17940889. Image Compression using Integrated Circuit Devices having Analog Inference Capability simplified abstract (Micron Technology, Inc.)

From WikiPatents
Jump to navigation Jump to search

Image Compression using Integrated Circuit Devices having Analog Inference Capability

Organization Name

Micron Technology, Inc.

Inventor(s)

Poorna Kale of Folsom CA (US)

Image Compression using Integrated Circuit Devices having Analog Inference Capability - A simplified explanation of the abstract

This abstract first appeared for US patent application 17940889 titled 'Image Compression using Integrated Circuit Devices having Analog Inference Capability

Simplified Explanation

The patent application describes a method in an integrated circuit device to compress images using image processing and inference logic circuits.

  • Image compression method in an integrated circuit device:
   * Generating input data based on first data representative of an input image.
   * Generating a column of inputs based on the input data.
   * Converting results of bitwise multiplications of bits in the column of inputs and bits stored in memory cells into output currents using voltage drivers connected to wordlines.
   * Digitizing currents summed in the bitlines to obtain column outputs.
   * Generating output data based on the column outputs.
   * Generating second data representative of an output image compressed from the input image using the output data.

Potential Applications

This technology can be applied in:

  • Image processing systems
  • Data compression algorithms
  • Embedded systems for image processing

Problems Solved

This technology helps in:

  • Efficient image compression
  • Faster image processing
  • Reduced memory storage requirements

Benefits

The benefits of this technology include:

  • Improved image compression ratios
  • Enhanced image processing speed
  • Lower memory usage for storing images

Potential Commercial Applications

The potential commercial applications of this technology can be seen in:

  • Consumer electronics devices
  • Medical imaging equipment
  • Surveillance systems

Possible Prior Art

One possible prior art for image compression in integrated circuits is the use of convolutional neural networks for image processing and compression.

What is the impact of this technology on image processing efficiency?

This technology significantly improves image processing efficiency by compressing images effectively, reducing the computational load, and speeding up the overall process.

How does this technology compare to traditional image compression methods?

This technology offers higher compression ratios and faster processing speeds compared to traditional image compression methods like JPEG or PNG.


Original Abstract Submitted

A method in an integrated circuit device to compress images, including: generating, by an image processing logic circuit and based on first data representative of an input image, input data; generating, by an inference logic circuit and based on the input data, a column of inputs; converting, by the inference logic circuit using voltage drivers connected to wordlines and memory cells storing a weight matrix, and into output currents of the memory cells summed in bitlines, results of bitwise multiplications of bits in the column of inputs and bits stored in the memory cells in a form of threshold voltages of the memory cells; digitizing currents summed in the bitlines to obtain column outputs; generating, by the inference logic circuit, output data based on the column outputs; and generating, using the output data, second data representative of an output image compressed from the input image.