Figure-ground Separation Research Articles

Texture difference cues in figure-ground separation

Texture difference cues in figure-ground separation

Functional recursion of orientation cues in figure-ground separation

Visual texture is an important cue to figure-ground organization. While processing of texture differences is a prerequisite for the use of this cue to extract figure-ground organization, these stages are distinct processes. One potential indicator of this distinction is the possibility that texture statistics play a different role in the figure vs. in the ground. To determine whether this is the case, we probed figure-ground processing with a family of local image statistics that specified textures that varied in the strength and spatial scale of structure, and the extent to which features are oriented. For image statistics that generated approximately isotropic textures, the threshold for identification of figure-ground structure was determined by the difference in correlation strength in figure vs. ground, independent of whether the correlations were present in figure, ground, or both. However, for image statistics with strong orientation content, thresholds were up to two times higher for correlations in the ground, vs. the figure. This held equally for texture-defined objects with convex or concave boundaries, indicating that these threshold differences are driven by border ownership, not boundary shape. Similar threshold differences were found for presentation times ranging from 125 to 500 ms. These findings identify a qualitative difference in how texture is used for figure-ground analysis, vs. texture discrimination. Additionally, it reveals a functional recursion: texture differences are needed to identify tentative boundaries and consequent scene organization into figure and ground, but then scene organization modifies sensitivity to texture differences according to the figure-ground assignment.

Spatial-Frequency Redistribution-based Saliency Region Detection for Thai Text Localisation

Saliency region detection plays an important role in computer vision applications and related areas, such as human fixation, figure-ground separation, face detection, and image compression. Nevertheless, state-of-the-art methods can moderately detect the saliency regions of a psychological pattern dataset. Therefore, this paper proposes a spatial-frequency redistribution (SFR) method to improve the efficiency of the detection of the saliency regions. The proposed SFR method consists of two main procedures: (i) adaptive cosine image construction-and-implantation and (ii) saliency region detection using complete multiple-object-implanted images. The former procedure constructs an adaptive cosine image by using a cosine function based on an object structure and then individually implants it into each object detectable. This stage provides the first significant property, spatial redistribution, to the object implanted. The adaptive cosine image redistributes the objects for controllability. Then, the latter procedure transforms a complete multiple object-implanted image into the frequency domain. At this point, the second significant property, frequency redistribution, provides the simple technique for identifying and separating the target object from the unwanted objects and background. In this paper, these properties are referred to as spatial-frequency redistribution. This method was realized as a computer program, and then such program was tested with a psychological pattern dataset and a Thai text dataset. The experimental results, when compared with state-of-the-art methods, show that the proposed SFR method can achieve the clear detection of the attention region in the psychological pattern dataset. Moreover, the proposed method can achieve a F-value of 80.28% with a recall and precision of 76.32% and 85.23%, respectively, for Thai text localisation in the Thai text dataset.

The orientation-difference cue in figure-ground separation: border ownership and timing

Figure-ground separation, a crucial component of visual processing, can be driven by differences in contrast, orientation, and other local cues. We previously showed (VSS 2020) that the orientation cue has distinctive characteristics: figure-ground separation depends not only on the magnitude of the orientation difference, but also on whether the oriented component is present in the figure vs. the ground. Here we show that this dependence is invariant with respect to convexity vs. concavity of the figure, and determine how it evolves over time. In a 2-AFC task, subjects (N=3) distinguished a target image containing five randomly-positioned figures rendered by one synthetic texture superimposed on a background defined by a second synthetic texture, from a non-target image consisting of a uniform texture whose image statistics matched the spatial average of the target’s statistics. Target and non-target images consisted of 64 x 64 arrays of 10-min black and white checks, and the figures covered 25% of the target’s area. Texture construction enabled control of the spatial frequency content of figure and ground in one or two orientations. For figures consisting of circular discs, figure-ground separation was facilitated when the figure texture was oriented, compared to when the ground was oriented. This difference was linked to the degree of anisotropy, as determined from the textures’ spectra (r=0.82, p<0.001). When figure boundaries were changed from convex to concave, results were similar, indicating that figure content and border ownership, but not border shape, determined performance. In preliminary results (N=1), we find that this asymmetry develops slowly; it is largely absent for a presentation time of 125 ms but close to maximal at 250 ms. In sum, figure-ground separation uses orientation differences in a way that depends on figure-ground assignment, suggesting a recurrent process that evolves over time.

