Conference Agenda

Overview and details of the sessions of this conference. Please register as a participant for the conference (free!) and then Login in order to have access to downloads in the detailed view. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view.

 
 
Session Overview
Session
Keynote 3: Thrasos Pappas, Northwestern University: "Perceptual Texture Analysis for Multimedia Processing"
Time:
Thursday, 24/Sept/2020:
3:10pm - 4:10pm

Session Chair: Giacomo Boracchi
Location: Virtual platform

Session Abstract

Texture is an important attribute for both human perception and signal analysis. It provides important clues for object detection and material recognition. Visual texture similarity is important for image and video quality, compression, and content-based retrieval. Texture analysis is also important for sense substitution (visual to acoustic-tactile conversion), multimodal interfaces for virtual reality and immersive environments, product design, surveillance and security, environmental monitoring, and medical applications.

We have proposed a new class of structural texture similarity metrics (STSIMs) that account for human visual perception and the stochastic nature of textures. They rely entirely on local image statistics and allow substantial point-by-point deviations between textures that according to human judgment are similar or essentially identical. We have identified three operating domains for evaluating the performance of objective texture similarity metrics, each with different performance goals and testing procedures. We have also proposed ViSiProG (Visual Similarity by Progressive Grouping), a new procedure for collecting subjective similarity data.

Our current focus is on material identification and characterization. Each material can be characterized by limited number of exemplars that reflect different environmental conditions. The characterization can also be based on specific attributes, such as roughness, glossiness, and spectral composition, which provide strong clues about material properties and can be estimated over a wide range of conditions.