Low-exposure image frame generation algorithms for feature extraction and classification

Vemuru, Krishnamurthy V.; Clark, Jeffrey

doi:10.1117/12.2518243

Cited by 1 publication

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also find that the shape of the objects is more distinctive and recognizable in the SNN edge map than in the other two edge maps. In order to test the potential of our SNN edge detector for applications in neuromorphic computing, especially processors such as IBM-TrueNorth, we first simulated low-exposure image frames with exposure times in the range of 1 to 50 ms using a Non-linear Subtraction Range (NSR) low-exposure frame generation algorithm [24]. Then, we generated the SNN edges of the low exposure frames.…”

Section: Comparison Of Snn Edges With Sobel and Canny Edge Detectorsmentioning

confidence: 99%

“…Object classification using deep learning from a series of 1 ms image frames captured with a camera is an interesting area of research for on-board signal processing and surveillance applications. In this context, we investigated the potential use of the SNN edge detector as a feature extraction layer in a CNN for object classification from low exposure image frames, each frame with an exposure time of 1 ms, simulated by the Non-linear Subtraction Range (NSR) algorithm [24]. The NSR algorithm is used to create low exposure frames with an assumed exposure time T of 40 ms for the Digits dataset, which is available in MATLAB [26].…”

Section: Edge Based Classification Of Digits Using a Convolutional Nementioning

confidence: 99%

See 1 more Smart Citation

Image Edge Detector with Gabor Type Filters Using a Spiking Neural Network of Biologically Inspired Neurons

Vemuru

2020

Algorithms

View full text Add to dashboard Cite

We report the design of a Spiking Neural Network (SNN) edge detector with biologically inspired neurons that has a conceptual similarity with both Hodgkin-Huxley (HH) model neurons and Leaky Integrate-and-Fire (LIF) neurons. The computation of the membrane potential, which is used to determine the occurrence or absence of spike events, at each time step, is carried out by using the analytical solution to a simplified version of the HH neuron model. We find that the SNN based edge detector detects more edge pixels in images than those obtained by a Sobel edge detector. We designed a pipeline for image classification with a low-exposure frame simulation layer, SNN edge detection layers as pre-processing layers and a Convolutional Neural Network (CNN) as a classification module. We tested this pipeline for the task of classification with the Digits dataset, which is available in MATLAB. We find that the SNN based edge detection layer increases the image classification accuracy at lower exposure times, that is, for 1 < t < T /4, where t is the number of milliseconds in a simulated exposure frame and T is the total exposure time, with reference to a Sobel edge or Canny edge detection layer in the pipeline. These results pave the way for developing novel cognitive neuromorphic computing architectures for millisecond timescale detection and object classification applications using event or spike cameras.

show abstract

Section: Comparison Of Snn Edges With Sobel and Canny Edge Detectorsmentioning

confidence: 99%

Section: Edge Based Classification Of Digits Using a Convolutional Nementioning

confidence: 99%

Image Edge Detector with Gabor Type Filters Using a Spiking Neural Network of Biologically Inspired Neurons

Vemuru

2020

Algorithms

View full text Add to dashboard Cite

show abstract

Low-exposure image frame generation algorithms for feature extraction and classification

Cited by 1 publication

References 12 publications

Image Edge Detector with Gabor Type Filters Using a Spiking Neural Network of Biologically Inspired Neurons

Image Edge Detector with Gabor Type Filters Using a Spiking Neural Network of Biologically Inspired Neurons

Contact Info

Product

Resources

About