Ge Medical Systems Global Technology Company, LLC

General Electric Company

Pinaki Ghosh

Ananthakrishna Madhyastha

Gopal Biligeri Avinash

Ramesh Venkatesan

Amit Saxena

Preethish M Kumar

Preethish Kumar M

Kunnampally Gopalakrishnan Ramesh

Prateek Arora

Preethish Kumar Manohar

An object of the present invention is to extract an image closest to a reference image from among a plurality of candidate images. A plurality of candidate images similar to the reference image are extracted from a plurality of images by utilizing granulometry. The plurality of candidate images is transformed based on the reference image. Mutual information shared by each of the transformed candidate images and the reference image is calculated. A candidate image sharing the largest amount of mutual information with the reference image is selected from among the plurality of candidate images.

Image processing method and apparatus for extracting an image

In an embodiment, a method of digital image processing is provided wherein the method includes the actions of (i) segmenting a data set of an image to be processed, based on predetermined conditions (ii) generating a maximum intensity projection of the segmented data set (iii) closing-by-reconstruction of said data set in parallel to action (ii) (iv) combining the result of action (i) with result of action (iii) by a logical AND function, and (v) replacing pixels of undesired intensity in result of action (ii) by pixels of desired intensity from result of action (iv).

Method and system for digital image processing

The present invention provides a system, method and computer program product for improving quality of images. The pixels of the input image are used to generate two lists of pixels based on two different scale space values. Thereafter, the two pixels lists are processed to obtain an output image with improved quality.

Systems and methods for optimized region growing algorithm for scale space analysis

An image processing method for conducting anisotropic diffusion filtering on a pixel value Iin a two-dimensional image, comprises: finding conduction coefficients C, C, C, C, C, C, Cand Cin eight surrounding directions for each pixel based on a pixel value gradient &#x2207;I to produce a two-dimensional distribution image of the conduction coefficients; and finding pixel value first partial differentials &#x2207;I, &#x2207;I, &#x2207;I, &#x2207;I, &#x2207;I, &#x2207;I, &#x2207;I and &#x2207;I in the eight surrounding directions for each pixel to calculate a pixel value in an output image according to: 

Image processing method and apparatus

Optimized region growing algorithm for scale space analysis

In ultrasound imaging, acquired images are corrupted by slowly varying multiplicative non-uniformity. When the image is corrected for non-uniformity alone, noise in the dark regions of the original image becomes multiplicatively enhanced, thereby providing an unnatural look to the image. A pre-filtering technique is used to reduce noise in ultrasound pixel images by shrinking initial image data and processing the shrunken image with known segmentation-based filtering techniques that identify and differentially process structures within the image. The segmentation is based on both gradient threshold and the distance from the near field of the ultrasound image. This modification selectively suppresses near-field artifacts. After processing, the shrunken image is enlarged to the dimensions of the initial data and then blended with the initial image to form the final image. During blending, a small predetermined fraction of intensity-dependent, uniform random noise is added to the non-structure region pixels whose intensities are above a pre-specified intensity threshold, to mitigate ultrasound speckles while leaving non-echogenic regions undisturbed.

Computationally efficient noise reduction filter for enhancement of ultrasound images

A system and a method for adjusting contrast and brightness in an image, e.g., an ultrasound image. The contrast and brightness are adjusted by processing global pixel intensity data to form a set of data representing a histogram. An algorithm is then employed to filter the pixel intensity values as a function of certain characteristics of the histogram data. The algorithm is designed to enhance contrast and brightness without affecting the near-field region in the ultrasound image. The filtering operations may be performed by a dedicated processor or by a fast general-purpose computer.

Growing community of inventors

Bengaluru, India

Pinaki Ghosh