Saliency Prioritization for Image Processing

Number: 20220198258
Published: 2022-06-23
Filed: 2020-12-21
Assignee: Disney Enterprises, Inc.
Inventors: Doggett; Erika Varis, Nguyen; David T., Tang; Binghao, Zhou; Hailing, Wolak; Anna M., Qi; Erick Keyu
CPC: G06N3/0455; G06F3/013; G06N3/09; G06N3/045; G06N3/08; G06N3/063; G06N3/0464
Verdict: Set aside generic image-saliency processing
Source: Google Patents · FreePatentsOnline

Abstract

According to one implementation, a system includes a computing platform having a hardware processor and a system memory storing a software code including a trained neural network (NN). The hardware processor executes the software code to receive an input image including a pixel anomaly, identify, using the trained NN, one or more salient regions of the input image, and determine whether the pixel anomaly is located inside any of the one or more salient regions. The hardware processor further executes the software code to assign a first priority to the pixel anomaly when it is determined that the pixel anomaly is located inside any of the one or more salient regions, and to assign a second priority, lower than the first priority, to the pixel anomaly when it is determined that the pixel anomaly is not located inside any of the one or more salient regions.

Background

BACKGROUND

Pixel errors in images occur with regularity but can be difficult and costly to correct. For example, pixel anomalies in video frames can be introduced by many different processes within a video production pipeline. A final quality procedure for correcting such errors is typically done before the video undergoes final release, and in the conventional art that process is usually performed by human inspectors. Due to its reliance on human participation, pixel error correction is expensive and time consuming. However, not all pixel anomalies require correction. For example, depending on its position within an image, for example with respect to a character or foreground object, as well as to regions within an image receiving high attention by observers, some pixel anomalies may be prioritized for correction, while others may reasonably be disregarded. That is to say, not all pixel errors are of equal importance. Accordingly, there is a need in the art for an automated solution for prioritizing the correction of pixel errors in an image. SUMMARY

There are provided systems and methods for performing saliency prioritization for image processing, substantially as shown in and described in connection with at least one of the figures, and as set forth more completely in the claims.

Claims

1. A system comprising: a hardware processor; and a system memory storing a soft are code including a trained neural network (NN); the hardware processor configured to execute the software code to: receive an input image including a pixel anomaly; identify, using the trained NN, one or more salient regions of the input image; determine whether the pixel anomaly is located inside any of the one or more salient regions of the input image; assign a first priority to the pixel anomaly when determined that the pixel anomaly is located inside any of the one or more salient regions of the input image; and assign a second priority, lower than the first priority, to the pixel anomaly when determined that the pixel anomaly is not located inside any of the one or more salient regions of the input image. || 11. A method for use by a system including a hardware processor and a system memory storing a software code including a trained neural network (NN), the method comprising: receiving, by the software code executed by the hardware processor, an input image including a pixel anomaly; identifying, by the software code executed by the hardware processor and using the trained NN, one or more salient regions of the input image; determining, by the software code executed by the hardware processor, whether the pixel anomaly is located inside any of the one or more salient regions of the input image; assigning a first priority to the anomalous pixel, by the software code executed by the hardware processor, when determined that the pixel anomaly is located inside any of the one or more salient regions of the input image; and assigning a second priority, lower than the first priority, to the anomalous pixel, by the software code executed by the hardware processor, when determined that the pixel anomaly is not located inside any of the one or more salient regions of the input image.