Non-classical Receptive Field Research Articles

Contour Detection Algorithm for α Phase Structure of TB6 Titanium Alloy fused with Multi-Scale Fretting Features

Aiming at the problems of inaccuracy in detecting the α phase contour of TB6 titanium alloy. By combining computer vision technology with human vision mechanisms, the spatial characteristics of the α phase can be simulated to obtain the contour accurately. Therefore, an algorithm for α phase contour detection of TB6 titanium alloy fused with multi-scale fretting features is proposed. Firstly, through the response of the classical receptive field model based on fretting and the suppression of new non-classical receptive field model based on fretting, the information maps of the α phase contour of the TB6 titanium alloy at different scales are obtained; then the information map of the smallest scale contour is used as a benchmark, the neighborhood is constructed to judge the deviation of other scale contour information, and the corresponding weight value is calculated; finally, Gaussian function is used to weight and fuse the deviation information, and the contour detection result of TB6 titanium alloy α phase is obtained. In the Visual Studio 2013 environment, 484 metallographic images with different temperatures, strain rates, and magnifications were tested. The results show that the performance evaluation F value of the proposed algorithm is 0.915, which can effectively improve the accuracy of α phase contour detection of TB6 titanium alloy.

Dependence of Contextual Modulation in Macaque V1 on Interlaminar Signal Flow.

In visual cortex, neural correlates of subjective perception can be generated by modulation of activity from beyond the classical receptive field (CRF). In macaque V1, activity generated by nonclassical receptive field (nCRF) stimulation involves different intracortical circuitry than activity generated by CRF stimulation, suggesting that interactions between neurons across V1 layers differ under CRF and nCRF stimulus conditions. Using Neuropixels probes, we measured border ownership modulation within large, local populations of V1 neurons. We found that neurons in single columns preferred the same side of objects located outside of the CRF. In addition, we found that cross-correlations between pairs of neurons situated across feedback/horizontal and input layers differed between CRF and nCRF stimulation. Furthermore, independent of the comparison with CRF stimulation, we observed that the magnitude of border ownership modulation increased with the proportion of information flow from feedback/horizontal layers to input layers. These results demonstrate that the flow of signals between layers covaries with the degree to which neurons integrate information from beyond the CRF.

Bio-Inspired Network for Diagnosing Liver Steatosis in Ultrasound Images.

Using ultrasound imaging to diagnose liver steatosis is of great significance for preventing diseases such as cirrhosis and liver cancer. Accurate diagnosis under conditions of low quality, noise and poor resolutions is still a challenging task. Physiological studies have shown that the visual cortex of the biological visual system has selective attention neural mechanisms and feedback regulation of high features to low features. When processing visual information, these cortical regions selectively focus on more sensitive information and ignore unimportant details, which can effectively extract important features from visual information. Inspired by this, we propose a new diagnostic network for hepatic steatosis. In order to simulate the selection mechanism and feedback regulation of the visual cortex in the ventral pathway, it consists of a receptive field feature extraction module, parallel attention module and feedback connection. The receptive field feature extraction module corresponds to the inhibition of the non-classical receptive field of V1 neurons on the classical receptive field. It processes the input image to suppress the unimportant background texture. Two types of attention are adopted in the parallel attention module to process the same visual information and extract different important features for fusion, which improves the overall performance of the model. In addition, we construct a new dataset of fatty liver ultrasound images and validate the proposed model on this dataset. The experimental results show that the network has good performance in terms of sensitivity, specificity and accuracy for the diagnosis of fatty liver disease.

Cognitive-Based Crack Detection for Road Maintenance: An Integrated System in Cyber-Physical-Social Systems

