2013 · 14 citations · 7 references
ComputingComputer ScienceComputer VisionData MiningMachine LearningClassificationFace RecognitionImage ClassificationObject RecognitionPattern RecognitionShape AnalysisComputer-based Facial AnalysisHair Appearance ModelingUnsupervised Image Clustering
This paper presents a novel method for discovery and recognition of hairstyles in a collection of colored face images. We propose the use of Agglomerative clustering for automatic discovery of distinct hairstyles. Our method proposes automated approach for generation of hair, background and face-skin probability-masks for different hairstyle category without requiring manual annotation. The probability-masks based density estimates are subsequently applied for recognizing the hairstyle in a new face image. The proposed methodology has been verified with a synthetic dataset of approximately thousand images, randomly collected from the Internet.
7
Modern hierarchical, agglomerative clustering algorithms
Daniel Müllner · arXiv (Cornell University) · 2011 · 356 citations · Full text
Image Segmentation Based on 2D Otsu Method with Histogram Analysis
Markov random field models for hair and face segmentation
Kuang-chih Lee, Dragomir Anguelov, Baris Sumengen et al. · 2008 · 50 citations