Debiased Opto-electronic Joint Transform Correlator for Enhanced Real-Time Pattern Recognition
Opto-electronic joint transform correlators (OJTCs) use a focal plane array (FPA) to detect the joint power spectrum (JPS) of two input images, projecting it onto a spatial light modulator (SLM) to be optically Fourier transformed. The JPS is composed of two self-intensities and two conjugate-products, where only the latter produce the cross-correlation. However, the self-intensity terms are typically much stronger than the conjugate-products, producing a bias that consumes most of the available bit-depth on the FPA and SLM. Here we propose and demonstrate, through simulation and experiment, a debiased OJTC (DOJTC) that electronically pre-processes the JPS to remove the self-intensity terms before sending it to the SLM, thereby enhancing the quality of the cross-correlation result. We show that under some conditions the DOJTC yields a nearly two orders of magnitude improvement in the signal-to-noise ratio compared to an OJTC.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Shift, Scale and Rotation Invariant Multiple Object Detection using Balanced Joint Transform Correlator
The Polar Mellin Transform (PMT) is a well-known technique that converts images into shift, scale and rotation invariant signatures for object detection using opto-electronic correlators. However, this technique cannot b…
object-detectionObject DetectionHigh-speed Opto-electronic Pre-processing of Polar Mellin Transform for Shift, Scale and Rotation Invariant Image Recognition at Record-Breaking Speeds
Space situational awareness demands efficient monitoring of terrestrial sites and celestial bodies, necessitating advanced target recognition systems. Current target recognition systems exhibit limited operational speed …
PhotoFourier: A Photonic Joint Transform Correlator-Based Neural Network Accelerator
The last few years have seen a lot of work to address the challenge of low-latency and high-throughput convolutional neural network inference. Integrated photonics has the potential to dramatically accelerate neural netw…
Direct Kernel Optimization: Efficient Design for Opto-Electronic Convolutional Neural Networks
Hybrid opto-electronic neural networks combine optical front-ends with electronic back-ends to perform vision tasks, but joint end-to-end (E2E) optimization of optical and electronic components is computationally expensi…
Monocular Depth EstimationDAD vision: opto-electronic co-designed computer vision with division adjoint method
The miniaturization and mobility of computer vision systems are limited by the heavy computational burden and the size of optical lenses. Here, we propose to use a ultra-thin diffractive optical element to implement pass…