Hyperparameter Optimization for Image Recognition over an AR-Sandbox Based on Convolutional Neural Networks Applying a Previous Phase of Segmentation by Color-Space.
Andrés Ovidio Restrepo RodríguezDaniel Esteban Casas MateusPaulo Alonso Gaona GarcíaCarlos Enrique Montenegro MarínRubén González CrespoPublished in: Symmetry (2018)
Keyphrases
- image recognition
- color space
- color image segmentation
- convolutional neural networks
- color features
- color images
- color model
- color models
- histogram analysis
- hsv color space
- rgb color space
- face recognition
- color quantization
- hsi color space
- image segmentation
- color regions
- pattern recognition
- skin color detection
- segmentation method
- pixel classification
- image retrieval
- segmentation algorithm
- hybrid color space
- object segmentation
- color components
- skin color
- color histogram
- image processing
- machine learning
- region growing
- segmented images
- level set
- image classification
- image analysis
- graph cuts
- computer vision
- similarity measure
- multiscale
- spatial color
- multiresolution
- energy function
- background subtraction
- skin detection
- color information
- color distribution