18162994. OBJECT ORIENTED IMAGE NORMALIZATION simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)

From WikiPatents
Jump to navigation Jump to search

OBJECT ORIENTED IMAGE NORMALIZATION

Organization Name

INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor(s)

Aviad Zlotnick of Mitzpeh Netofah (IL)

OBJECT ORIENTED IMAGE NORMALIZATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 18162994 titled 'OBJECT ORIENTED IMAGE NORMALIZATION

Simplified Explanation

The patent application describes a method and system for reducing the number of colors per pixel in an image to improve object detection or anomaly detection.

  • The method determines a final number of colors per pixel to reduce the image to, which is less than the original number of colors per pixel.
  • It identifies corresponding threshold values for each of the final number of colors, optimizing an arithmetic combination of separation score functions applied to the pixels and threshold values.
  • The image is then reduced to the final number of colors per pixel by creating an output image, where the value of each output pixel represents the number of threshold values that are less than the value of the corresponding input pixel.

Potential applications of this technology:

  • Object detection: The reduced color image can enhance the ability to detect objects in images, making it useful in various fields such as surveillance, autonomous vehicles, and robotics.
  • Anomaly detection: By reducing the number of colors per pixel, this technology can help identify anomalies or abnormalities in images, aiding in areas like medical imaging, quality control, and security.

Problems solved by this technology:

  • Improved detection: By reducing the number of colors per pixel, the method enhances the ability to detect objects or anomalies that may be difficult to identify in the original image.
  • Increased efficiency: The reduction in colors per pixel allows for more efficient processing and analysis of images, saving computational resources.

Benefits of this technology:

  • Enhanced detection accuracy: The reduced color image improves the ability to detect objects or anomalies, leading to more accurate results.
  • Efficient processing: By reducing the number of colors per pixel, the method enables faster processing and analysis of images.
  • Versatile applications: The technology can be applied in various fields where object detection or anomaly detection is crucial, providing a wide range of potential applications.


Original Abstract Submitted

A method and system for reducing the number of colors per pixel present in an image to increase the ability to detect objects or anomalies in the image. A final number of colors per pixel to reduce the image to is determined, wherein the final number of colors is a number of colors less than the number of colors per pixel in the original image. A corresponding threshold value for each of the final number of colors is identified, such that the corresponding threshold values optimize an arithmetic combination of separation score functions applied to the plurality of pixels and the threshold values. The image is reduced to the final number of colors per pixel, by creating an output image where a value of each output pixel is equal to the number of threshold values that are less than the value of the corresponding input pixel.

Retrieved from "http://wikipatents.org/index.php?title=18162994._OBJECT_ORIENTED_IMAGE_NORMALIZATION_simplified_abstract_(INTERNATIONAL_BUSINESS_MACHINES_CORPORATION)&oldid=25770"