2000
DOI: 10.1002/1098-111x(200010)15:10<901::aid-int1>3.0.co;2-c
|View full text |Cite
|
Sign up to set email alerts
|

Genetic algorithms for scene interpretation from prototypical semantic description

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2006
2006
2011
2011

Publication Types

Select...
3
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(4 citation statements)
references
References 16 publications
0
4
0
Order By: Relevance
“…The Red Green Blue (RGB) is the space representation of images that we used. In this case, and as the first step in designing an evolutionary algorithm is to encode (represent) solutions as chromosomes which are strings of genes mainly depends on the considered application and the mannered goal [11], then an encoding of individuals is thus introduced.…”
Section: Encodingmentioning
confidence: 99%
See 1 more Smart Citation
“…The Red Green Blue (RGB) is the space representation of images that we used. In this case, and as the first step in designing an evolutionary algorithm is to encode (represent) solutions as chromosomes which are strings of genes mainly depends on the considered application and the mannered goal [11], then an encoding of individuals is thus introduced.…”
Section: Encodingmentioning
confidence: 99%
“…So, in order to evaluate or quantify the difference between two images, we used the same measures as those used in [28]. The Number of Pixels Change Rate (NPCR) formulated through the expression (9), Mean Absolute Error (MAE) given by the expression (11) and Mean Square Error (MSE) given by the expression (12). …”
Section: Statistical Attackmentioning
confidence: 99%
“…The overall GA optimization system [5] is described by the schematic in Figure 1. GA starts with an initial population of coded strings, which are generally called individual or chromosome and randomly selected.…”
Section: Standard Genetic Algorithmmentioning
confidence: 99%
“…The EA-based approach to automatic classification and labeling of the objects observed in the image is further developed by Buckles and his co-workers [16,17], and applied to the classification of noisy and obscured natural scenes from oceanographic and meteorological data collection. Investigators report that a series of experiments on the identification of ocean currents in infrared imagery of North Atlantic, and on the classification of clouds in AVHRR (Advanced Very High Resolution Radiometer) imagery of the Western US show a high degree of accuracy.…”
Section: Semantic Scene Interpretationmentioning
confidence: 99%