Image Segmentation: A Survey of Methods Based on Evolutionary Computation

Liang, Yuyu; Zhang, Mengjie; Browne, Will N.

doi:10.1007/978-3-319-13563-2_71

Cited by 29 publications

(12 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods solve the problems associated with large dimensionality spaces using a natural selection which has been shown as a powerful search method. Recently, Yuyu et al [88] have presented a deep study on EC-based segmentation algorithms. Generally, many segmentation-based works combine the EC approach with other segmentation algorithms such as threshold, region growing, and partial differential equations.…”

Section: ) Evolutionary Computation-based Segmentationmentioning

confidence: 99%

“…In these hybrid methods, the EC takes the role of optimizing parameters or minimizing/maximizing objective functions. Additionally, the EC techniques could be applied to generate segmentation algorithms from a subset of basic image operators such as filters, histogram equalization and threshold [88]. 6) Co-segmentation Methods: Recently, more attention paid on the unsupervised image co-segmentation approach, where the segments are forced to be consistent across a collection of similar images.…”

Section: ) Evolutionary Computation-based Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Semantic content-based image retrieval: A comprehensive study

Alzu’bi

Amira

Ramzan

2015

Journal of Visual Communication and Image Representation

180

106

View full text Add to dashboard Cite

Section: ) Evolutionary Computation-based Segmentationmentioning

confidence: 99%

Section: ) Evolutionary Computation-based Segmentationmentioning

confidence: 99%

Semantic content-based image retrieval: A comprehensive study

Alzu’bi

Amira

Ramzan

2015

Journal of Visual Communication and Image Representation

180

106

View full text Add to dashboard Cite

“…AI based computation techniques imitate learning, reasoning and self-correction processes of intelligent beings to provide adequate solutions to problems that otherwise may require closed form formulations or computationally expensive algorithms. Among AI methods, biologically inspired algorithms have been successfully applied to a diverse set of problems including image processing [55], robotics [56], finance [57], cybersecurity [58], data processing [59] and autonomous movement control [60]. Genetic algorithms, genetic programming, swarm intelligence and AI planning are among the most popular AI methods employed for QCC.…”

Section: Artificial Intelligence Techniques For Qccmentioning

confidence: 99%

Survey on Quantum Circuit Compilation for Noisy Intermediate-Scale Quantum Computers: Artificial Intelligence to Heuristics

Kusyk

Saeed

2021

IEEE Trans. Quantum Eng.

View full text Add to dashboard Cite

Computationally expensive applications, including machine learning, chemical simulations and financial modeling, are promising candidates for noisy intermediate scale quantum (NISQ) computers. In these problems, one important challenge is mapping a quantum circuit onto NISQ hardware while satisfying physical constraints of an underlying quantum architecture. Quantum circuit compilation (QCC) aims to generate feasible mappings such that a quantum circuit can be executed in a given hardware platform with acceptable confidence in outcomes. Physical constraints of a NISQ computer change frequently, requiring QCC process to be repeated often. When a circuit cannot directly be executed on a quantum hardware due to its physical limitations, it is necessary to modify the circuit by adding new quantum gates and auxiliary qubits, increasing its space and time complexity. An inefficient QCC may significantly increase error rate and circuit latency for even the simplest algorithms. In this survey, we present AI and heuristic based methods recently reported in the literature that attempt to address these QCC challenges. We group them based on underlying techniques that they implement, such as AI algorithms including genetic algorithms, genetic programming, ant colony optimization and AI planning, and heuristics methods employing greedy algorithms, satisfiability problem solvers, dynamic and graph optimization techniques. We discuss performance of each QCC technique and evaluate its potential limitations.

show abstract

“…It is clear that intra-cluster similarity should be maximized and inter-cluster similarity should be minimized. Based on this idea, objective functions are defined [24]. The best partitioning of a given data set can be attained by minimizing/maximizing one or more objective functions.…”

Section: Image Clustering Using Cuckoo Search (Cs) Algorithmmentioning

confidence: 99%

StuCoSReC. Proceedings of the 2018 5th Student Computer Science Research Conference.

2018

View full text Add to dashboard Cite

show abstract

Image Segmentation: A Survey of Methods Based on Evolutionary Computation

Cited by 29 publications

References 20 publications

Semantic content-based image retrieval: A comprehensive study

Semantic content-based image retrieval: A comprehensive study

Survey on Quantum Circuit Compilation for Noisy Intermediate-Scale Quantum Computers: Artificial Intelligence to Heuristics

StuCoSReC. Proceedings of the 2018 5th Student Computer Science Research Conference.

Contact Info

Product

Resources

About