Contour detection based on a non-classical receptive field model with butterfly-shaped inhibition subregions

Zeng, Chi; Li, Yongjie; Yang, Kai-Fu; Li, Chaoyi

doi:10.1016/j.neucom.2010.12.022

Cited by 32 publications

(25 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…8 clearly shows that the results with image-specific optimal parameters (red bars) are substantially better than that with the optimal parameter setting for the whole dataset (blue bars). More importantly, in both situations, the model of MCI shows obvious improvement over other models, except the models of butterfly-shaped inhibition [72] and adaptive inhibition [43] with optimal parameters for the whole dataset. The good performance of the models of butterfly-shaped inhibition and adaptive inhibition could be attributed to the dividing of the whole surrounding non-CRF into four subregions, which provides a more flexible way to adapt to local features.…”

Section: B Experiments On Rug40 Datasetmentioning

confidence: 95%

“…Fig. 8 illustrates more comparisons of our MCI operator with other recent biologically-inspired models, including Butterfly-shaped inhibition [72] and Adaptive inhibition [43]. For Butterfly-shaped inhibition, we selected the parameter Quantitative comparison of various models on the whole RuG40 dataset.…”

Section: B Experiments On Rug40 Datasetmentioning

confidence: 99%

“…Besides the models compared in Figs. 6 and 7, the existing models of Butterfly-shaped inhibition [72], Adaptive inhibition [43] are also compared here.…”

Section: B Experiments On Rug40 Datasetmentioning

confidence: 99%

“…as σ = 2.0, and other parameters were the same as those listed in Table I in [72]. For Adaptive inhibition, we also set the parameters as same as ref.…”

Section: B Experiments On Rug40 Datasetmentioning

confidence: 99%

See 3 more Smart Citations

Multifeature-Based Surround Inhibition Improves Contour Detection in Natural Images

Yang

2014

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

To effectively perform visual tasks like detecting contours, the visual system normally needs to integrate multiple visual features. Sufficient physiological studies have revealed that for a large number of neurons in the primary visual cortex (V1) of monkeys and cats, neuronal responses elicited by the stimuli placed within the classical receptive field (CRF) are substantially modulated, normally inhibited, when difference exists between the CRF and its surround, namely, non-CRF, for various local features. The exquisite sensitivity of V1 neurons to the center-surround stimulus configuration is thought to serve important perceptual functions, including contour detection. In this paper, we propose a biologically motivated model to improve the performance of perceptually salient contour detection. The main contribution is the multifeature-based center-surround framework, in which the surround inhibition weights of individual features, including orientation, luminance, and luminance contrast, are combined according to a scale-guided strategy, and the combined weights are then used to modulate the final surround inhibition of the neurons. The performance was compared with that of single-cue-based models and other existing methods (especially other biologically motivated ones). The results show that combining multiple cues can substantially improve the performance of contour detection compared with the models using single cue. In general, luminance and luminance contrast contribute much more than orientation to the specific task of contour extraction, at least in gray-scale natural images.

show abstract

Section: B Experiments On Rug40 Datasetmentioning

confidence: 95%

Section: B Experiments On Rug40 Datasetmentioning

confidence: 99%

“…Besides the models compared in Figs. 6 and 7, the existing models of Butterfly-shaped inhibition [72], Adaptive inhibition [43] are also compared here.…”

Section: B Experiments On Rug40 Datasetmentioning

confidence: 99%

“…as σ = 2.0, and other parameters were the same as those listed in Table I in [72]. For Adaptive inhibition, we also set the parameters as same as ref.…”

Section: B Experiments On Rug40 Datasetmentioning

confidence: 99%

See 2 more Smart Citations

Multifeature-Based Surround Inhibition Improves Contour Detection in Natural Images

Yang

2014

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Ernst et al [11] developed the theory for non-classical RF phenomena. Zeng et al [12] proposed a feasible contour detection method based on an improvedorientation-selective inhibition model. Wei et al [13] placed their emphasis on the investigations of non-classical RF and multi-scale integration to deal with the problem of contour detection.…”

Section: Introductionmentioning

confidence: 99%

Technique for image fusion based on NSST domain improved fast non-classical RF

Kong¹,

Liu²

2013

Infrared Physics & Technology

View full text Add to dashboard Cite

Brain-Inspired Algorithms for Processing of Visual Data

Strisciuglio

Petkov

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The study of the visual system of the brain has attracted the attention and interest of many neuro-scientists, that derived computational models of some types of neuron that compose it. These findings inspired researchers in image processing and computer vision to deploy such models to solve problems of visual data processing.In this paper, we review approaches for image processing and computer vision, the design of which is based on neuro-scientific findings about the functions of some neurons in the visual cortex. Furthermore, we analyze the connection between the hierarchical organization of the visual system of the brain and the structure of Convolutional Networks (ConvNets). We pay particular attention to the mechanisms of inhibition of the responses of some neurons, which provide the visual system with improved stability to changing input stimuli, and discuss their implementation in image processing operators and in ConvNets.

show abstract

Contour detection based on a non-classical receptive field model with butterfly-shaped inhibition subregions

Cited by 32 publications

References 16 publications

Multifeature-Based Surround Inhibition Improves Contour Detection in Natural Images

Multifeature-Based Surround Inhibition Improves Contour Detection in Natural Images

Technique for image fusion based on NSST domain improved fast non-classical RF

Brain-Inspired Algorithms for Processing of Visual Data

Contact Info

Product

Resources

About