Finger Detection Using PCA Eigenspace Projection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing systems face challenges in accurately detecting and recognizing fingers in images, often misidentifying objects due to the brightness-based approach, which can lead to inefficiencies in human-computer interaction.
Innovation Solution
The system employs Principal Component Analysis (PCA) to reduce image dimensionality by projecting training images into an eigenspace, creating a geometric model that allows for accurate detection and tracking of fingers by comparing image points to a cloud of training points, using infrared illumination and eigenvectors to distinguish fingers from other objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If brightness-based object perception is used, then the system can quickly identify objects in images, but it misidentifies non-finger objects as fingers
Solution Approach 1:
The patent segments the object recognition process into multiple stages: initial brightness-based detection to locate potential objects, followed by PCA-based analysis to verify if the object is a finger. This segmentation allows the system to quickly filter candidates while maintaining high accuracy through subsequent verification steps.
Solution Approach 2:
The patent introduces PCA eigenspace analysis as an intermediary step between brightness-based detection and final finger identification. This intermediary process projects image data into a reduced-dimensional space where finger characteristics can be accurately distinguished from other objects, resolving the contradiction between speed and accuracy.
2Productivity
If PCA dimensionality reduction is applied to all images, then processing efficiency improves, but computational complexity increases during the training phase
Solution Approach 1:
The patent performs PCA dimensionality reduction and creates the eigenspace model during a preliminary training phase using only finger images. This pre-computed model is then reused during actual finger detection, allowing efficient processing of test images without repeating the complex eigenspace construction, thus resolving the contradiction between processing efficiency and computational complexity.
Solution Approach 2:
The patent transforms the image data from high-dimensional pixel space to a lower-dimensional eigenspace representation, changing the parameter space from thousands of pixels to a small number of principal components. This parameter transformation maintains essential finger characteristics while dramatically reducing processing requirements for detection.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances the accuracy and efficiency of finger detection, enabling more natural human-computer interaction by accurately identifying fingers and excluding non-finger objects, thus improving processing power and interaction speed.
Implementation Method 1
A camera and an infrared (IR) illuminator are placed behind the surface or screen. A finger touching or moving near the surface or screen reflects some of the IR radiation projected by the IR illuminator.
Data Source
AI summary
According to one disclosed method, coordinates in a multi-dimensional space are determined for an image point characterizing a particular object. An equation describing a model in the multi-dimensional space is provided. The model is characteristic of a set of training images of one or more other objects. The coordinates are applied to the equation to determine a distance between the image point and the model. Based on the determined distance, a determination is made as to whether the particular object matches the one or more other objects.A set of training images may be received. A multi-dimensional space (e.g., eigenspace) may be determined based on the set of training images. A set of training points may be generated by projecting the set of training images into the multi-dimensional space. An equation describing a model in the multi-dimensional space that is characteristic of the set of training points may be determined.