Sensitive Picture Recognition Model for Automatic Privacy Protection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for protecting sensitive pictures on smartphones require manual user intervention to move and encrypt them, which is time-consuming and inefficient, and existing image recognition technologies lack accuracy in distinguishing sensitive content.
Innovation Solution
A method and device utilizing a convolutional neural network-based sensitive picture recognition model that automatically identifies sensitive pictures by training on a dataset of sensitive and non-sensitive images, applying a skin color model, and iteratively updating the model for improved classification accuracy, allowing for automatic storage in a private, encrypted album.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual moving and encryption of sensitive pictures is implemented, then privacy protection is achieved, but user time and effort are consumed
Solution Approach 1:
The system performs automatic sensitive picture recognition and classification without requiring user intervention. The neural network model autonomously identifies sensitive pictures and moves them to private albums, enabling the system to serve itself rather than requiring manual user operation.
Solution Approach 2:
The system proactively identifies and classifies sensitive pictures before any potential privacy breach can occur. By performing preliminary recognition and automatic movement to encrypted storage, the system prevents privacy issues before they arise, eliminating the need for subsequent manual intervention.
2Productivity
If existing image recognition technology is used, then picture classification is performed, but recognition accuracy for sensitive content is insufficient
Solution Approach 1:
The system transforms the image recognition problem into a different parameter space by converting images to grayscale and applying histogram equalization. These parameter changes enhance the contrast and visual differences between sensitive and non-sensitive pictures, thereby improving recognition accuracy while maintaining processing efficiency.
Solution Approach 2:
The recognition process is divided into distinct segments: grayscale conversion, histogram calculation, histogram equalization, and final classification. This segmentation allows each processing stage to be optimized independently, improving both accuracy and efficiency by breaking down the complex recognition task into manageable steps.
Data Source
AI summary
Method, device and computer-readable medium for sensitive picture recognition are provided in the disclosure. Aspects of the disclosure provide a method for sensitive picture recognition. The method includes receiving a picture to be processed from a picture library associated with a user account, applying a sensitive picture recognition model to the picture to determine whether the picture is a sensitive picture or not, and providing a privacy protection associated with the user account to the picture when the picture is the sensitive picture. In an example, the method includes storing the picture in a private album under the user account with access security protection.