Single Pixel Image Classification using an Ultrafast Digital Light Projector

2026-03-12

AI Summary

This work proposes a single-pixel image classification method that bypasses conventional image reconstruction to address the latency and complexity inherent in traditional imaging approaches under high-speed scenarios. By integrating single-pixel imaging (SPI) with micro-LED-on-CMOS ultrafast digital light projection, the system achieves sub-millisecond image encoding. Classification is performed directly from temporal measurement signals using extreme learning machines (ELMs) combined with lightweight deep neural networks. Evaluated on the MNIST handwritten digit dataset, the system demonstrates highly accurate and efficient classification at multi-kilohertz frame rates, confirming the feasibility and advantages of the proposed approach for real-time applications such as ultrafast anomaly detection.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Multi-modal Vision
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Pattern recognition and image classification are essential tasks in machine vision. Autonomous vehicles, for example, require being able to collect the complex information contained in a changing environment and classify it in real time. Here, we experimentally demonstrate image classification at multi-kHz frame rates combining the technique of single pixel imaging (SPI) with a low complexity machine learning model. The use of a microLED-on-CMOS digital light projector for SPI enables ultrafast pattern generation for sub-ms image encoding. We investigate the classification accuracy of our experimental system against the broadly accepted benchmarking task of the MNIST digits classification. We compare the classification performance of two machine learning models: An extreme learning machine (ELM) and a backpropagation trained deep neural network. The complexity of both models is kept low so the overhead added to the inference time is comparable to the image generation time. Crucially, our single pixel image classification approach is based on a spatiotemporal transformation of the information, entirely bypassing the need for image reconstruction. By exploring the performance of our SPI based ELM as binary classifier we demonstrate its potential for efficient anomaly detection in ultrafast imaging scenarios.

Problem

• single pixel imaging
• image classification
• ultrafast imaging
• real-time classification
• anomaly detection

Innovation

• single pixel imaging
• ultrafast digital light projector
• image classification without reconstruction
• extreme learning machine
• spatiotemporal transformation