Gestalt Research on Problem Solving and Today’s Gestalt

This article will focus on two pioneering scientific work on problem solving, or per Gestalt Theory, “productive thinking”. One of them is Köhler’s research on goal-directed tool use and overcoming obstacles in chimpanzees, the other one is Duncker’s studies on problem solving using a “think aloud” technique. In both Köhler’s and Duncker’s work, productive thinking is linked to a restructuring behavior. For example, tearing off a thin and long branch from a tree to serve as a stick or removing the various objects in a matchbox to transform it from a container to a platform on which to mount a candle are examples of such restructuring. In the final section, I will look at how today’s research trends might and should connect to Gestalt Theory. In conclusion, just as in memory, the two main proposals of Gestalt Theory, i.e., figure-ground separation and grouping in figures play a critical role also in thinking. Thus, Gestalt Theory seems to be able to come up with a common way of understanding perception, memory, as well as thinking. To our knowledge there is no other single theory within cognitive psychology that has such broad an explanatory power. This in itself is one more reason why Gestalt Theory in large deserves crucial attention. Keywords: Gestalt Theory, productive thinking, problem solving

A distinctive role for orientation in figure-ground separation

A distinctive role for orientation in figure-ground separation

Longitudinal progression of posterior cortical atrophy over 11 years: Relationship between lesion topology and clinical deficits

ABSTRACTPosterior cortical atrophy (PCA) is a rare form of dementia primarily characterized by slowly progressing deterioration of visual processing corresponding to atrophy in the posterior parietal and occipital cortices with less prominent memory loss than are usually seen in other forms of dementia such as Alzheimer’s Disease (AD). In the present case report, we describe longitudinal data over a period of 11 years regarding clinical and neuropsychological impairments and their relation to the location and extent of cortical changes related to higher order visual processing in a patient with posterior cortical atrophy. In our patient, visual processing deficits concerning space, motion and object perception emerged at the age of 50 and continued to worsen. By the age of 58, while the perception of contrast, color and figure-ground separation appeared undisturbed the patient exhibited pronounced dorsal- and ventral-related visual deficits, which continued to worsen with age. The patient’s MRI scans over the course of the disease revealed increasing circumscribed and bilateral atrophy of the parietal and occipital cortices, with a right-sided predominance. The specific localization of cortical atrophy, the slow progression characterized by visual processing deficits and relatively preserved memory were the main criteria for the diagnosis of posterior cortical atrophy.The case report also highlights the importance of an early extensive neurological and neuropsychological evaluation of visual deficits that occur without the presence of ophthalmological disease.

Sequential Convex Programming for Computing Information-Theoretic Minimal Partitions: Nonconvex Nonsmooth Optimization

We consider an unsupervised image segmentation problem---from figure-ground separation to multiregion partitioning---that consists of maximal distribution separation (in terms of mutual information) with spatial regularity (total variation regularization), which is what we call information-theoretic minimal partitioning. Adopting the bounded variation framework, we provide an in-depth analysis of the problem which establishes theoretical foundations and investigates the structure of the associated energy from a variational perspective. In doing so, we show that the objective exhibits a form of difference of convex functionals, which leads us to a class of large-scale nonconvex optimization problems where convex optimization techniques can be successfully applied. In this regard, we propose sequential convex programming based on the philosophy of stochastic optimization and the Chambolle--Pock primal-dual algorithm. The key idea behind it is to construct a stochastic family of convex approximations of the original nonconvex function and sequentially minimize the associated subproblems. Indeed, its stochastic nature makes it possible to often escape from bad local minima toward near-optimal solutions, where such optimality can be justified in terms of the recent findings in statistical physics regarding a striking characteristic of the high-dimensional landscapes. We experimentally demonstrate such a favorable ability of the proposed algorithm as well as show the capacity of our approach in numerous experiments. The preliminary conference paper can be found in [Y. Kee, M. Souiai, D. Cremers, and J. Kim, Proceedings of the IEEE Conference on Computer Vision and Pattern, Recognition, 2014].

