Colored facial image restoration by similarity enhanced implicative fuzzy association memory
| Autor: | Doo Heon Song, Kwang Baek Kim |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Control and Optimization
Similarity (geometry) Computer Networks and Communications Computer science Fuzzy similarity ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Similarity measure Fuzzy logic Image (mathematics) Image restoration 0202 electrical engineering electronic engineering information engineering Electrical and Electronic Engineering business.industry Process (computing) 020206 networking & telecommunications Pattern recognition Mean square error Fuzzy associative memory Colored Hardware and Architecture Signal Processing 020201 artificial intelligence & image processing Artificial intelligence Noise (video) business Facial image Information Systems |
| Popis: | Image restoration refers to the recovery of an underlying image from an observation that has been corrupted by various types of noise. In a digital forensic software, such image restoration process should be noise-tolerant, robust, fast, and scalable. In this paper, we apply implicative fuzzy association memory structure in colored facial image restoration with enhanced similarity measure involved in output computarion. The efficacy if the proposed fuzzy associative memory model is verified by the experiment in that it was 95% successful (with zero mean square error) out of 20 tested images. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|