Effective road maintenance can not only achieve a balance between limited resources and long-term high-efficiency performance of road but also reduce the loss of life and property caused by road damage to vehicles and pedestrians. Due to the lack of a multidimensional dynamic monitoring system and enough extremely special data, the existing road maintenance system cannot accurately assess the road surface condition and provide timely early warning of sudden road damage. In this article, the M-RM system is proposed, that is, a metaverse-enabled road maintenance system based on cyber–physical–social systems (CPSSs), which fully utilizes the social and artificial system information of CPSS, as well as the simulation, monitoring, diagnosis and prediction functions of road systems in the virtual world of the metaverse. Then, in the road damage detection of system model in the virtual world, for the virtual data of the core assets of the metaverse, we propose an adaptive and information-preserving data augmentation (AIDA) algorithm-based nonclassical receptive field suppression and enhancement, an algorithm developed from human visual cognition. This algorithm enables the generation of a large amount of scarce fidelity data and avoids the introduced noise from impairing the performance of nonaugmented data. Finally, a crack detection algorithm named pay attention twice (PAT) is proposed, which uses the generated virtual data for training, and achieves secondary attention to high-frequency targets by fusing frequency-division convolution and mixed-domain attention mechanism. The detection performance of small targets in uncertain environments is enhanced. The metaverse system built in the current research can not only be used for road maintenance but also empower the traffic metaverse by using the traffic flow prediction module embedded in the algorithm. Experimental results demonstrate that the proposed algorithm can be applied to the road damage detection task under different noise and weather conditions, and the performance outweighs other state-of-the-art algorithms.

Urban garden spatial environment layout method based on random forest

In order to solve the problems of low layout accuracy and long cost in urban garden spatial environment layout, an urban garden spatial environment layout method based on random forest is designed. Firstly, the multi vision camera is used to collect the spatial environment image of urban garden, the spatial environment coordinates are transformed by rigid body, and the non-classical receptive field suppression method is used to remove the interference in the features. Then, with the help of analytic hierarchy process, the hierarchical model of configuration index rating is constructed, the layout index system is determined according to the model, and the constraints of judgment matrix are set. Finally, the layout model is constructed with the help of random forest algorithm, and the final input layout model data is determined to complete the layout. The experimental results show that the layout accuracy of the proposed method is high.

Saturation of visual responses explains size tuning in rat collicular neurons.

The receptive field of many visual neurons is composed of a central responsive area, the classical receptive field, and a non-classical receptive field, also called the "suppressive surround." A visual stimulus placed in the suppressive surround does not induce any response but modulates visual responses to stimuli within the classical receptive field, usually by suppressing them. Therefore, visual responses become smaller when stimuli exceed the classical receptive field size. The stimulus size inducing the maximal response is called the preferred stimulus size. In cortex, there is good correspondence between the sizes of the classical receptive field and the preferred stimulus. In contrast, in the rodent superior colliculus, the preferred size is often several fold smaller than the classical receptive field size. Here, we show that in the rat superior colliculus, the preferred stimulus size changes as a square root of the contrast inverse and the classical receptive field size is independent of contrast. In addition, responses to annulus were largely independent of the inner hole size. To explain these data, three models were tested: the divisive modulation of the gain by the suppressive surround (the "normalization" model), the difference of the Gaussians, and a divisive model that incorporates saturation to light flux. Despite the same number of free parameters, the model incorporating saturation to light performed the best. Thus, our data indicate that in rats, the saturation to light can be a dominant phenomenon even at relatively low illumination levels defining visual responses in the collicular neurons.

Explaining Orientation Adaptation in V1 by Updating the State of a Spatial Model.

In this work, we extend an influential statistical model based on the spatial classical receptive field (CRF) and non-classical receptive field (nCRF) interactions (Coen-Cagli et al., 2012) to explain the typical orientation adaptation effects observed in V1. If we assume that the temporal adaptation modifies the “state” of the model, the spatial statistical model can explain all of the orientation adaptation effects in the context of neuronal output using small and large grating observed in neurophysiological experiments in V1. The “state” of the model represents the internal parameters such as the prior and the covariance trained on a mixed dataset that totally determine the response of the model. These two parameters, respectively, reflect the probability of the orientation component and the connectivity among neurons between CRF and nCRF. Specifically, we have two key findings: First, neural adapted results using a small grating that just covers the CRF can be predicted by the change of the prior of our model. Second, the change of the prior can also predict most of the observed results using a large grating that covers both CRF and nCRF of a neuron. However, the prediction of the novel attractive adaptation using large grating covering both CRF and nCRF also necessitates the involvement of a connectivity change of the center-surround RFs. In addition, our paper contributes a new prior-based winner-take-all (WTA) working mechanism derived from the statistical-based model to explain why and how all of these orientation adaptation effects can be predicted by relying on this spatial model without modifying its structure, a novel application of the spatial model. The research results show that adaptation may link time and space by changing the “state” of the neural system according to a specific adaptor. Furthermore, different forms of stimulus used for adaptation can cause various adaptation effects, such as an a priori shift or a connectivity change, depending on the specific stimulus size.

