Face-based Chromatic Adaptation for Tagged Photo Collections
نویسنده
چکیده
Colour constancy is the phenomenon where the chromaticity of a surface material appears to remain constant to an observer under different illuminants. Studies have shown human vision exhibits colour constancy to varying degrees. Digital camera sensors completely lack this property, resulting in pictures with unsightly colour casts. This paper presents a method for semi-automatically removing colour casts due to the incorrect application of in-camera white balance settings. Correction is done in a perceptually uniform opponent colour space derived from the Munsell colour system. CR Categories: I.2.10 [Artificial Intelligence]: Vision and Scene Understanding—Intensity, color, photometry, and thresholding; I.4.8 [Image Processing and Computer Vision]: Scene Analysis— Color;
منابع مشابه
AutoTag 'n Search My Photos: Leveraging the Social Graph for Photo Tagging
Personal photo collections are large and growing rapidly. Today, it is difficult to search such a photo collection for people who occur in them since it is tedious to manually associate face tags in photos. The key idea is to learn face models for friends and family of the user using tagged photos in a social graph such as Facebook as training examples. These face models are then used to automa...
متن کاملIdentity Annotation in Photo Collections: A Survey
This paper reviews the problem of determining the identity of people appearing in photo collections. The applications and social impact of problem solutions are also given. Finally, some of the main open challenges and other future outlooks are provided. The basic approach to the person identification problem uses machine vision techniques to perform face recognition, however such methods are i...
متن کاملAutomatic Text Searching For Personal Photos
This demonstration presents the MediAssist prototype system for organisation of personal digital photo collections based on contextual information, such as time and location of image capture, and content-based analysis, such as face detection and recognition. This metadata is used directly for identification of photos which match specified attributes, and also to create text surrogates for phot...
متن کاملMediaEval Benchmark: Social Event Detection in collaborative photo collections
In this paper, we present an approach to detect social events in collaboratively annotated photo collections as part of the MediaEval Benchmark. We combine various information from tagged photos with external data sources to train a classification model. Experiments based on the MediaEval Social Event Detection Dataset demonstrate the effectiveness of our approach.
متن کاملMediAssist: Using Content-Based Analysis and Context to Manage Personal Photo Collections
We present work which organises personal digital photo collections based on contextual information, such as time and location, combined with content-based analysis such as face detection and other feature detectors. The MediAssist demonstration system illustrates the results of our research into digital photo management, showing how a combination of automatically extracted context and content-b...
متن کامل