EE Seminar: Adaptive Focus Estimation in Shape from Focus

~~Speaker: Yuval Frommer
M.Sc. student under the supervision of Prof. Nahum Kiryati and Dr. Rami Ben Ari

Wednesday, June 1st, 2016 at 15:00
Room 011, Kitot Bldg., Faculty of Engineering

Adaptive Focus Estimation in Shape from Focus

Abstract

Shape from Focus (SFF) methods frequently use a single focus measure to obtain a depth map. Common focus measures are fixed and spatially invariant. In this paper we present a framework to create an adaptive focus measure based on ensemble of basis focus operators. Using the proposed framework, we derive a new spatially variant focus measure obtained from a linear combination of image derivatives. This approach effectively generalizes some of the existing measures. We introduce a new focus measure which combines high order derivatives to produce robust and accurate focus measurement. We rely on the focus curve standard deviation (CSTD) to determine the linear coefficients in our model. The proposed focus measure copes effectively with texture variation, as well as depth discontinuities. Using CSTD we further suggest a new approach for aggregating the focus volume, succeeded by reconstruction based on the focus curve centroid. This different approach of aggregation and reconstruction yields improved depth maps, respecting shape smoothness and depth discontinuities for diversity of textured images.
We assess the performance of our new approach by extensive experiments with highly realistic synthetic
images and real images including two unique cases captured in the wild. In terms of focus measure, we significantly outperform the state-of-the-art. Considering the complete SFF pipeline, we present superior results comparing to two previously published alternatives.