Application of binocular disparity and receptive field dynamics: A biologically-inspired model for contour detection

Neurophysiological evidence demonstrates that classical receptive field responses in the primary visual cortex can be modulated by the non-classical receptive field. Although models based on the non-classical receptive field have been proposed, which has not employed the two following characteristics: dynamic regulation of the receptive field under external stimuli and depth determination by binocular cells. We propose a model that includes processing of gray-scale images and depth images. Luminance of grayscale image response was preprocessed using weighted least squares filtering; luminance of grayscale image and disparity information of depth image responses were obtained by V1 neuron responses. The receptive field size of each pixel used to calculate the luminance and disparity response is determined by the depth information. Luminance and disparity information responses were combined based on the optimal orientation, and robust contour maps were developed. Experimental results show that the proposed contour detection model outperforms biologically inspired models.

Blind S3D image quality prediction using classical and non-classical receptive field models

We develop a novel no-reference image quality assessment model for stereoscopic 3D (S3D) images that is inspired by functional receptive field models of perceptual mechanisms in primary visual cortex (V1). The approach is called the Blind S3D Integrated Quality Evaluator (BSIQE). BSIQE simulates monocular and binocular responses to stereo views using channel separation and weighted multi-channel combination models. Binocular responses are modeled as the fusion of the two channels using a weighted multi-channel combination. The responses to stereoscopic image content of both classical and non-classical anisotropic receptive fields are then modeled based on a determination of the relative importance of the receptive field responses. In the last stage of feature extraction, we deploy a simple and efficient way of decorrelating the picture data. We extract local binary pattern (LBP) statistical features from the computed receptive field responses, and use them to train a regressor to predict the perceptual quality of stereoscopic images. We carefully evaluate BSIQE on four public-domain 3D image quality databases, and find that it is statistically superior to all compared 2D and 3D IQA algorithms. BSIQE exhibits good performance across the datasets suggesting that it is general, and it has relatively low complexity.

Contour Detection by Simulating the Curvature Cell in the Visual Cortex and its Application to Object Classification

This paper addresses contour detection by simulating the human visual system and its application to visual object classification. Unlike previously designed bioinspired contour detection algorithms, we consider contour to be the salience of an edge image, and we extract the salience by simulating the endstopped cell and curvature cell in the visual cortex. Generally, we follow a local-to-global feed-forward architecture, in which the size of the receptive field (RF) increases from the primary visual cortex to the higher visual cortex. Edges are first detected by simple cells in small RFs, where textural details are suppressed by non-classical receptive fields (NCRFs) and sparse coding. Second, edges are integrated into local segments by complex cells. Afterwards, they are combined into the salience of edge images by endstopped cells and curvature cells and are ultimately the core of the final contour. In addition, we also apply the bioinspired contour detection algorithm to visual object classification tasks. Experiments on contour extraction show that, compared with state-of-the-art bioinspired algorithms, our algorithm makes a considerable improvement on contour detection. Experiments on visual object classification show that the contours produced by our proposal are powerful representations of the original images, which implies that our proposal is both biologically plausible and technologically useful.

Learning Nonclassical Receptive Field Modulation for Contour Detection.

This work develops a biologically inspired neural network for contour detection in natural images by combining the nonclassical receptive field modulation mechanism with a deep learning framework. The input image is first convolved with the local feature detectors to produce the classical receptive field responses, and then a corresponding modulatory kernel is constructed for each feature map to model the nonclassical receptive field modulation behaviors. The modulatory effects can activate a larger cortical area and thus allow cortical neurons to integrate a broader range of visual information to recognize complex cases. Additionally, to characterize spatial structures at various scales, a multiresolution technique is used to represent visual field information from fine to coarse. Different scale responses are combined to estimate the contour probability. Our method achieves state-of-the-art results among all biologically inspired contour detection models. This study provides a method for improving visual modeling of contour detection and inspires new ideas for integrating more brain cognitive mechanisms into deep neural networks.

