You are here

Category
Technology Name
Briefcase
Scientist
1461
Bidirectional Similarity offers a new approach to summarization of visual data (images and video) based on optimization of well defined similarity measure. Common visual summarization methods (mainly scaling and cropping) suffer from significant deficiencies related to image quality and loss of...

Bidirectional Similarity offers a new approach to summarization of visual data (images and video) based on optimization of well defined similarity measure.

Common visual summarization methods (mainly scaling and cropping) suffer from significant deficiencies related to image quality and loss of important data. Many attempts have been made to overcome these problems, however, success was very limited and neither has become commercially applicable.

Using an optimization problem approach and state-of-the-art algorithms, our method provides superior summarization of visual data as well as a measure to determine similarity, which together provides a basis for a wide range of applications in image and video processing.

Applications


The technology can be utilized in any application where an image size is changed or were similarity of images is important. Sample applications include:

  • Image processing software (as an added-on feature)

  • Resizing software

  • Creation of Thumbnails

  • Adjustment of images to different screen sizes (TV-cellular etc.)

  • Optimization of space-time patches in video processing

  • Image montages

  • Automatic image & video cropping

  • Images synthesis, photo reshuffling and many more


Advantages


While Bidirectional Similarity summarization will not replace existing technologies in all applications, it enjoys significant advantages that will offer better results in many of them. Among its advantages, the Bidirectional Similarity summarization:

  • Provides better resolution and in many cases reduces distortion compared to scaling
  • Reduces (or avoids) loss of important data compared to cropping
  • Allows importance-based summarization even when important information is widespread and hard to define
  • Uses quantitative objective similarity measure
  • Offers a generic tool for different image processing applications (synthesis, montage, reshuffling etc.)

Technology's Essence


Bidirectional Similarity Summarization is a patent-pending image and video processing method, which maximizes “completeness” and “coherence” between images and videos, using a measure for quantifying how “good” a visual summary is.

The algorithm uses and iterative process, gradually reducing the image size, while keeping all source patches in the target image, without introducing visual artifacts that are not in the input data. Using a Similarity Index, the algorithm identifies redundant information and compromise the “less important” data while generating the required target image or video.

The Similarity Index, which stands in the heart of the Bidirectional Similarity summarization algorithm, can be utilized by its own, as an objective function within other optimization processes, as well as in comparing the quality of visual summaries generated by different methods

+
  • Prof. Michal Irani
1021
A method for mapping and correcting optical distortion conferred by live cell specimens in microscopy that cannot be overcome using optical techniques alone can be used both for light microscopy and confocal microscopy. The system determines the 3D refractive index for the samples, and provides a...

A method for mapping and correcting optical distortion conferred by live cell specimens in microscopy that cannot be overcome using optical techniques alone can be used both for light microscopy and confocal microscopy. The system determines the 3D refractive index for the samples, and provides a method for ray tracing, calculation of 3D space variant point spread, and generalized deconvolution.

Applications


Microscopy: The method was developed and applied for light microscopy, and is of critical importance for detection of weak fluorescently labeled molecules (like GFP fusion proteins) in live cells. It may be applicable also to confocal microscopy and other imaging methods like ultrasound, deep ocean sonar imaging, radioactive imaging, non-invasive deep tissue optical probing and photodynamic therapy. Gradient glasses: The determination of the three-dimensional refractive index of samples allows testing and optimization of techniques for production of gradient glasses. Recently continuous refractive index gradient glasses (GRIN, GRADIUM) were introduced, with applications in high quality optics, microlenses, aspherical lenses, plastic molded optics etc. Lenses built from such glasses can be aberration-corrected at a level, which required doublets and triplets using conventional glasses. Optimized performance of such optics requires ray tracing along curved path, as opposed to straight segments between surface borders of homogeneous glass lenses. Curved ray tracing is computation-intensive and dramatically slows down optimization of optical properties. Our algorithm for ray tracing in gradient refractive index eliminates this computational burden.

Technology's Essence


A computerized package to process three-dimensional images from live biological cells and tissues was developed in order to computationally correct specimen induced distortions that cannot be achieved by optical technique. The package includes: 1. Three-dimensional (3D) mapping of the refractive index of the specimen. 2. Fast method for ray tracing through gradient refractive index medium. 3. Three-dimensional space variant point spread function calculation. 4. Generalized three-dimensional deconvolution.

+
  • Prof. Zvi Kam

Pages