Formal Auditory Training with Individuals after Traumatic Brain Injury

Purpose: Establishing the effects of a formal auditory training program on individuals, after a traumatic brain injury by means of behavioral and electrophysiological tests. Study Design: Longitudinal study. Setting: Study conducted at the electrophysiology clinic of the Federal University of Sao Paulo. Patients: Nine individuals with normal hearing, 20 to 37 years old, who were exposed to severe traumatic brain injury (score of 3 - 8 on the Glasgow Coma Scale upon hospital admission), 6 - 24 months earlier (11 months on average) and had imaging tests showing diffuse axonal injury with or without associated focal lesion. Intervention(s): subjected to a formal auditory training program in an acoustic booth involving eight 45-minute sessions aiming at training the auditory temporal order judgment (frequency and duration of sounds), auditory closure, and figure-ground separation skills for verbal and nonverbal sounds in monotic and dichotic listening tasks. The sessions and activities, in each session, were organized in increasing order of complexity to challenge the auditory system. In order to establish the efficacy of the auditory training, all participants were subjected to behavioral and electrophysiological assessments of the auditory processing, before and after the formal auditory training. Results: On the electrophysiological assessment, the absolute latencies of waves III and V, and of interpeak interval I-V decreased after the auditory training. However, the P300 did not exhibit a significant difference in either the latency or the amplitude parameters. Regarding the behavioral assessment of the auditory processing, it was verified that adequacy of the auditory figure-ground skills for verbal sounds, and the temporal order judging skills. Conclusions: individuals with diffuse axonal injury following a severe traumatic brain injury exhibited an improvement of central auditory processing after formal auditory training, as manifested on electrophysiological and behavioral assessments.

The Time-Course of Ultrarapid Categorization: The Influence of Scene Congruency and Top-Down Processing.

Although categorization can take place at different levels of abstraction, classic studies on semantic labeling identified the basic level, for example, dog, as entry point for categorization. Ultrarapid categorization tasks have contradicted these findings, indicating that participants are faster at detecting superordinate-level information, for example, animal, in a complex visual image. We argue that both seemingly contradictive findings can be reconciled within the framework of parallel distributed processing and its successor Leabra (Local, Error-driven and Associative, Biologically Realistic Algorithm). The current study aimed at verifying this prediction in an ultrarapid categorization task with a dynamically changing presentation time (PT) for each briefly presented object, followed by a perceptual mask. Furthermore, we manipulated two defining task variables: level of categorization (basic vs. superordinate categorization) and object presentation mode (object-in-isolation vs. object-in-context). In contradiction with previous ultrarapid categorization research, focusing on reaction time, we used accuracy as our main dependent variable. Results indicated a consistent superordinate processing advantage, coinciding with an overall improvement in performance with longer PT and a significantly more accurate detection of objects in isolation, compared with objects in context, at lower stimulus PT. This contextual disadvantage disappeared when PT increased, indicating that figure-ground separation with recurrent processing is vital for meaningful contextual processing to occur.

Cortical Dynamics of Figure-Ground Separation in Response to 2D Pictures and 3D Scenes: How V2 Combines Border Ownership, Stereoscopic Cues, and Gestalt Grouping Rules.

