Using Human Visual System modeling for bio-inspired low level image processing

Benoît, Alexandre; Caplier, Alice; Durette, Barthélémy; Hérault, Jeanny

doi:10.1016/j.cviu.2010.01.011

Cited by 85 publications

(41 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Indeed, we will rather focus on biomimetic sparse models as tools to shape future computer vision algorithms (Benoit et al, 2010;Serre and Poggio, 2010). In particular, we will not review models which mimic neural activity, but rather on algorithms which mimic their efficiency, bearing in mind the constraints that are linked to neural systems (no central clock, internal noise, parallel processing, metabolic cost, wiring length).…”

Section: Outline: Sparse Models For Computer Visionmentioning

confidence: 99%

Sparse Models for Computer Vision

Perrinet¹

2015

Biologically Inspired Computer Vision

View full text Add to dashboard Cite

show abstract

Section: Outline: Sparse Models For Computer Visionmentioning

confidence: 99%

Sparse Models for Computer Vision

Perrinet¹

2015

Biologically Inspired Computer Vision

View full text Add to dashboard Cite

show abstract

“…6. Figure 1 presents the global architecture of the adopted retina model [6] as a combination of low-level processing modules. Basically, it is a layered model with: (1) photoreceptors, where local contrast is enhanced; (2) outer plexiform layer (OPL), where the nonseparable spatio-temporal filtering removes spatio-temporal noise and enhances spatial high-frequency contours while reducing or removing the mean luminance; (3) inner plexiform layer (IPL), with two channels: the parvocellular (Parvo) channel, dedicated to spatial analysis enhancing static contours contrast, and the magnocellular (Magno) channel that enhances moving contours and removes static ones.…”

Section: Introductionmentioning

confidence: 99%

“…This paper proposes a new scheme to address the problem of unsupervised segmentation of moving objects, which exploits the fusion of information obtained from two inherently different approaches: a bio-inspired motion detection method, using low-level information from the modeling of the human visual system, and a BS algorithm based on pixel color information. The biologically inspired model of the human retina presented in [6] has been adopted for the former. Experiments were performed with several BS algorithms showing that our method consistently improves the results, particularly in complex situations, where the BS algorithms critically fail.…”

Section: Introductionmentioning

confidence: 99%

Bio-inspired Boosting for Moving Objects Segmentation

Martins

Carvalho

Côrte-Real

et al. 2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Developing robust and universal methods for unsupervised segmentation of moving objects in video sequences has proved to be a hard and challenging task. State-of-the-art methods show good performance in a wide range of situations, but systematically fail when facing more challenging scenarios. Lately, a number of image processing modules inspired in biological models of the human visual system have been explored in different areas of application. This paper proposes a bio-inspired boosting method to address the problem of unsupervised segmentation of moving objects in video that shows the ability to overcome some of the limitations of widely used state-of-the-art methods. An exhaustive set of experiments was conducted and a detailed analysis of the results, using different metrics, revealed that this boosting is more significant when challenging scenarios are faced and state-of-the-art methods tend to fail.

show abstract

“…It should be noted that the clipped part of each histogram is not discarded and, instead, it is redistributed among the bins that their values do not exceed the clipping threshold. • Retinex: Inspired from the Human Visual System (HVS); particularly, the retina that is a preprocessing step to condition the visual data for facilitated high level analysis, and V1 cortex area which is a low-level visual information describer [15]. The two well-known channels of the retina's output are Parvocellular channel (Parvo) that is dedicated to detail extraction and Magnocellular (Magno) for motion information extraction.…”

Section: Photometric Correctionmentioning

confidence: 99%

Real-time embedded age and gender classification in unconstrained video

Azarmehr

Laganière

Lee

et al. 2015

2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Recently, automatic demographic classification has found its way into embedded applications such as targeted advertising in mobile devices, and in-car warning systems for elderly drivers. In this thesis, we present a complete framework for video-based gender classification and age estimation which can perform accurately on embedded systems in real-time and under unconstrained conditions. We propose a segmental dimensionality reduction technique utilizing Enhanced Discriminant Analysis (EDA) to minimize the memory and computational requirements, and enable the implementation of these classifiers for resource-limited embedded systems which otherwise is not achievable using existing resource-intensive approaches. On a multi-resolution feature vector we have achieved up to 99.5% compression ratio for training data storage, and a maximum performance of 20 frames per second on an embedded Android platform.Also, we introduce several novel improvements such as face alignment using the nose, and an illumination normalization method for unconstrained environments using bilateral filtering. These improvements could help to suppress the textural noise, normalize the skin color, and rectify the face localization errors. A non-linear Support Vector Machine (SVM) classifier along with a discriminative demography-based classification strategy is exploited to improve both accuracy and performance of classification. We have performed several cross-database evaluations on different controlled and uncontrolled databases to assess the generalization capability of the classifiers. Our experiments demonstrated competitive accuracies compared to the resource-demanding state-of-the-art approaches.ii Acknowledgements I would like to take the opportunity to appreciate my supervisors, Prof. Robert Laganière, for his invaluable guidance, encouragement, and persistent support throughout the project and, Prof. WonSook Lee, for providing me with all the necessary facilities for research, and sharing expertise.

show abstract

Using Human Visual System modeling for bio-inspired low level image processing

Cited by 85 publications

References 42 publications

Sparse Models for Computer Vision

Sparse Models for Computer Vision

Bio-inspired Boosting for Moving Objects Segmentation

Real-time embedded age and gender classification in unconstrained video

Contact Info

Product

Resources

About