Automated salience assessment of pixel anomalies

Number: 11508143
Published: 2022-11-22
Filed: 2020-04-03
Assignee: Disney Enterprises, Inc.
Inventors: Doggett; Erika Varis
CPC: G06V20/46; G06V10/462; G06V10/82; G06T7/0002
Verdict: Set aside generic image anomaly/QC detection
Source: Google Patents · FreePatentsOnline

Abstract

According to one implementation, a system for performing automated salience assessment of pixel anomalies includes a computing platform having a hardware processor and a system memory storing a software code. The hardware processor is configured to execute the software code to analyze an image for a presence of a pixel anomaly in the image, obtain a salience criteria for the image when the analysis of the image detects the presence of the pixel anomaly, and classify the pixel anomaly as one of a salient anomaly or an innocuous anomaly based on the salience criteria for the image. The hardware processor is further configured to execute the software code to disregard the pixel anomaly when the pixel anomaly is classified as an innocuous anomaly, and to flag the pixel anomaly when the pixel anomaly is classified as a salient anomaly.

Background

BACKGROUND (1) Pixel errors in images occur with regularity but can be difficult and costly to identify and correct. For example, anomalous pixels in video frames can be introduced by many different processes within a video production pipeline. A final quality procedure for detecting and correcting such errors is typically done before the video undergoes final release. (2) In the conventional art, anomalous pixel detection is usually performed by human inspectors. Generally, those human inspectors are tasked with checking every single frame of each video several hundreds of times before its final distribution. Due to this intense reliance on human participation, the conventional approach to pixel error detection and correction is undesirably expensive and time consuming. Moreover, not all pixel anomalies require correction. For example, depending on its position within an image, as well as its relationship to particularly important features within the image, some pixel anomalies may reasonably be disregarded. That is to say, not all pixel errors are sufficiently salient to justify the costs associated with their correction. Accordingly, there is a need in the art for an automated solution enabling the accurate assessment of the salience of anomalous pixel errors detected in an image. SUMMARY (3) There are provided systems and methods for performing automated salience assessment of pixel anomalies, substantially as shown in and/or described in connection with at least one of t

Claims

1. A system comprising: a computing platform including a hardware processor and a system memory storing a software code; the hardware processor configured to execute the software code to: detect a pixel anomaly in an image; obtain a salience criterion for the image; after detecting the pixel anomaly, classify the pixel anomaly as one of a salient anomaly or an innocuous anomaly based on the salience criterion for the image; disregard the pixel anomaly when the pixel anomaly is classified as the innocuous anomaly; and flag the pixel anomaly when the pixel anomaly is classified as the salient anomaly. || 9. A method for use by a system including a computing platform having a hardware processor and a system memory storing a software code, the method comprising: detecting, by the software code executed by the hardware processor, a pixel anomaly in an image; obtaining, by the software code executed by the hardware processor, a salience criterion for the image; after detecting the pixel anomaly, classifying, by the software code executed by the hardware processor, the pixel anomaly as one of a salient anomaly or an innocuous anomaly based on the salience criterion for the image; disregarding the pixel anomaly, by the software code executed by the hardware processor, when the pixel anomaly is classified as the innocuous anomaly; and flagging the pixel anomaly, by the software code executed by the hardware processor, when the pixel anomaly is classified as the salient anomaly. || 17. A method for use by a system including a computing platform having a hardware processor and a system memory storing a software code providing a graphical user interface (GUI), the method comprising: detecting, by the software code executed by the hardware processor, a pixel anomaly in a first video segment of a plurality of video segments; displaying, by the software code executed by the hardware processor, via the GUI, at least one video frame in the first video segment when analyzing the first video segment detects the pixel anomaly in the first video segment; receiving, by the software code executed by the hardware processor, via the GUI, a salience criterion for the first video segment; after detecting the pixel anomaly, classifying, by the software code executed by the hardware processor, the pixel anomaly as one of a salient anomaly or an innocuous anomaly based on the salience criterion received for the first video segment; and disregarding the pixel anomaly, by the software code executed by the hardware processor, when the pixel anomaly is classified as the innocuous anomaly; flagging the pixel anomaly, by the software code executed by the hardware processor, when the pixel anomaly is classified as the salient anomaly.