The FACADE model, and its laminar cortical realization and extension in the 3D LAMINART model, have explained, simulated, and predicted many perceptual and neurobiological data about how the visual cortex carries out 3D vision and figure-ground perception, and how these cortical mechanisms enable 2D pictures to generate 3D percepts of occluding and occluded objects. In particular, these models have proposed how border ownership occurs, but have not yet explicitly explained the correlation between multiple properties of border ownership neurons in cortical area V2 that were reported in a remarkable series of neurophysiological experiments by von der Heydt and his colleagues; namely, border ownership, contrast preference, binocular stereoscopic information, selectivity for side-of-figure, Gestalt rules, and strength of attentional modulation, as well as the time course during which such properties arise. This article shows how, by combining 3D LAMINART properties that were discovered in two parallel streams of research, a unified explanation of these properties emerges. This explanation proposes, moreover, how these properties contribute to the generation of consciously seen 3D surfaces. The first research stream models how processes like 3D boundary grouping and surface filling-in interact in multiple stages within and between the V1 interblob—V2 interstripe—V4 cortical stream and the V1 blob—V2 thin stripe—V4 cortical stream, respectively. Of particular importance for understanding figure-ground separation is how these cortical interactions convert computationally complementary boundary and surface mechanisms into a consistent conscious percept, including the critical use of surface contour feedback signals from surface representations in V2 thin stripes to boundary representations in V2 interstripes. Remarkably, key figure-ground properties emerge from these feedback interactions. The second research stream shows how cells that compute absolute disparity in cortical area V1 are transformed into cells that compute relative disparity in cortical area V2. Relative disparity is a more invariant measure of an object's depth and 3D shape, and is sensitive to figure-ground properties.

A biologically inspired neurocomputing circuit for image representation

Biological vision systems have evolved over millions of years, resulting in complex neural structures for representation and processing of stimuli. Moreover, biological visual systems are typically far more efficient than current human-made machine vision systems. The present report describes a non-task-dependent image representation scheme that simulates a biological neural vision mechanism in the early visual system. We designed a neural model involving multiple types of computational units to simulate ganglion cells and their non-classical receptive fields, local feedback control circuits and receptive field dynamic self-adjustment mechanisms in the retina. Beyond the pixel level, our model is able to represent images self-adaptively and rapidly. In addition, the improved representation was found to substantially facilitate image segmentation, figure-ground separation, saliency detection, and object recognition. We propose that these improvements arise because the retinal ganglion cells can resize their receptive fields, enabling multi-scale analysis functionality, a neighborhood referring function, and a localized synthetic function. The ganglion cell layer is the starting point for a diverse variety of subsequent visual processing. The extracted features and image presentation by the ganglion cell will be transmitted into high levels of visual system, for many visual tasks such as image segmentation, contour detection, object recognition and so on, the visual representation in the early stage of visual system is universal and independent on visual tasks.

Binocular fusion and invariant category learning due to predictive remapping during scanning of a depthful scene with eye movements.

How does the brain maintain stable fusion of 3D scenes when the eyes move? Every eye movement causes each retinal position to process a different set of scenic features, and thus the brain needs to binocularly fuse new combinations of features at each position after an eye movement. Despite these breaks in retinotopic fusion due to each movement, previously fused representations of a scene in depth often appear stable. The 3D ARTSCAN neural model proposes how the brain does this by unifying concepts about how multiple cortical areas in the What and Where cortical streams interact to coordinate processes of 3D boundary and surface perception, spatial attention, invariant object category learning, predictive remapping, eye movement control, and learned coordinate transformations. The model explains data from single neuron and psychophysical studies of covert visual attention shifts prior to eye movements. The model further clarifies how perceptual, attentional, and cognitive interactions among multiple brain regions (LGN, V1, V2, V3A, V4, MT, MST, PPC, LIP, ITp, ITa, SC) may accomplish predictive remapping as part of the process whereby view-invariant object categories are learned. These results build upon earlier neural models of 3D vision and figure-ground separation and the learning of invariant object categories as the eyes freely scan a scene. A key process concerns how an object's surface representation generates a form-fitting distribution of spatial attention, or attentional shroud, in parietal cortex that helps maintain the stability of multiple perceptual and cognitive processes. Predictive eye movement signals maintain the stability of the shroud, as well as of binocularly fused perceptual boundaries and surface representations.

