below are selected from a list of 30456 Experts worldwide ranked by ideXlab platform
Laurent Najman - One of the best experts on this subject based on the ideXlab platform.
-
hierarchical image simplification and segmentation based on mumford shah salient level line selection
Pattern Recognition Letters, 2016Co-Authors: Thierry Geraud, Laurent NajmanAbstract:An efficient hierarchical image simplification and segmentation method.Stack hierarchically level lines from meaningless to salient ones.Highlight salient level lines.Strongly simplify image while preserving salient structures intact.Quasi-linear time complexity w.r.t. the number of pixels. Hierarchies, such as the tree of shapes, are popular representations for image simplification and segmentation thanks to their multiscale structures. Selecting meaningful level lines (boundaries of shapes) yields to simplify image while preserving intact salient structures. Many image simplification and segmentation methods are driven by the optimization of an energy Functional, for instance the celebrated Mumford-Shah Functional. In this paper, we propose an efficient approach to hierarchical image simplification and segmentation based on the minimization of the piecewise-constant Mumford-Shah Functional. This method conforms to the current trend that consists in producing hierarchical results rather than a unique partition. Contrary to classical approaches which compute optimal hierarchical segmentations from an input hierarchy of segmentations, we rely on the tree of shapes, a unique and well-defined representation equivalent to the image. Simply put, we compute for each level line of the image an Attribute Function that characterizes its persistence under the energy minimization. Then we stack the level lines from meaningless ones to salient ones through a saliency map based on extinction values defined on the tree-based shape space. Qualitative illustrations and quantitative evaluation on Weizmann segmentation evaluation database demonstrate the state-of-the-art performance of our method.
-
hierarchical image simplification and segmentation based on mumford shah salient level line selection
arXiv: Computer Vision and Pattern Recognition, 2016Co-Authors: Thierry Geraud, Laurent NajmanAbstract:Hierarchies, such as the tree of shapes, are popular representations for image simplification and segmentation thanks to their multiscale structures. Selecting meaningful level lines (boundaries of shapes) yields to simplify image while preserving intact salient structures. Many image simplification and segmentation methods are driven by the optimization of an energy Functional, for instance the celebrated Mumford-Shah Functional. In this paper, we propose an efficient approach to hierarchical image simplification and segmentation based on the minimization of the piecewise-constant Mumford-Shah Functional. This method conforms to the current trend that consists in producing hierarchical results rather than a unique partition. Contrary to classical approaches which compute optimal hierarchical segmentations from an input hierarchy of segmentations, we rely on the tree of shapes, a unique and well-defined representation equivalent to the image. Simply put, we compute for each level line of the image an Attribute Function that characterizes its persistence under the energy minimization. Then we stack the level lines from meaningless ones to salient ones through a saliency map based on extinction values defined on the tree-based shape space. Qualitative illustrations and quantitative evaluation on Weizmann segmentation evaluation database demonstrate the state-of-the-art performance of our method.
Thierry Geraud - One of the best experts on this subject based on the ideXlab platform.
-
hierarchical image simplification and segmentation based on mumford shah salient level line selection
Pattern Recognition Letters, 2016Co-Authors: Thierry Geraud, Laurent NajmanAbstract:An efficient hierarchical image simplification and segmentation method.Stack hierarchically level lines from meaningless to salient ones.Highlight salient level lines.Strongly simplify image while preserving salient structures intact.Quasi-linear time complexity w.r.t. the number of pixels. Hierarchies, such as the tree of shapes, are popular representations for image simplification and segmentation thanks to their multiscale structures. Selecting meaningful level lines (boundaries of shapes) yields to simplify image while preserving intact salient structures. Many image simplification and segmentation methods are driven by the optimization of an energy Functional, for instance the celebrated Mumford-Shah Functional. In this paper, we propose an efficient approach to hierarchical image simplification and segmentation based on the minimization of the piecewise-constant Mumford-Shah Functional. This method conforms to the current trend that consists in producing hierarchical results rather than a unique partition. Contrary to classical approaches which compute optimal hierarchical segmentations from an input hierarchy of segmentations, we rely on the tree of shapes, a unique and well-defined representation equivalent to the image. Simply put, we compute for each level line of the image an Attribute Function that characterizes its persistence under the energy minimization. Then we stack the level lines from meaningless ones to salient ones through a saliency map based on extinction values defined on the tree-based shape space. Qualitative illustrations and quantitative evaluation on Weizmann segmentation evaluation database demonstrate the state-of-the-art performance of our method.
