Image Processing with Spiking Neuron Networks

Meftah, Boudjelal; Lézoray, Olivier; Chaturvedi, Soni; Khurshid, A.A.; Benyettou, Abdelkader

doi:10.1007/978-3-642-29694-9_20

Cited by 19 publications

(12 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To begin, picture of a minute cell is portioned with spiking neural system. Once the division done, the recording process will take place as it will record the movement of every yield neuron which gives every info pixel a yield twofold 1 if the neuron is dynamic or 0 if the neuron is idle [1]. The after effect of two fold networks actuation of yield neurons can be spoken by pairing the pictures containing the edges recognized by these neurons for each of their classes.…”

Section: Snn Architecture For Edge Detectionmentioning

confidence: 99%

“…Artificial neural networks it"s all about understanding the early computations that take place in the dense networks connected neurons cell in central nervous system of human being. Originally, in 1943, McCulloch and Pitts proposed a model in view of improved double neurons, where a solitary neuron actualizes a basic thresholding function, a neuron's state is either dynamic or not dynamic, and this is controlled by ascertaining the weighted entirety of the conditions of neurons it is associated with [1]. Spiking neural system (SNN) which is named the third era of neural system had extremely well structures, suited for complex data handling.…”

Section: Introductionmentioning

confidence: 99%

“…Creatures demonstrate an extraordinary simplicity as a team with element situations, raising enthusiasm for the utilization of simulated neural systems in undertakings that arrangement with real-world interaction. Throughout the years, three generation of simulated neural systems have been proposed, each generation naturally more reasonable and computationally more powerful [1]. Spiking neural systems utilize the component of time in conveying by conveying singular heartbeats.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Guide Sign Analysis of Traffic Sign Data-Set Using Supervised Spiking Neuron Technique

Ali¹,

Karis²,

Ali³

et al. 2018

IJET

View full text Add to dashboard Cite

In this paper, 20 guided traffic signs mostly displayed around Malacca area were selected as project databased. Early hypothesis was made as the error for each usable image will increased as more interference introduced to the original image used. Three types of conditions which are hidden region, image brightness and image rotation were selected as an experiment to analyze the performance of each sign used. Each condition will perform a specific error to generate their mean value and in the same, image recognition will take place in the matchup process. By focusing on the result, it produces hidden region critically ascending mean error value at 62.5% = 0.07 and has average value at others points. For image brightness effect, it shows a higher mean error value collected at less brightness points and non-stable pattern at 10% to 60% brightness. As for rotation upshot, the values show a critically ascending for error value at 22.5% and slightly increase at 2% to 5% rotation point. For the recognition process, at 6.25% hidden region, almost 70% of images are correctly matched to its own classes while at 62.5% hidden region only 40% of images are correctly matched to its own classes and leaving 2 images to outperform. For -40% brightness, 45% of images are correctly matched to its own classes while at 60% brightness 65% of images are correctly matched to its own classes and leaving 1 image to outperform. Lastly, at 2.5 degree rotation, 85% of images are correctly matched to its own classes while at 25° rotation, 45% of images are correctly matched to its own classes and leaving 2 images to outperform. Finally, the error forms will affect the final output response of the detected traffic signs used.

show abstract

Section: Snn Architecture For Edge Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Guide Sign Analysis of Traffic Sign Data-Set Using Supervised Spiking Neuron Technique

Ali¹,

Karis²,

Ali³

et al. 2018

IJET

View full text Add to dashboard Cite

show abstract

“…The current lack of technology for neuromorphic sensing in robotics (IMU, sonar, radar, Lidar, etc.) can be tackled in a quite efficient way by means of spike coding algorithms [15], [16], [17], which allow to convert traditional sensors data into a stream of spikes, that is, a series of events determined by their timestamp and their polarity (+1 or −1). Although the overall performances will be hampered by the sensors' sampling frequency, it is worth noting that spike encoding, and decoding algorithms offer the opportunity to investigate novel neuromorphic algorithms while benefiting from standard off-the-shelf sensors.…”

Section: Introductionmentioning

confidence: 99%

A toolbox for neuromorphic sensing in robotics

Dupeyroux,

Stroobants,

de Croon

2021

Preprint

View full text Add to dashboard Cite

The third generation of artificial intelligence (AI) introduced by neuromorphic computing is revolutionizing the way robots and autonomous systems can sense the world, process the information, and interact with their environment. The promises of high flexibility, energy efficiency, and robustness of neuromorphic systems is widely supported by software tools for simulating spiking neural networks, and hardware integration (neuromorphic processors). Yet, while efforts have been made on neuromorphic vision (event-based cameras), it is worth noting that most of the sensors available for robotics remain inherently incompatible with neuromorphic computing, where information is encoded into spikes. To facilitate the use of traditional sensors, we need to convert the output signals into streams of spikes, i.e., a series of events (+1, −1) along with their corresponding timestamps. In this paper, we propose a review of the coding algorithms from a robotics perspective and further supported by a benchmark to assess their performance. We also introduce a ROS (Robot Operating System) toolbox to encode and decode input signals coming from any type of sensor available on a robot. This initiative is meant to stimulate and facilitate robotic integration of neuromorphic AI, with the opportunity to adapt traditional off-the-shelf sensors to spiking neural nets within one of the most powerful robotic tools, ROS.

show abstract

“…In [21] a hierarchical SNN is used for a visual attention system and in [30] for a categorisation system. In [31] image clustering, segmentation and edge detection applications and moving object recognition and EEG data recognition in [32]. A Spiking Deep Belief network is used for visual classification of handwritten digits in [33] and human gesture recognition for robot partners by SNN is investigated in [34].…”

Section: Introductionmentioning

confidence: 99%

Biologically Inspired Intensity and Depth Image Edge Extraction

Kerr

Coleman

McGinnity

2018

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

In recent years, artificial vision research has moved from focusing on the use of only intensity images to include using depth images, or RGB-D combinations due to the recent development of low-cost depth cameras. However, depth images require a lot of storage and processing requirements. In addition, it is challenging to extract relevant features from depth images in real time. Researchers have sought inspiration from biology in order to overcome these challenges resulting in biologically inspired feature extraction methods. By taking inspiration from nature, it may be possible to reduce redundancy, extract relevant features, and process an image efficiently by emulating biological visual processes. In this paper, we present a depth and intensity image feature extraction approach that has been inspired by biological vision systems. Through the use of biologically inspired spiking neural networks, we emulate functional computational aspects of biological visual systems. The results demonstrate that the proposed bioinspired artificial vision system has increased performance over existing computer vision feature extraction approaches.

show abstract

Image Processing with Spiking Neuron Networks

Cited by 19 publications

References 35 publications

Guide Sign Analysis of Traffic Sign Data-Set Using Supervised Spiking Neuron Technique

Guide Sign Analysis of Traffic Sign Data-Set Using Supervised Spiking Neuron Technique

A toolbox for neuromorphic sensing in robotics

Biologically Inspired Intensity and Depth Image Edge Extraction

Contact Info

Product

Resources

About