Object Separation Using Saliency Algorithm

In this paper we are examining saliency algorithm with utilization of a straight forward image signature or image descriptor. With the assistance of image signature we can summarize the foreground area of an image inside the zone of signal mixing. At this point with the assistance of experimentation we are going to figure out whether the rough foreground area and the areas which are not outwardly clear overlap with one another. The proposed work will be fulfilled with the assistance of saliency algorithm utilizing image signature. The procedure includes division of all the item scenes and the dark image, this partition methodology is called Figure Ground Separation or FGS. Human intelligence can decipher image and can perform reckoning effectively yet doing so with the assistance of electrical gadgets will be a difficult task for analysts. Using saliency algorithm we are recreating brain tumor discovery.Keywords: Brain Tumor, Image Signature, Saliency, Saliency Method

A unified account of perceptual layering and surface appearance in terms of gamut relativity.

When we look at the world—or a graphical depiction of the world—we perceive surface materials (e.g. a ceramic black and white checkerboard) independently of variations in illumination (e.g. shading or shadow) and atmospheric media (e.g. clouds or smoke). Such percepts are partly based on the way physical surfaces and media reflect and transmit light and partly on the way the human visual system processes the complex patterns of light reaching the eye. One way to understand how these percepts arise is to assume that the visual system parses patterns of light into layered perceptual representations of surfaces, illumination and atmospheric media, one seen through another. Despite a great deal of previous experimental and modelling work on layered representation, however, a unified computational model of key perceptual demonstrations is still lacking. Here we present the first general computational model of perceptual layering and surface appearance—based on a boarder theoretical framework called gamut relativity—that is consistent with these demonstrations. The model (a) qualitatively explains striking effects of perceptual transparency, figure-ground separation and lightness, (b) quantitatively accounts for the role of stimulus- and task-driven constraints on perceptual matching performance, and (c) unifies two prominent theoretical frameworks for understanding surface appearance. The model thereby provides novel insights into the remarkable capacity of the human visual system to represent and identify surface materials, illumination and atmospheric media, which can be exploited in computer graphics applications.

Review of free software tools for image analysis of fluorescence cell micrographs.

An increasing number of free software tools have been made available for the evaluation of fluorescence cell micrographs. The main users are biologists and related life scientists with no or little knowledge of image processing. In this review, we give an overview of available tools and guidelines about which tools the users should use to segment fluorescence micrographs. We selected 15 free tools and divided them into stand-alone, Matlab-based, ImageJ-based, free demo versions of commercial tools and data sharing tools. The review consists of two parts: First, we developed a criteria catalogue and rated the tools regarding structural requirements, functionality (flexibility, segmentation and image processing filters) and usability (documentation, data management, usability and visualization). Second, we performed an image processing case study with four representative fluorescence micrograph segmentation tasks with figure-ground and cell separation. The tools display a wide range of functionality and usability. In the image processing case study, we were able to perform figure-ground separation in all micrographs using mainly thresholding. Cell separation was not possible with most of the tools, because cell separation methods are provided only by a subset of the tools and are difficult to parametrize and to use. Most important is that the usability matches the functionality of a tool. To be usable, specialized tools with less functionality need to fulfill less usability criteria, whereas multipurpose tools need a well-structured menu and intuitive graphical user interface.

