17455024. DETECTING UNACCEPTABLE DETECTION AND SEGMENTATION ALGORITHM OUTPUT simplified abstract (International Business Machines Corporation)

From WikiPatents
Jump to navigation Jump to search

DETECTING UNACCEPTABLE DETECTION AND SEGMENTATION ALGORITHM OUTPUT

Organization Name

International Business Machines Corporation

Inventor(s)

PEDRO LUIS Esquinas Fernandez of Etobicoke (CA)

Giovanni John Jacques Palma of Chaville (FR)

Omid Bonakdar Sakhi of North York (CA)

Paul Dufort of Toronto (CA)

Thomas Binder of Fontenay-sous-Bois (FR)

DETECTING UNACCEPTABLE DETECTION AND SEGMENTATION ALGORITHM OUTPUT - A simplified explanation of the abstract

This abstract first appeared for US patent application 17455024 titled 'DETECTING UNACCEPTABLE DETECTION AND SEGMENTATION ALGORITHM OUTPUT

Simplified Explanation

The patent application describes a method for automatically determining the quality of the output generated by a detection and segmentation algorithm. Here are the key points:

  • The processor receives an image and applies a detection stage of the algorithm to identify objects in the image.
  • The processor then analyzes the detection score map, which is a result of the detection stage, at multiple operating points to compute a set of features.
  • These features are then input into a classifier, which predicts whether the final output of the algorithm will meet a predefined quality threshold.
  • The quality threshold is based on whether a certain level of detection precision has been achieved.
  • The processor receives the output of the classifier, which indicates whether the algorithm's output is of acceptable quality.

Potential applications of this technology:

  • Object detection and segmentation in computer vision applications.
  • Quality control in image processing systems.
  • Automated assessment of the performance of detection and segmentation algorithms.

Problems solved by this technology:

  • Manual inspection and evaluation of the output generated by detection and segmentation algorithms can be time-consuming and subjective.
  • This technology automates the process of determining the quality of the algorithm's output, reducing the need for manual intervention.

Benefits of this technology:

  • Saves time and effort by automating the evaluation of detection and segmentation algorithm outputs.
  • Provides an objective measure of the quality of the algorithm's output.
  • Enables real-time assessment of the algorithm's performance, allowing for immediate feedback and adjustments if necessary.


Original Abstract Submitted

In an approach for automatically detecting whether an output of a detection and segmentation algorithm is of an acceptable quality, a processor receives an image. A processor applies a detection stage of a detection and segmentation algorithm to the image. A processor computes a set of features from a detection score map output by the detection stage of the detection and segmentation algorithm by analyzing the detection score map at more than one different operating points. A processor inputs the set of features into a classifier that predicts whether a final output of the detection and segmentation algorithm will be of an acceptable quality, wherein the acceptable quality is defined based on whether a detection precision threshold has been reached. A processor receives an output of the classifier.

Retrieved from "http://wikipatents.org/index.php?title=17455024._DETECTING_UNACCEPTABLE_DETECTION_AND_SEGMENTATION_ALGORITHM_OUTPUT_simplified_abstract_(International_Business_Machines_Corporation)&oldid=23549"