Multi-scale contour detection model based on fixational eye movement mechanism

Physiological evidence has shown that classical receptive field (CRF) responses in the primary visual cortex (V1) can be suppressed by its surrounding region, called the non-classical receptive field (nCRF). Currently, the contour detection model based on the physiological characteristics of the V1 region is mainly used to suppress texture and highlight contour information through the inhibition of nCRF features. However, the effect of eye movement on inhibition is not considered in the inhibition calculation of such models. Inspired by the fixational eye movement (FEyeM) mechanism, we propose a multi-scale contour detection model based on fixational eye movement (MsFem) and the surrounding suppression mechanism. A bank of filters was proposed to simulate the influence of FEyeMs on nCRF, and multi-scale cues were utilized to improve the fine and coarse contour extraction and texture inhibition. The experiments showed that MsFem outperformed some biologically motivated ones in retaining the small-scale target contour information and suppressing the large-scale background textures.

结合人眼微动的新型非经典感受野模型

结合人眼微动的新型非经典感受野模型

Contour detection model using linear and non‐linear modulation based on non‐CRF suppression

Psychophysical and neurophysiological investigations on the human visual system show that most neurons in the primary visual cortex (V1) possess a non-classical receptive field (nCRF) region in addition to the CRF region. The nCRF has a modulatory, normally inhibitory, effect on the responses to visual stimuli generated within the CRF. In computational terms, this mechanism suppresses the response to edges in the presence of similar edges in the surroundings. Many computational techniques have been proposed to address the surround suppression mechanism. These methods introduce an inhibition term that is required to suppress the textures and protect the contours. Several studies have found that the spatial summation properties over the receptive fields of retinal X cells are approximately linear, while they are non-linear for Y cells. Inspired by the visual information processing in the X–Y channel and spatial summation properties of X and Y cells, the authors propose a contour detector using linear and non-linear modulations based on nCRF suppression. Extensive experimental evaluations demonstrate that their contour detector significantly outperforms other algorithms. The methods proposed in this study are expected to facilitate the development of efficient computational models in the field of machine vision.

A Fast Contour Detection Model Inspired by Biological Mechanisms in Primary Vision System.

Compared to computer vision systems, the human visual system is more fast and accurate. It is well accepted that V1 neurons can well encode contour information. There are plenty of computational models about contour detection based on the mechanism of the V1 neurons. Multiple-cue inhibition operator is one well-known model, which is based on the mechanism of V1 neurons' non-classical receptive fields. However, this model is time-consuming and noisy. To solve these two problems, we propose an improved model which integrates some additional other mechanisms of the primary vision system. Firstly, based on the knowledge that the salient contours only occupy a small portion of the whole image, the prior filtering is introduced to decrease the running time. Secondly, based on the physiological finding that nearby neurons often have highly correlated responses and thus include redundant information, we adopt the uniform samplings to speed up the algorithm. Thirdly, sparse coding is introduced to suppress the unwanted noises. Finally, to validate the performance, we test it on Berkeley Segmentation Data Set. The results show that the improved model can decrease running time as well as keep the accuracy of the contour detection.

Improved contour detection model with spatial summation properties based on nonclassical receptive field

The responses of cortical neurons to a stimulus in a classical receptive field (CRF) can be modulated by stimulating the non-CRF (nCRF) of neurons in the primary visual cortex (V1). In the very early stages (at around 40 ms), a neuron in V1 exhibits strong responses to a small set of stimuli. Later, however (after 100 ms), the neurons in V1 become sensitive to the scene’s global organization. As per these visual cortical mechanisms, a contour detection model based on the spatial summation properties is proposed. Unlike in previous studies, the responses of the nCRF to the higher visual cortex that results in the inhibition of the neuronal responses in the primary visual cortex by the feedback pathway are considered. In this model, the individual neurons in V1 receive global information from the higher visual cortex to participate in the inhibition process. Computationally, global Gabor energy features are involved, leading to the more coherent physiological characteristics of the nCRF. We conducted an experiment where we compared our model with those proposed by other researchers. Our model explains the role of the mutual inhibition of neurons in V1, together with an approach for object recognition in machine vision.

