A fuzzy set approach to Retinex spray sampling

Gianini, G.; Rizzi, Alessandro

doi:10.1007/s11042-017-4877-5

Cited by 12 publications

(6 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…it process colors based on their positions and combines these information by a specific equation aggregator. As for the spatial exploration, some use random walk processes [28], or their probabilistic representation [13], and some others use point sampling processes [29], [30] or their probabilistic representation [31]- [34]), while the aggregation can involve various kinds of averaging of the local intensity maxima.…”

Section: Related Work a The Retinex Algorithm Familymentioning

confidence: 99%

“…Finally, Tanaka et al [39] produced two variants of RSR by concentrating on the region of interest (ROI): the first variant proposed a cone distribution based on anatomical data as a ROI, while the second variant focuses on the visual field information's visual resolution and considers it an ROI. Among the most efficient and fastest implementations of RSR is FuzzyRSR [29], which exploits the same spray for the correction of several pixels.…”

Section: Related Work a The Retinex Algorithm Familymentioning

confidence: 99%

See 1 more Smart Citation

An Efficient In-Memory Computing Architecture for Image Enhancement in AI Applications

et al. 2022

Self Cite

View full text Add to dashboard Cite

Random Spray Retinex (RSR) is an effective image enhancement algorithm due to its effectiveness in improving image quality. However, the algorithm computing complexity and the required hardware resources and memory accesses hampered its deployment in many applications scenarios, for instance in IoT systems with limited hardware resources. With the rise of Artificial Intelligence (AI), the use of image enhancement has become essential to improve the performance for many emerging applications. In this paper, we propose the use of the RSR as a pre-processing filter before the task of semantic segmentation of low-quality urban road scenes. Using the publicly available Cityscapes dataset, we compare the performance of a pre-trained deep semantic segmentation network on dark noisy images and on RSR pre-processed images. Our findings confirm the effectiveness of RSR in improving segmentation accuracy. In addition, to address the computation complexity and suitability to edge devices, we propose a novel efficient implementation of the RSR using resistive random access memory (RRAM) technology. The architecture provides highly parallel analog in-memory computing (IMC) capabilities. A detailed, efficient and low latency implementation of the RSR using RRAM-CMOS technology is described. The design is verified using SPICE simulations with measured data from fabricated RRAM and 65nm CMOS technologies. The approach provided here represents an important step towards low-complexity and realtime hardware-friendly architecture and design for Retinex algorithms for edge devices.

show abstract

Section: Related Work a The Retinex Algorithm Familymentioning

confidence: 99%

Section: Related Work a The Retinex Algorithm Familymentioning

confidence: 99%

An Efficient In-Memory Computing Architecture for Image Enhancement in AI Applications

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The number n of points in the spray and the number N of sprays are parameters that can be tuned to reduce as much as possible statistical noise. A version of this algorithm based on fuzzy set theory was also created to further reduce the computational cost [7].…”

Section: Random Spray Retinex (Rsr)mentioning

confidence: 99%

Gradient attenuation as an emergent property of reset-based Retinex models

Gianini

Mio

Fossi

et al. 2019

Proceedings of the 11th International Conference on Management of Digital EcoSystems

Self Cite

View full text Add to dashboard Cite

The Retinex image ltering algorithms have been inspired by experimental ndings on the behavior of the Human Vision System. They are known to locally adjust image color and contrast by preserving edges and attenuating gradients. In a reference formulation of the algorithm by Land and McCann, edge preservation and gradient attenuation are granted by two ad-hoc mechanisms: called respectively reset (the distinctive feature of all the Retinex algorithms) and thresholding. A somehow unanticipated nding is that gradient attenuation is also observed with algorithm variants that do not include the latter mechanism, which was explicitly devised to implement gradient attenuation. In this work, we provide an analytic demonstration of the capability of Retinex models to attenuate gradients using only the "reset" mechanism, combined with the local character of the mutual pixel in uences. We show that this capability is an emergent property of all the reset-based Retinex models. CCS CONCEPTS • Applied computing → Imaging.

show abstract

“…The main characteristic of Retinex models is the spatial recomputation of each pixel value performed with a series of ratio operation in luminous intensity difference across the image. This idea of exploring the image content through paths is a common feature for many Retinex implementations (not all) and has been modeling studies [7,[13][14][15][16][17][18][19].…”

Section: Introductionmentioning

confidence: 99%

Random Spray Retinex Extensions Considering Region of Interest and Eye Movements

Tanaka¹,

Lanaro²,

Horiuchi³

et al. 2019

jist

Self Cite

View full text Add to dashboard Cite

The Random spray Retinex (RSR) algorithm was developed by taking into consideration the mathematical description of Milano-Retinex. The RSR substituted random paths with random sprays. Mimicking some characteristics of the human visual system (HVS), this article proposes two variants of RSR adding a mechanism of region of interest (ROI). In the first proposed model, a cone distribution based on anatomical data is considered as ROI. In the second model, the visual resolution depending on the visual field based on the knowledge of visual information processing is considered as ROI. We have measured actual eye movements using an eye-tracking system. By using the eye-tracking data, we have simulated the HVS using test images. Results show an interesting qualitative computation of the appearance of the processed area around real gaze points.

show abstract

A fuzzy set approach to Retinex spray sampling

Cited by 12 publications

References 46 publications

An Efficient In-Memory Computing Architecture for Image Enhancement in AI Applications

An Efficient In-Memory Computing Architecture for Image Enhancement in AI Applications

Gradient attenuation as an emergent property of reset-based Retinex models

Random Spray Retinex Extensions Considering Region of Interest and Eye Movements

Contact Info

Product

Resources

About