Alvaro Soto
Transcripción
Alvaro Soto
DCC - PUC Case Study 80 million tiny images: a large dataset for nonparametric object and scene recognition A. Torralba, R. Fergus and W. T. Freeman PAMI, Nov. 2008 Alvaro Soto Alvaro Soto 1 DCC - PUC K-Vecinos Cercanos Predicción Uso de métrica de distancia Clasificación Votación por mayoría Alvaro Soto 2 DCC - PUC Parámetros y Modelos • Modelos Paramétricos • Ej. Regresión lineal • Modelos SemiParamétricos • Ej. Fourier, wavelets • Modelos No Paramétricos • Ej. K-vecinos cercanos Alvaro Soto 3 DCC - PUC What can you do with 80M images? A. Torralba, R. Fergus and W. T. Freeman. 80 million tiny images: a large dataset for non-parametric object and Alvaro Soto scene recognition. IEEE PAMI, 2006. 4 DCC - PUC Alvaro Soto 5 DCC - PUC Alvaro Soto 6 DCC - PUC Alvaro Soto 7 DCC - PUC Alvaro Soto 8 DCC - PUC How to measure similarity between images? Patch horizontal mirror, translations and scaling. Individual pixel shift in 5x5 window. T given By best Dwarp. Alvaro Soto 9 DCC - PUC Image matching using distance metrics: Dssd , Dwarp and Dshift Alvaro Soto 10 DCC - PUC Images They use 7 independent image search engines: Altavista, Ask, Flickr, Cydral, Google, Picsearch and Webshots. They extract all non-abstract nouns from wordnet: 75.846 in total. They automatically download all the images provided by each engine for all non-abstract nouns. Running over 8 months, this method gathered 97.245.098 images in total. Once intra-word duplicates and uniform images (images with zero variance) are removed, this number is reduced to 79.302.017 images from 75.062 words (around 1% of the keywords had no images). They store the images using a resolution of 32x32 pixels (eficiency). Alvaro Soto 11 DCC - PUC Wordnet Wikipedia: WordNet es una enorme base de datos léxica del idioma inglés. Agrupa las palabras en conjuntos de sinónimos llamados 'synsets', almacenando las relaciones semánticas entre estos conjuntos de sinónimos. Alvaro Soto 12 DCC - PUC A histogram of images per keyword collected Alvaro Soto 13 DCC - PUC Precision in Outputs from Search Engines Accuracy drops after the 100th image and then stabilizes at around 44% correct on average. Alvaro Soto 14 DCC - PUC Accuracy of labeling for different nodes of a portion of the Wordnet tree. More precision for more specific words Alvaro Soto 15 DCC - PUC Recognition Using Wordnet and Original Keywords Used to Retrieve Each Image Alvaro Soto 16 DCC - PUC Alvaro Soto 17