A ganglion-cell-based primary image representation method and its contribution to object recognition

ABSTRACTA visual stimulus is represented by the biological visual system at several levels: in the order from low to high levels, they are: photoreceptor cells, ganglion cells (GCs), lateral geniculate nucleus cells and visual cortical neurons. Retinal GCs at the early level need to represent raw data only once, but meet a wide number of diverse requests from different vision-based tasks. This means the information representation at this level is general and not task-specific. Neurobiological findings have attributed this universal adaptation to GCs' receptive field (RF) mechanisms. For the purposes of developing a highly efficient image representation method that can facilitate information processing and interpretation at later stages, here we design a computational model to simulate the GC's non-classical RF. This new image presentation method can extract major structural features from raw data, and is consistent with other statistical measures of the image. Based on the new representation, the performances of other state-of-the-art algorithms in contour detection and segmentation can be upgraded remarkably. This work concludes that applying sophisticated representation schema at early state is an efficient and promising strategy in visual information processing.

ASCII Art Synthesis from Natural Photographs.

While ASCII art is a worldwide popular art form, automatic generating structure-based ASCII art from natural photographs remains challenging. The major challenge lies on extracting the perception-sensitive structure from the natural photographs so that a more concise ASCII art reproduction can be produced based on the structure. However, due to excessive amount of texture in natural photos, extracting perception-sensitive structure is not easy, especially when the structure may be weak and within the texture region. Besides, to fit different target text resolutions, the amount of the extracted structure should also be controllable. To tackle these challenges, we introduce a visual perception mechanism of non-classical receptive field modulation (non-CRF modulation) from physiological findings to this ASCII art application, and propose a new model of non-CRF modulation which can better separate the weak structure from the crowded texture, and also better control the scale of texture suppression. Thanks to our non-CRF model, more sensible ASCII art reproduction can be obtained. In addition, to produce more visually appealing ASCII arts, we propose a novel optimization scheme to obtain the optimal placement of proportional-font characters. We apply our method on a rich variety of images, and visually appealing ASCII art can be obtained in all cases.

A Bio-Inspired Integration Method for Object Semantic Representation

Abstract We have two motivations. Firstly, semantic gap is a tough problem puzzling almost all sub-fields of Artificial Intelligence. We think semantic gap is the conflict between the abstractness of high-level symbolic definition and the details, diversities of low-level stimulus. Secondly, in object recognition, a pre-defined prototype of object is crucial and indispensable for bi-directional perception processing. On the one hand this prototype was learned from perceptional experience, and on the other hand it should be able to guide future downward processing. Human can do this very well, so physiological mechanism is simulated here. We utilize a mechanism of classical and non-classical receptive field (nCRF) to design a hierarchical model and form a multi-layer prototype of an object. This also is a realistic definition of concept, and a representation of denoting semantic. We regard this model as the most fundamental infrastructure that can ground semantics. Here a AND-OR tree is constructed to record prototypes of a concept, in which either raw data at low-level or symbol at high-level is feasible, and explicit production rules are also available. For the sake of pixel processing, knowledge should be represented in a data form; for the sake of scene reasoning, knowledge should be represented in a symbolic form. The physiological mechanism happens to be the bridge that can join them together seamlessly. This provides a possibility for finding a solution to semantic gap problem, and prevents discontinuity in low-order structures.

Contrast-dependent surround suppression models for contour detection

The goal of this work is to present a computational model for contour detection, based on the surround suppression mechanisms of the primary visual cortex, in which the strength of surround suppression can adaptively vary with contrast—the surround modulation tends to be clearly suppressive at high contrast and less suppressive at low contrast, which may help to achieve the tradeoff between reducing cluttered edges and retaining object structures with weak responses, thus improving performance of contour detection under different circumstances; on the other hand, for similar texels can engender stronger suppression effects, more than orientation feature, texton is introduced to homogeneity measurement, which can well character multiple properties of texture regions, thereby yielding better contour detection results than other suppression models. The study can provide useful suggestions for contour detection algorithm in computer vision, but may also contribute to understanding contrast influence and feature representation in non-classical receptive field inhibition.