Invite you to consult the lecture content "Image segmentation" below. Contents of lectures introduce to you the content: The goals of segmentation, inspiration from psychology, the gestalt school, gestalt factors,. Hopefully document content to meet the needs of learning, work effectively. | Image segmentation The goals of segmentation Group together similar-looking pixels for efficiency of further processing “Bottom-up” process Unsupervised X. Ren and J. Malik. Learning a classification model for segmentation. ICCV 2003. “superpixels” The goals of segmentation Separate image into coherent “objects” “Bottom-up” or “top-down” process? Supervised or unsupervised? Berkeley segmentation database: image human segmentation Inspiration from psychology The Gestalt school: Grouping is key to visual perception The Muller-Lyer illusion The Gestalt school Elements in a collection can have properties that result from relationships “The whole is greater than the sum of its parts” subjective contours occlusion familiar configuration Emergence Gestalt factors Grouping phenomena in real life Forsyth & Ponce, Figure The story is in the book (figure ) Grouping phenomena in real life Forsyth & Ponce, Figure The story is in the book (figure ) Gestalt factors These factors make intuitive sense, but are very difficult to translate into algorithms Segmentation as clustering Source: K. Grauman Image Intensity-based clusters Color-based clusters Segmentation as clustering K-means clustering based on intensity or color is essentially vector quantization of the image attributes Clusters don’t have to be spatially coherent I gave each pixel the mean intensity or mean color of its cluster --- this is basically just vector quantizing the image intensities/colors. Notice that there is no requirement that clusters be spatially localized and they’re not. Segmentation as clustering Source: K. Grauman Segmentation as clustering Clustering based on (r,g,b,x,y) values enforces more spatial coherence I | Image segmentation The goals of segmentation Group together similar-looking pixels for efficiency of further processing “Bottom-up” process Unsupervised X. Ren and J. Malik. Learning a classification model for segmentation. ICCV 2003. “superpixels” The goals of segmentation Separate image into coherent “objects” “Bottom-up” or “top-down” process? Supervised or unsupervised? Berkeley segmentation database: image human segmentation Inspiration from psychology The Gestalt school: Grouping is key to visual perception The Muller-Lyer illusion The Gestalt school Elements in a collection can have properties that result from relationships “The whole is greater than the sum of its parts” subjective contours occlusion familiar configuration Emergence .