-
hierarchical image simplification and segmentation based on mumford shah salient level line selection
arXiv: Computer Vision and Pattern Recognition, 2016Co-Authors: Thierry Geraud, Laurent NajmanAbstract:Hierarchies, such as the tree of shapes, are popular representations for image simplification and segmentation thanks to their multiscale structures. Selecting meaningful level lines (boundaries of shapes) yields to simplify image while preserving intact salient structures. Many image simplification and segmentation methods are driven by the optimization of an energy Functional, for instance the celebrated Mumford-Shah Functional. In this paper, we propose an efficient approach to hierarchical image simplification and segmentation based on the minimization of the piecewise-constant Mumford-Shah Functional. This method conforms to the current trend that consists in producing hierarchical results rather than a unique partition. Contrary to classical approaches which compute optimal hierarchical segmentations from an input hierarchy of segmentations, we rely on the tree of shapes, a unique and well-defined representation equivalent to the image. Simply put, we compute for each level line of the image an Attribute Function that characterizes its persistence under the energy minimization. Then we stack the level lines from meaningless ones to salient ones through a saliency map based on extinction values defined on the tree-based shape space. Qualitative illustrations and quantitative evaluation on Weizmann segmentation evaluation database demonstrate the state-of-the-art performance of our method.
Wei Chen - One of the best experts on this subject based on the ideXlab platform.
-
product Attribute Function deployment for Attribute identification concept selection and target setting
2013Co-Authors: Wei Chen, Christopher Hoyle, Henk Jan WassenaarAbstract:In this chapter, we provide a systematic method for determining the Attributes to appear in the customer utility Functions such as those used in discrete choice analysis (DCA) and ordered logit (OL) modeling as introduced in Chap.3 for implementing the decision-based design (DBD) approach. The product Attribute Function deployment (PAFD) method overcomes the limitations of the qualitative matrix principles of popular design tools, such as quality Function deployment (QFD), to map qualitative customer needs into quantitative engineering Attributes by following the DBD principles. The PAFD is a process tool for implementation of DBD, for design concept selection and setting targets in conceptual design. A case study of the design of an automotive pressure sensor is provided to illustrate the method as well as demonstrate its advantages over the existing method.
-
Product Attribute Function Deployment (PAFD) for Decision-Based Conceptual Design
IEEE Transactions on Engineering Management, 2009Co-Authors: Christopher J. Hoyle, Wei ChenAbstract:The critical product planning phase, early in the product development cycle, requires a design tool to establish engineering priorities, select the preferred design concept, and set target levels of engineering performance while considering the needs of both the consumer and producer. The quality Function deployment (QFD) method was developed as a design process tool to translate customer needs into engineering characteristics; however, limitations have been identified in using the QFD method for product planning. In this paper, a new design tool called product Attribute Function deployment (PAFD), based on the principles of decision-based design (DBD), is introduced as a decision-theoretic, enterprise-level process tool to guide the conceptual design phase. The PAFD method extends the qualitative matrix principles of QFD while utilizing the quantitative decision-making processes of DBD. The PAFD method is built upon established methods in engineering, marketing, and decision analysis to eliminate the need for the user ratings and rankings of performance, priority, and Attribute coupling in the QFD method. The differences between the QFD and the PAFD processes are compared and contrasted, and the conceptual design of an automotive manifold absolute pressure sensor is used as a case study to demonstrate the features and benefits of the PAFD method.
-
next generation qfd decision based product Attribute Function deployment
16th International Conference on Engineering Design ICED 2007, 2007Co-Authors: Christopher Hoyle, Wei ChenAbstract:The critical product planning phase, early in the product development cycle, requires a design tool to set engineering priorities, capable of selecting the preferred design concept and setting target levels of engineering performance to guide the later product development stages, while considering the needs of both the consumer and producer. The Quality Function Deployment (QFD) method was developed to transfer customer needs into engineering characteristics; however, limitations have been identified in using QFD, which can result in irrational and unrealistic results when used to set engineering priorities and target levels of product performance. In this paper, based on the principles of Decision-Based Design (DBD), a new design tool called the Product Attribute Function Deployment (PAFD) is demonstrated as a decision-theoretic, enterprise-wide process tool to guide the conceptual design phase. The PAFD method extends the qualitative matrix principles of QFD while utilizing the quantitative decision making processes of DBD to create a new process specifically for translating qualitative customer needs into quantitative engineering Attributes and making early product design decisions. It is built upon established methods in engineering, marketing, and decision analysis to eliminate the need for subjective user ratings. In addition, the technical Attributes considered are expanded beyond those typically considered to include requirements from the producer and regulators. The differences between QFD and PAFD are compared and the conceptual design of an automotive Manifold Absolute Pressure sensor is used to demonstrate the benefits of the PAFD method.
