Event-Based Vision Sensor Object Recognition via ROI Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current identity verification methods using authentication information and equipment are prone to identity theft and inconvenient for users, while human attribute-based verification methods consume more energy and require complex manipulations.
Innovation Solution
An object recognition method utilizing an event-based vision sensor to generate images, extract region of interest (ROI) images, and process them through multiple-input convolutional neural networks to recognize objects with low energy consumption and simple user interactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If human attribute-based verification is used, then security against identity theft is improved, but energy consumption increases
Solution Approach 1:
The patent divides the face image into multiple regions of interest (ROIs) such as left eye, right eye, nose, mouth, and chin. Each ROI is processed independently by dedicated recognizers, allowing the system to focus computational resources only on relevant facial features for verification, thereby reducing overall energy consumption while maintaining security
Solution Approach 2:
The system processes only the necessary portions of the facial image (ROIs) rather than the entire face image. By selecting and processing only relevant regions, the patent reduces computational load and energy consumption while still achieving accurate identity verification
2Reliability
If human attribute-based verification is used, then security against identity theft is improved, but operation complexity increases
Solution Approach 1:
The system automatically captures facial images and performs verification without requiring user intervention. The device autonomously processes the facial recognition task, eliminating the need for users to manually input information or perform complex operations, thus simplifying usage while maintaining high security
3Ease of operation
If authentication information methods are used, then ease of operation is improved, but security against identity theft deteriorates
Solution Approach 1:
The patent replaces traditional mechanical authentication methods (keys, ID cards, passwords) with biometric authentication using facial recognition. The system captures facial images and automatically verifies identity through pattern matching, eliminating the need for users to manually input information while providing enhanced security that is difficult to steal or replicate
Data Source
AI summary
An object recognition apparatus and an object recognition method are provided. The object recognition method includes generating an input image based on an event flow of an object, generating a composite feature based on features extracted by a plurality of recognizers, and recognizing the object based on the composite feature.