Evolutionary image processing
≈ 5 min read
Names in other languages
- Deutschevolutionäre BildverarbeitungEB
- EnglishEvolutionary image processing
- УкраїнськаЕволюційна обробка зображень
Article bodies are English and are not machine-translated. A name in another language is not a translation of the article.
Evolutionary image processing (EIP) is a sub-area of digital image processing.[1] Evolutionary algorithms (EA) are used to optimize and solve various image processing problems. Evolutionary image processing thus represents the combination of evolutionary optimization and digital image processing. EAs have been used for several decades in computer science to optimize various problems. The application in image processing, on the other hand, is still a relatively new field of research. This is primarily due to the technological development of computer systems, as EIP is a relatively computationally intensive process. Evolutionary computer vision (ECV) is an application of EIP for computer vision.[2] It has been shown that genetic programming (GP) as a subclass of EAs is particularly useful for image processing.
Genetic programming for image processing
edit edit sourceIn evolutionary image processing, genetic programming optimizes the arrangement of different image-processing operators for specific outputs or task performance.[3] As of 2021, in comparison to popular and well developed convolutional neural networks, GP is an emerging technique for feature learning.[4] In particular, GP has been used for developing accurate classifiers for object detection, classification of medical images, and optical character recognition. GP has multiple advantages in case of image processing.[3] They include:
- The GP output is a program or a collection of programs in the form of mathematical expressions, which are easy to interpret after simplification and conversion to normal notation.
- The GP needs considerable time for evolution of GP based classifiers. However, the resulting GP tree needs very short execution time in the testing.
- GP fitness function is flexible and can be adapted according to the problem to be solved.
The disadvantages of GP for image processing include:
- Computational cost for evolution of GP based classifiers is very high.
- A large dataset is required for the training.
- Due to their stochastic nature, a solution is not guaranteed.
See also
edit edit sourceReferences
edit edit source- ^ Proceedings / 22. Workshop Computational Intelligence: Dortmund, 6 - 7. Dezember 2012. Karlsruhe: KIT Scientific Publishing. 2012. ISBN 9783866449176.
- ^ Ebner, Marc (2010). "Evolving Object Detectors with a GPU Accelerated Vision System". Evolvable Systems: From Biology to Hardware. Lecture Notes in Computer Science. Vol. 6274. Springer. pp. 109–120. doi:10.1007/978-3-642-15323-5_10. ISBN 978-3-642-15322-8.
- ^ a b Khan, Asifullah; Qureshi, Aqsa Saeed; Wahab, Noorul; Hussain, Mutawarra; Hamza, Muhammad Yousaf (2021). "A recent survey on the applications of genetic programming in image processing". Computational Intelligence. 37 (4): 1745–1778. arXiv:1901.07387. doi:10.1111/coin.12459. ISSN 1467-8640.
- ^ Bi, Ying; Xue, Bing; Zhang, Mengjie (August 2022). "Genetic Programming-Based Discriminative Feature Learning for Low-Quality Image Classification". IEEE Transactions on Cybernetics. 52 (8): 8272–8285. Bibcode:2022ITCyb..52.8272B. doi:10.1109/TCYB.2021.3049778. PMID 33531319.
- Cellular evolutionary algorithm
- Covariance Matrix Adaptation Evolution Strategy (CMA-ES)
- Cultural algorithm
- Differential evolution
- Evolutionary programming
- Genetic algorithm
- Genetic programming
- Gene expression programming
- Evolution strategy
- Natural evolution strategy
- Neuroevolution
- Learning classifier system
- Artificial development
- Artificial intelligence
- Artificial life
- Digital organism
- Evolutionary robotics
- Fitness function
- Fitness landscape
- Fitness approximation
- Genetic operators
- Interactive evolutionary computation
- No free lunch in search and optimization
- Machine learning
- Mating pool
- Premature convergence
- Program synthesis
- Evolutionary Computation (journal)
- IEEE Trans Evol Comput
- ACM Trans Evol Learning Optim
- 3D pose estimation
- Activity recognition
- Audio-visual speech recognition
- Automatic image annotation
- Automatic number-plate recognition
- Automated species identification
- Augmented reality
- Bioimage informatics
- Bin picking
- Blob detection
- Computer-aided diagnosis
- Content-based image retrieval
- Eye tracking
- Face recognition
- Foreground detection
- Gesture recognition
- Image denoising
- Image restoration
- Landmark detection
- Medical image computing
- Object detection
- Optical character recognition
- Pose tracking
- Remote sensing
- Robotic mapping
- Autonomous vehicles
- Video browsing
- Video content analysis
- Video motion analysis
- Video surveillance
- Video synopsis
- Video tracking
Text derived from https://en.wikipedia.org/w/index.php?oldid=1310019138 under CC BY-SA 4.0; modifications have been made.