Seminar by Prof. Kay Barthel on "Visually Browsing Millions of Images using Image Graphs"

03 March 2017


Visually Browsing Millions of Images using Image Graphs

Kai Uwe Barthel
(HTW-Berlin - University of Applied Sciences)

Where: Amphitheatre 2 (FC6), CS Department, FCUP, Rua do Campo Alegre 1021, Porto

When: 3rd of March 2017 / 11:30am

Abstract: We present a new approach to visually browse very large sets of untagged images. High quality image descriptors are generated using transformed activations of a convolutional neural network. These features are used to model image similarities, from which a hierarchical image graph is build. We show how such a graph can be constructed efficiently. Best user experience for navigating this graph is achieved by projecting sub-graphs onto a regular 2D-image map. This allows users to explore the image graph similar to navigation services.

Short Bio: Prof. Dr. Kai Uwe Barthel studied electrical engineering at the Technical University of Berlin. At the university’s department for image and signal processing he finished his PhD in 1996 thesis about fractal image compression. In 1998 Kai became head of R&D with LuraTech Inc. where hard- and software for image compression were developed. He also participated in the JPEG2000 standardization committee. His research topic of that time was the  segmentation of documents for Mixed-Raster-Content compression. In 2001 Kai became a professor for visual computing at HTW Berlin, University of applied sciences. At HTW Berlin Kai is teaching courses such as image processing, computer vision, visual information retrieval and machine learning. Main research topics are visual image search and automatic image understanding. In 2009 Kai founded pixolution, a company for visual image search. Pixolution’s visual search technologies are used by many stock agencies. Kai’s latest research topics include automatic keywording of images, image clustering and the development of visual image navigation systems such as