-
product Attribute Function deployment pafd for decision based conceptual design
2006 ASME International Design Engineering Technical Conferences and Computers and Information In Engineering Conference DETC2006, 2006Co-Authors: Christopher Hoyle, Deepak Kumar, Wei ChenAbstract:Quality Function Deployment (QFD) is a method that links the “Voice of the Customer” to product planning activities within design, production and marketing. It utilizes weighting factors and relationship matrices to rank order the importance of product Attributes. However, fundamental flaws have been identified in using QFD, which result in irrational and unrealistic results when used for design concept selection and setting target levels of Attributes for a design team. In this paper, based on the principles of Decision-Based Design (DBD), a new tool called the Product Attribute Function Deployment (PAFD) is introduced as an improvement to the QFD process. The PAFD method extends the qualitative matrix principles of QFD and utilizes the quantitative decision making processes of DBD, which incorporates the needs from both the producer and consumers in a rigorous decision making framework. The DBD method takes an enterprise view in problem formulation and optimizes a single criterion to avoid the difficulties associated with weighting factors and multi-objective optimization. In addition to the quantitative improvement, the definition of engineering Attributes in the QFD method is formalized to include corporate, regulatory, manufacturing and other technical requirements to facilitate conceptualization of design alternatives and constraints. The conceptual design of the automotive Manifold Absolute Pressure (MAP) sensor is used as a case study to demonstrate the benefits of the PAFD method.Copyright © 2006 by ASME
Christopher Hoyle - One of the best experts on this subject based on the ideXlab platform.
-
product Attribute Function deployment for Attribute identification concept selection and target setting
2013Co-Authors: Wei Chen, Christopher Hoyle, Henk Jan WassenaarAbstract:In this chapter, we provide a systematic method for determining the Attributes to appear in the customer utility Functions such as those used in discrete choice analysis (DCA) and ordered logit (OL) modeling as introduced in Chap.3 for implementing the decision-based design (DBD) approach. The product Attribute Function deployment (PAFD) method overcomes the limitations of the qualitative matrix principles of popular design tools, such as quality Function deployment (QFD), to map qualitative customer needs into quantitative engineering Attributes by following the DBD principles. The PAFD is a process tool for implementation of DBD, for design concept selection and setting targets in conceptual design. A case study of the design of an automotive pressure sensor is provided to illustrate the method as well as demonstrate its advantages over the existing method.
-
next generation qfd decision based product Attribute Function deployment
16th International Conference on Engineering Design ICED 2007, 2007Co-Authors: Christopher Hoyle, Wei ChenAbstract:The critical product planning phase, early in the product development cycle, requires a design tool to set engineering priorities, capable of selecting the preferred design concept and setting target levels of engineering performance to guide the later product development stages, while considering the needs of both the consumer and producer. The Quality Function Deployment (QFD) method was developed to transfer customer needs into engineering characteristics; however, limitations have been identified in using QFD, which can result in irrational and unrealistic results when used to set engineering priorities and target levels of product performance. In this paper, based on the principles of Decision-Based Design (DBD), a new design tool called the Product Attribute Function Deployment (PAFD) is demonstrated as a decision-theoretic, enterprise-wide process tool to guide the conceptual design phase. The PAFD method extends the qualitative matrix principles of QFD while utilizing the quantitative decision making processes of DBD to create a new process specifically for translating qualitative customer needs into quantitative engineering Attributes and making early product design decisions. It is built upon established methods in engineering, marketing, and decision analysis to eliminate the need for subjective user ratings. In addition, the technical Attributes considered are expanded beyond those typically considered to include requirements from the producer and regulators. The differences between QFD and PAFD are compared and the conceptual design of an automotive Manifold Absolute Pressure sensor is used to demonstrate the benefits of the PAFD method.
-
product Attribute Function deployment pafd for decision based conceptual design
2006 ASME International Design Engineering Technical Conferences and Computers and Information In Engineering Conference DETC2006, 2006Co-Authors: Christopher Hoyle, Deepak Kumar, Wei ChenAbstract:Quality Function Deployment (QFD) is a method that links the “Voice of the Customer” to product planning activities within design, production and marketing. It utilizes weighting factors and relationship matrices to rank order the importance of product Attributes. However, fundamental flaws have been identified in using QFD, which result in irrational and unrealistic results when used for design concept selection and setting target levels of Attributes for a design team. In this paper, based on the principles of Decision-Based Design (DBD), a new tool called the Product Attribute Function Deployment (PAFD) is introduced as an improvement to the QFD process. The PAFD method extends the qualitative matrix principles of QFD and utilizes the quantitative decision making processes of DBD, which incorporates the needs from both the producer and consumers in a rigorous decision making framework. The DBD method takes an enterprise view in problem formulation and optimizes a single criterion to avoid the difficulties associated with weighting factors and multi-objective optimization. In addition to the quantitative improvement, the definition of engineering Attributes in the QFD method is formalized to include corporate, regulatory, manufacturing and other technical requirements to facilitate conceptualization of design alternatives and constraints. The conceptual design of the automotive Manifold Absolute Pressure (MAP) sensor is used as a case study to demonstrate the benefits of the PAFD method.Copyright © 2006 by ASME
Smarandache Florentin - One of the best experts on this subject based on the ideXlab platform.
-
Extension of Soft Set to Hypersoft Set, and then to Plithogenic Hypersoft Set
UNM Digital Repository, 2019Co-Authors: Smarandache FlorentinAbstract:In this paper, we generalize the soft set tothe hypersoft set by transforming the Function F into a multi-Attribute Function. Then we introduce the hybrids of Crisp, Fuzzy, Intuitionistic Fuzzy, Neutrosophic, and Plithogenic Hypersoft Set
