Acquiring/Recognising Eyes TRIZ Cases

Optically replicated exit pupils spatially distribute light across multiple zones, expanding the eyebox volume without increasing device bulk.

UV and IR illumination creates opaque lens edges against the sclera for automated tracking without visible light discomfort.

An iris authentication device captures wide-angle overview images to determine eye orientation before processing detailed iris data for verification.

Integrated lens molding creates a sealed chamber around the IR LED, resolving manufacturing complexity and light focusing issues.

Displayed enrollment images guide users to align biometric features, reducing computational burden and improving alignment accuracy.

Face image analysis identifies unsuitable users before iris data acquisition, preventing futile authentication attempts and reducing wasted processing time.

An eye movement-based system records fixation sequences on a dynamically rearranged character matrix to prevent static biometric replication.

Automated target search apparatus extracts object regions and calculates image feature amounts for precise identification.

An AI director analyzes non-verbal cues to calculate a meeting health index and provide moderation recommendations.

Local density analysis of coherent bits reduces negative errors in iris identification without increasing computational complexity.

A head-mounted retina and iris scanner captures biometric images for identity verification on a mobile computing device.

Two-stage sharpness analysis filters low-quality iris images, reducing computational load while maintaining recognition accuracy.

Nonparametric thresholding segments iris images via grey scale histograms, resolving weak edge detection errors between the iris and sclera.

Segmenting red-eye detection into size-specific classifiers reduces false positives and computational load compared to single neural networks.

Environmental feature detectors analyze user context to distinguish live subjects from spoofing attempts.

Genetic programming embedded in adaptive boosting creates lightweight classifiers for real-time eye state detection.

A combined face and iris recognition system uses pan-tilt-zoom cameras to capture biometric data.

A reflection unit redirects light to image collection units for iris recognition.

A display device adjusts luminance using a pupil computing module to reduce blue light exposure while maintaining image color.

System skips redundant iris authentication for tracked objects, suppressing arithmetic operations and lowering computational load.

A user terminal acquires iris images and converts them to codes for recognition.

An optical coherence tomography method calculates attenuation parameters from signal intensity and depth to identify the iris edge.

A rearview mirror adjusting system uses image capture and light detection to automatically reposition the mirror, resolving manual adjustment bottlenecks.

Infrared scanning captures unique iris patterns to authenticate users on wearable heads-up displays without external capture devices.

Feature fusion and encryption resolve security speed trade-offs in biometric recognition.

Segmenting external and internal scanners resolves the contradiction between high security and system complexity by enabling tiered access control.

A camera selection module automatically switches between front and rear lenses based on user eye gaze direction.

An FCN-based iris recognition pipeline uses 8-bit dynamic fixed-point precision to reduce computational complexity.

Radial line analysis fits curves to candidate points along eyelid edges, resolving occlusion challenges in iris segmentation.

A clasp with integrated biometric sensor initiates the boot process upon touch.

A display system aggregates viewer counts from secondary units to direct primary monitor content.

A biometric system fuses periocular and facial features to enhance authentication accuracy.

A wide-angle image collector helps users locate the eye region on a display without alternating views.

A hybrid intelligent retrieval system combines machine detection models with human EEG classification to identify targets in mass video libraries.