Visual Recognition via Scale-Invariant Feature Normalization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Computer vision systems face challenges in recognizing objects in unconstrained environments due to lack of invariance to object presentation, lighting, occlusion, and background, requiring significant computational power and prior knowledge, limiting their effectiveness in real-world applications.
Innovation Solution
The method involves extracting unique, scale-rotation-invariant points from images, normalizing icons to a fixed size, and comparing them for similarity, allowing for robust object recognition regardless of position, orientation, distance, and perspective, enabling the recognition of hundreds of objects quickly and learning millions of objects without limitations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If computer vision systems perform visual recognition in unconstrained environments, then recognition accuracy improves, but computational power requirements increase significantly
Solution Approach 1:
The patent segments the visual recognition process into distinct stages: feature extraction, normalization, indexing, and comparison. By dividing the complex recognition task into manageable segments, the system achieves accurate object recognition in unconstrained environments while reducing overall computational requirements through efficient processing at each stage.
Solution Approach 2:
The patent applies preliminary action by pre-processing images to extract features and normalize them before storage in an index. This preliminary processing transforms raw images into standardized representations, enabling rapid comparison and recognition without requiring intensive computational resources during the actual recognition phase.
2Adaptability or versatility
If computer vision systems are designed to recognize multiple object classes with high accuracy, then recognition capability improves, but system complexity increases
Solution Approach 1:
The patent implements universality through a standardized feature extraction and normalization framework that works across multiple object classes. The same processing pipeline handles diverse objects by extracting invariant features and normalizing them to a common representation, enabling the system to recognize various object types without requiring class-specific complex processing.
Solution Approach 2:
The patent applies parameter changes by transforming images through normalization operations that adjust scale, rotation, and other parameters to standard values. This parameter transformation enables the system to handle variable object presentations while maintaining consistent processing complexity across different object classes.
3Productivity
If visual recognition systems process images in real-time, then processing speed improves, but computational resources required increase
Solution Approach 1:
The patent performs preliminary feature extraction and normalization during image acquisition or preprocessing phases, preparing data in advance for rapid recognition. This preliminary action reduces the computational burden during real-time processing, enabling fast recognition with fewer resources during critical operations.
Solution Approach 2:
The patent creates simplified copies of objects through normalized feature representations and icons that capture essential characteristics without preserving all original image data. These compressed representations enable rapid comparison and recognition while significantly reducing the computational resources needed for processing.
Data Source
AI summary
A method for visual recognition of an object in an electronic image includes extracting unique points of an object to be learned and/or a target object. The unique points are obtained by cross-correlating the image with a structure. Generally, the structure and/or the size of the structure may vary to detect extremum information associated with the learned object and/or target object. An icon corresponding to each of the unique points is extracted. The size of the icon corresponds to the scale of the unique point. After extraction of the various icons, an object becomes a collection of icons. Each of these icons is un-rotated and normalized or resized to a constant size so it can be compared with other icons. One of the unique properties of these icons is their stability over scale and angle. Thus, this invention allows the recognition of an image(s) or object(s) from large number of trained images or objects very quickly.