Skip to main content
eScholarship
Open Access Publications from the University of California

Scholarly Works (2 results)

  • Thesis
  • Peer Reviewed
UC Berkeley Electronic Theses and Dissertations (2017)

The objective of this research is to advance the state of the art in image matching algorithms, especially with regard to input image pairs that include dramatically inconsistent appearance (e.g., different sensor modalities, significant intensity/color changes, different times such as day/night and years apart, etc.). We denote this range of input as disparate input. To handle disparate input, one should be able to capture the underlying aspects not affected by superficial changes to appearance.

To this end, we present a novel image descriptor based on the distribution of line segments in an image; we call it DUDE (DUality Descriptor). By exploiting line-point duality, DUDE descriptors are computationally efficient and robust to unstable line segment detection. Our experiments show that DUDE can provide more true-positive correspondences for challenging disparate datasets.

Beyond traditional image matching, we have designed an effective autograding system for multiview engineering drawings that also uses DUDE to improve its performance. The autograding system needs to be able to compare drawings that may include appearance changes due to students' mistakes, but also needs to differentiate between allowable and erroneous translation and/or scale changes.

In the addition to hand-crafted descriptors, this research also investigates data-driven descriptors generated by new deep learning based approaches. Due to the lack of labeled disparate imagery datasets, it is still challenging to effectively target disparate input using deep learning approaches. Therefore we introduce an aggressive data augmentation strategy called Artificial Intensity Remapping (AIR). By applying AIR to standard datasets, one can obtain models that are more effective for registration of disparate data. Finally, we compare the DUDE descriptor to a deep learning based descriptor powered by AIR.

    Cover page: Automated Registration of Image Pairs with Dramatically Inconsistent Appearance
    • Article
    • Peer Reviewed
    UC Berkeley Previously Published Works (2020)
    The impact of topological defects associated with grain boundaries (GB defects) on the electrical, optical, magnetic, mechanical and chemical properties of nanocrystalline materials1,2 is well known. However, elucidating this influence experimentally is difficult because grains typically exhibit a large range of sizes, shapes and random relative orientations3-5. Here we demonstrate that precise control of the heteroepitaxy of colloidal polyhedral nanocrystals enables ordered grain growth and can thereby produce material samples with uniform GB defects. We illustrate our approach with a multigrain nanocrystal comprising a Co3O4 nanocube core that carries a Mn3O4 shell on each facet. The individual shells are symmetry-related interconnected grains6, and the large geometric misfit between adjacent tetragonal Mn3O4 grains results in tilt boundaries at the sharp edges of the Co3O4 nanocube core that join via disclinations. We identify four design principles that govern the production of these highly ordered multigrain nanostructures. First, the shape of the substrate nanocrystal must guide the crystallographic orientation of the overgrowth phase7. Second, the size of the substrate must be smaller than the characteristic distance between the dislocations. Third, the incompatible symmetry between the overgrowth phase and the substrate increases the geometric misfit strain between the grains. Fourth, for GB formation under near-equilibrium conditions, the surface energy of the shell needs to be balanced by the increasing elastic energy through ligand passivation8-10. With these principles, we can produce a range of multigrain nanocrystals containing distinct GB defects.
      Cover page: Design and synthesis of multigrain nanocrystals via geometric misfit strain
      Top