Edge Image Processing for Accurate PII Blurring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current image processing methods, particularly in online mapping services, fail to adequately protect personal identifiable information (PII) due to potential data breaches in cloud storage and incorrect blurring of non-PII regions, risking unauthorized access and misidentification.
Innovation Solution
A device and method that includes an image capturing module, memory, communication interface, and processor to detect and blur PII regions, store images temporarily in encrypted format, and transmit processed images to remote storage after approval, using EDGE computing to manage image capture and processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the image is stored in the cloud without blurring, then the image can be accessed and processed, but the personal identifiable information can be accessed in case of data breach
Solution Approach 1:
The patent applies preliminary action by blurring the PII regions in the image before storing it in the cloud. The processing device detects PII regions and generates a blurred version of the image in advance, so that even if a data breach occurs, the sensitive information remains protected. This pre-processing step ensures that the harmful effect of potential data breaches is mitigated before the image is stored.
2Reliability
If the current blurring algorithm is used, then the PII regions can be blurred, but the non-personal identifiable information may be wrongly blurred
Solution Approach 1:
The patent implements feedback by receiving notification information from the third party about wrongly blurred regions, and using this feedback to correct the blurring. When the processor receives notification that a region was wrongly blurred, it generates corrected notification information and uses this feedback to improve future blurring operations, ensuring that only actual PII regions are blurred in subsequent processing.
Solution Approach 2:
The system applies self-service by having the third party automatically provide notification information about wrongly blurred regions, and the processor automatically uses this information to correct future blurring operations without requiring manual intervention. The system self-corrects its errors through automated feedback loops.
3Productivity
If the first image is stored in the memory for a predetermined time, then the image can be processed and transmitted, but the unblurred image may be accessed by unauthorized parties
Solution Approach 1:
The patent applies the taking out principle by extracting the PII regions from the original image and separating them into blurred versions. The processing device creates a blurred image where the PII regions are obscured, and this blurred version is what is transmitted to the cloud. The original unblurred image remains only in temporary memory and is deleted after processing, preventing unauthorized access to sensitive data.
Solution Approach 2:
The system applies preliminary action by blurring the PII regions before the image is transmitted to the cloud. This pre-processing ensures that even though the unblurred image is temporarily stored in memory for processing, the sensitive information is already protected in the version that will be stored long-term in the cloud.
4Reliability
If the image is processed and transmitted to remote storage, then the PII can be protected, but the processing time and storage requirements increase
Solution Approach 1:
The patent applies segmentation by dividing the image processing task into separate operations: detecting PII regions, generating blurred versions of specific regions, and transmitting only the blurred image to the cloud. This segmentation allows the system to process only the necessary portions of the image (the PII regions) rather than the entire image, reducing processing time and storage requirements while maintaining protection.
Data Source
AI summary
According to various embodiments, there is a device comprising: an image capturing module configured to obtain a first image capturing an external environment; a memory configured to store data; a communication interface arranged in data communication with a remote data storage; and a processor communicatively couplable with the image capturing module, the memory, and the communication interface, and configured to: detect one or more regions of the first image, wherein the one or more regions include one or more objects of a predetermined type, and generate a second image corresponding to the first image, by blurring one or more regions of the second image each corresponding to the one or more regions of the first image, wherein the processor is further configured to store the first image in the memory for a predetermined time, and transmit the second image to the remote data storage via the communication interface.