The Experts below are selected from a list of 195 Experts worldwide ranked by ideXlab platform
Mengjie Zhang - One of the best experts on this subject based on the ideXlab platform.
-
EvoWorkshops - Program Size and Pixel Statistics in Genetic Programming for Object Detection
Lecture Notes in Computer Science, 2004Co-Authors: Mengjie Zhang, Urvesh BhowanAbstract:This paper describes an approach to the use of genetic programming for object detection problems. In this approach, local region pixel statistics are used to form three terminal sets. The function set is constructed by the four standard arithmetic Operators and a Conditional Operator. A multi-objective fitness function is constructed based on detection rate, false alarm rate, false alarm area and program size. This approach is applied to three object detection problems of increasing difficulty. The results suggest that the concentric circular pixel statistics are more effective than the square features for the coin detection problems. The fitness function with program size is more effective and more efficient for these object detection problems and the evolved genetic programs using this fitness function are much shorter and easier to interpret.
-
ACSW Frontiers - Applying online gradient descent search to genetic programming for object recognition
2004Co-Authors: William D. Smart, Mengjie ZhangAbstract:This paper describes an approach to the use of gradient descent search in genetic programming (GP) for object classification problems. In this approach, pixel statistics are used to form the feature terminals and a random generator produces numeric terminals. The four arithmetic Operators and a Conditional Operator form the function set and the classification accuracy is used as the fitness function. In particular, gradient descent search is introduced to the GP mechanism and is embedded into the genetic beam search, which allows the evolutionary learning process to globally follow the beam search and locally follow the gradient descent search. This method is compared with the basic GP method on four image data sets with object classification problems of increasing difficulty. The results show that the new method outperformed the basic GP method on all cases in both classification accuracy and training time, suggesting that the GP method with the gradient descent search is more effective and more efficient than without on object classification problems.
-
EvoWorkshops - Pixel statistics and false alarm area in genetic programming for object detection
Lecture Notes in Computer Science, 2003Co-Authors: Mengjie Zhang, Peter Andreae, Mark PritchardAbstract:This paper describes a domain independent approach to the use of genetic programming for object detection problems. Rather than using raw pixels or high level domain specific features, this approach uses domain independent statistical features as terminals in genetic programming. Besides position invariant statistics such as mean and standard deviation, this approach also uses position dependent pixel statistics such as moments and local region statistics as terminals. Based on an existing fitness function which uses linear combination of detection rate and false alarm rate, we introduce a new measure called "false alarm area" to the fitness function. In addition to the standard arithmetic Operators, this approach also uses a Conditional Operator if in the function set. This approach is tested on two object detection problems. The experiments suggest that position dependent pixel statistics computed from local (central) regions and nonlinear condition functions are effective to object detection problems. Fitness functions with false alarm area can reflect the smoothness of evolved genetic programs. This approach works well for the detecting small regular multiple class objects on a relatively uncluttered background.
Urvesh Bhowan - One of the best experts on this subject based on the ideXlab platform.
-
EvoWorkshops - Program Size and Pixel Statistics in Genetic Programming for Object Detection
Lecture Notes in Computer Science, 2004Co-Authors: Mengjie Zhang, Urvesh BhowanAbstract:This paper describes an approach to the use of genetic programming for object detection problems. In this approach, local region pixel statistics are used to form three terminal sets. The function set is constructed by the four standard arithmetic Operators and a Conditional Operator. A multi-objective fitness function is constructed based on detection rate, false alarm rate, false alarm area and program size. This approach is applied to three object detection problems of increasing difficulty. The results suggest that the concentric circular pixel statistics are more effective than the square features for the coin detection problems. The fitness function with program size is more effective and more efficient for these object detection problems and the evolved genetic programs using this fitness function are much shorter and easier to interpret.
Mark Pritchard - One of the best experts on this subject based on the ideXlab platform.
-
EvoWorkshops - Pixel statistics and false alarm area in genetic programming for object detection
Lecture Notes in Computer Science, 2003Co-Authors: Mengjie Zhang, Peter Andreae, Mark PritchardAbstract:This paper describes a domain independent approach to the use of genetic programming for object detection problems. Rather than using raw pixels or high level domain specific features, this approach uses domain independent statistical features as terminals in genetic programming. Besides position invariant statistics such as mean and standard deviation, this approach also uses position dependent pixel statistics such as moments and local region statistics as terminals. Based on an existing fitness function which uses linear combination of detection rate and false alarm rate, we introduce a new measure called "false alarm area" to the fitness function. In addition to the standard arithmetic Operators, this approach also uses a Conditional Operator if in the function set. This approach is tested on two object detection problems. The experiments suggest that position dependent pixel statistics computed from local (central) regions and nonlinear condition functions are effective to object detection problems. Fitness functions with false alarm area can reflect the smoothness of evolved genetic programs. This approach works well for the detecting small regular multiple class objects on a relatively uncluttered background.
