Patent · US Active

Weakly supervised anomaly detection and segmentation in images

US10672115B2 · kind B2 · utility

3Cited by
0References
14Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 6, 2017
Grant dateJun 2, 2020
Priority date
Expiry dateDec 6, 2037

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/20084
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Systems and methods are disclosed for processing an image to detect anomalous pixels. An image classification is received from a trained convolutional neural network (CNN) for an input image with a positive classification being defined to represent detection of an anomaly in the image and a negative classification being defined to represent absence of an anomaly. A backward propagation analysis of the input image for each layer of the CNN generates an attention mapping that includes a positive attention map and a negative attention map. A positive mask is generated based on intensity thresholds of the positive attention map and a negative mask is generated based on intensity thresholds of the negative attention map. An image of segmented anomalous pixels is generated based on an aggregation of the positive mask and the negative mask.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.