Object Recognition via Multi-Image Feature Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object recognition systems face challenges in accurately identifying objects in images, especially when objects are moving or have unstructured features due to variations in photography conditions such as location and time.
Innovation Solution
The method involves extracting first feature information from multiple images using a pre-generated learning network model, combining this information to generate second feature information representing correlations between images, and using a pre-generated learning network model to recognize objects based on the combined features, even when objects are moving or have unstructured features.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If object recognition is performed on single images with unstructured features, then processing speed is maintained, but recognition accuracy deteriorates due to variations in photography conditions
Solution Approach 1:
The patent combines feature information from multiple images to generate comprehensive feature data for object recognition. By merging features across multiple images, the system overcomes the limitations of single-image recognition and handles unstructured features more effectively, thereby improving recognition accuracy despite increased processing complexity
Solution Approach 2:
The patent transitions from two-dimensional single image analysis to multi-dimensional feature space by incorporating temporal and spatial relationships across multiple images. This dimensional expansion allows the system to capture object characteristics more comprehensively, improving recognition accuracy while managing complexity through structured feature combination
2Measurement precision
If multiple images are processed to extract feature information, then recognition accuracy improves, but processing time increases
Solution Approach 1:
The patent performs preliminary feature extraction on multiple images before the actual recognition process. By pre-processing and extracting key features in advance, the system reduces the computational burden during real-time recognition, thereby improving accuracy while minimizing processing time loss
Solution Approach 2:
The patent extracts only the most relevant feature information from multiple images rather than processing all image data. This selective extraction of critical features maintains high recognition accuracy while significantly reducing processing time by eliminating redundant computations
Data Source
AI summary
The present disclosure relates to an artificial intelligence (AI) system for simulating functions of a human brain such as cognition and decision-making by using machine learning algorithms such as deep learning, and applications thereof. In particular, the present disclosure provides a method of recognizing an object by using an AI system and its application, including: extracting pieces of first feature information respectively regarding a plurality of images, each image including an object; generating at least one piece of second feature information representing a correlation between the plurality of images by combining together the extracted pieces of first feature information respectively regarding the plurality of images; and recognizing, based on the at least one piece of second feature information, the object included in each of the plurality of images by using a pre-generated learning network model.