Juanito Camilleri - One of the best experts on this subject based on the ideXlab platform.
-
a Conditional Operator for ccs
International Conference on Concurrency Theory, 1991Co-Authors: Juanito CamilleriAbstract:This paper investigates an extension of Milner's CCS with a Conditional Operator called unless [Cam90]. The agent \(\mathcal{K} \triangleright E\), pronounced E unless \(\mathcal{K}\), behaves as E unless the environment is ready to perform any action in the set \(\mathcal{K}\). This dependency on the set of actions the environment is ready to perform goes beyond that encountered in traditional CCS. Its expression is realised by an operational semantics in which transitions carry ready-sets (of the environment) as well as the normal action symbols from CCS. A notion of strong bisimulation is defined on Conditional agents via this semantics. It is a congruence and satisfies new equational laws (including a new expansion law) which are shown to be complete for finite agents with the unless Operator. The laws are conservative over agents of traditional CCS. The unless Operator provides a rudimentary means of expressing bias (or priority) in the behaviour of agents; it is more expressive than the prisum Operator presented in [CW91] and [Cam90].
-
CONCUR - A Conditional Operator for CCS
Lecture Notes in Computer Science, 1991Co-Authors: Juanito CamilleriAbstract:This paper investigates an extension of Milner's CCS with a Conditional Operator called unless [Cam90]. The agent \(\mathcal{K} \triangleright E\), pronounced E unless \(\mathcal{K}\), behaves as E unless the environment is ready to perform any action in the set \(\mathcal{K}\). This dependency on the set of actions the environment is ready to perform goes beyond that encountered in traditional CCS. Its expression is realised by an operational semantics in which transitions carry ready-sets (of the environment) as well as the normal action symbols from CCS. A notion of strong bisimulation is defined on Conditional agents via this semantics. It is a congruence and satisfies new equational laws (including a new expansion law) which are shown to be complete for finite agents with the unless Operator. The laws are conservative over agents of traditional CCS. The unless Operator provides a rudimentary means of expressing bias (or priority) in the behaviour of agents; it is more expressive than the prisum Operator presented in [CW91] and [Cam90].
Uwe Nestmann - One of the best experts on this subject based on the ideXlab platform.
-
This work is licensed under the Creative Commons Attribution License. Matching in the Pi-Calculus
2016Co-Authors: C K. Peters, Kirstin Peters, Tsvetelina Yonova-karbe, Uwe NestmannAbstract:We study whether, in the pi-calculus, the match prefix—a Conditional Operator testing two names for (syntactic) equality—is expressible via the other Operators. Previously, Carbone and Maffeis proved that matching is not expressible this way under rather strong requirements (preservation and reflection of observables). Later on, Gorla developed a by now widely-tested set of criteria for en-codings that allows much more freedom (e.g. instead of direct translations of observables it allows comparison of calculi with respect to reachability of successful states). In this paper, we offer a con-siderably stronger separation result on the non-expressibility of matching using only Gorla’s relaxed requirements.
-
EXPRESS/SOS - Matching in the Pi-Calculus.
Electronic Proceedings in Theoretical Computer Science, 2014Co-Authors: Kirstin Peters, Tsvetelina Yonova-karbe, Uwe NestmannAbstract:We study whether, in the pi-calculus, the match prefix-a Conditional Operator testing two names for (syntactic) equality-is expressible via the other Operators. Previously, Carbone and Maffeis proved that matching is not expressible this way under rather strong requirements (preservation and reflection of observables). Later on, Gorla developed a by now widely-tested set of criteria for encodings that allows much more freedom (e.g. instead of direct translations of observables it allows comparison of calculi with respect to reachability of successful states). In this paper, we offer a considerably stronger separation result on the non-expressibility of matching using only Gorla's relaxed requirements.
-
Matching in the Pi-Calculus (Technical Report)
arXiv: Logic in Computer Science, 2014Co-Authors: Kirstin Peters, Tsvetelina Yonova-karbe, Uwe NestmannAbstract:We study whether, in the pi-calculus, the match prefix---a Conditional Operator testing two names for (syntactic) equality---is expressible via the other Operators. Previously, Carbone and Maffeis proved that matching is not expressible this way under rather strong requirements (preservation and reflection of observables). Later on, Gorla developed a by now widely-tested set of criteria for encodings that allows much more freedom (e.g. instead of direct translations of observables it allows comparison of calculi with respect to reachability of successful states). In this paper, we offer a considerably stronger separation result on the non-expressibility of matching using only Gorla's relaxed requirements.