Adaptive illumination through spatial modulation of light intensity and image inversion

Castellini, Paolo; Cecchini, S.; Stroppa, L.; Paone, Nicola

doi:10.1088/0957-0233/24/5/055401

Cited by 5 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [16] we proposed to use a digital light projector (DLP) to realize a fully controllable illumination, not only in terms of intensity and color, but in terms of spatial distribution, so that it is possible to illuminate with different color or intensity each portion of the scene, using an 'image inversion' technique.…”

Section: Control Of Spatial Light Distributionmentioning

confidence: 99%

Optimization of spatial light distribution through genetic algorithms for vision systems applied to quality control

Castellini¹,

Cecchini²,

Stroppa³

et al. 2015

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

The paper presents an adaptive illumination system for image quality enhancement in vision-based quality control systems. In particular, a spatial modulation of illumination intensity is proposed in order to improve image quality, thus compensating for different target scattering properties, local reflections and fluctuations of ambient light. The desired spatial modulation of illumination is obtained by a digital light projector, used to illuminate the scene with an arbitrary spatial distribution of light intensity, designed to improve feature extraction in the region of interest. The spatial distribution of illumination is optimized by running a genetic algorithm. An image quality estimator is used to close the feedback loop and to stop iterations once the desired image quality is reached. The technique proves particularly valuable for optimizing the spatial illumination distribution in the region of interest, with the remarkable capability of the genetic algorithm to adapt the light distribution to very different target reflectivity and ambient conditions. The final objective of the proposed technique is the improvement of the matching score in the recognition of parts through matching algorithms, hence of the diagnosis of machine vision-based quality inspections. The procedure has been validated both by a numerical model and by an experimental test, referring to a significant problem of quality control for the washing machine manufacturing industry: the recognition of a metallic clamp. Its applicability to other domains is also presented, specifically for the visual inspection of shoes with retro-reflective tape and T-shirts with paillettes.

show abstract

Section: Control Of Spatial Light Distributionmentioning

confidence: 99%

Optimization of spatial light distribution through genetic algorithms for vision systems applied to quality control

Castellini¹,

Cecchini²,

Stroppa³

et al. 2015

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The signal-to-noise ratio would be improved dramatically well before subsequent image processing. A similar approach has demonstrated considerable illumination distribution control ability over the reflecting surface [13]. In the proposed illumination system, a shrunken image of the reference image displayed on a LCD panel is projected onto a target surface as an initial structured illumination.…”

Section: Introductionmentioning

confidence: 99%

Approach of self-adaptive illumination for optical imaging systems

et al. 2014

View full text Add to dashboard Cite

An optical imaging signal is vulnerable to undesired features such as ambient light illumination and partial specular reflection from the target; the success of extracting target features from images depends largely on appropriate design of illumination. This paper presents an approach for self-adaptive illumination for optical imaging systems. The proposed illumination system projects a reference image to a target surface as an initial structured illumination, and then adjusts the projected image automatically to compensate the negative influences of undesired features. After this self-adaptive control process, undesired features would appear mostly invisible in the captured images. The signal-to-noise ratio would be improved dramatically well before subsequent image processing. In the validation experiments, several images with uniform brightness were offered as reference images; the captured images could achieve high brightness uniformity, even when the target surface was uneven or was illuminated by ambient light. In a further experiment of selective vessel illumination on a human palm, simulated vessel regions were selectively illuminated. Undesired features, like palm prints, almost disappeared in the images captured.

show abstract