Reconstructing the acoustic scenes encountered by free-flying, foraging bats

Aerial insectivorous bats face the challenge of efficient echo scene analysis for localizing obstacles and capturing prey in flight. Data collected with a telemetry microphone mounted on the foraging bat's head provide a valuable opportunity to reconstruct acoustic scenes comprised of echoes returning to the bat's ears. This study explores the information embedded in echoes from a tethered insect and background clutter recorded by the telemetry microphone in laboratory experiments. Using images from high-speed video cameras and recordings from a far-field microphone array, angular information about different objects in the echoes are restored by assimilating the reconstructed bat's position and echolocation beam aim with respect to the objects along its flight trajectory toward prey capture. This procedure is further augmented by theoretical simulations using acoustic scattering principles to circumvent the limitation imposed by the sensitivity and signal-to-noise ratio of the telemetry microphone. The reconstructed acoustic scenes offer an avenue for detailed analysis of important cues for figure-ground separation in a cluttered environment, and serve as a basis for subsequent neurocomputational modeling of auditory scene analysis performed by the bat's sonar receiver.

Enhancing automated micrograph‐based evaluation of LPS‐stimulated macrophage spreading

To evaluate macrophage spreading in immunofluorescence images of macrophages for surface protein CD11b and nuclear counterstaining with DAPI, it is necessary to measure the size of the macrophages at different time points after stimulation. Manual evaluation of fluorescent micrographs is usually a time-consuming and error-prone task, with poor reproducibility. Automatic image analysis methods can be used to improve the results. The quality of the analysis with these methods mainly depends on the quality of the image segmentation. A segmentation and quantification scheme based on shading correction, k-means clustering, and fast marching level sets has been developed for the purpose. An initial application of this approach showed that separating touching and overlapping cells in particular suffers severely in the inevitably blurred conditions, leading to partly erroneous measurements of macrophage spreading. An alternative method of segmentation in fluorescent micrographs was therefore investigated and evaluated in this study. The proposed approach uses a methodology that separates foreground objects from background objects on the basis of Boykov's graph cuts. In this process, a rough estimation of background pixels is used for background seeds. To identify foreground seeds, a difference of Gaussian band pass filter based workflow is developed. Information on foreground and background seeds is then used for a gradient magnitude based graph cut resulting in a robust figure-ground separation method. In addition, a fast marching level set approach is used in the post-processing step, which makes it possible to split touching cells by incorporating information about the cell nuclei. An evaluation based on a total of 553 manually labeled macrophages depicted in 21 micrographs showed that the proposed method significantly improves segmentation and splitting performance for fluorescent micrographs of LPS-stimulated macrophages and reduces the rate of error in automated analysis of macrophage spreading in comparison with alternative methods.

Figure–ground separation during active electrolocation in the weakly electric fish, Gnathonemus petersii

The weakly electric fish Gnathonemus petersii uses active electrolocation to detect and discriminate between objects in its environment. Objects are recognised by analysing the electric images, which they project onto the fish’s skin. In this study, we determined whether different types of large backgrounds interfere with the fishes’ ability to discriminate between objects. Fish were trained in a food-rewarded two-alternative forced-choice procedure to discriminate between two objects. In subsequent tests, structured and non-structured as well as stationary and moving backgrounds were positioned behind the objects and discrimination performance between objects was measured at different object distances. To define the electrosensory stimuli during the tests, the electric images of the objects and backgrounds used were measured. Without a background G. petersii was able to discriminate between objects up to distances of about 3–4cm. Even though the electric images of background and object superimposed in a complex way, the addition of stationary structured or plain backgrounds had only minor effects on the range of object discrimination. However, two types of moving backgrounds improved electrolocation by extending the range of object discrimination up to a distance of almost 5cm. This suggests that movements in the environment plays an important role for object identification and improves figure–ground separation during active electrolocation.

A Convex Max-Flow Approach to Distribution-Based Figure-Ground Separation

This study investigates a convex relaxation approach to figure-ground separation with a global distribution matching prior evaluated by the Bhattacharyya measure. The problem amounts to finding a region that most closely matches a known model distribution. It has been previously addressed by curve evolution, which leads to suboptimal and computationally intensive algorithms, or by graph cuts, which result in metrication errors. Solving a sequence of convex subproblems, the proposed relaxation is based on a novel bound of the Bhattacharyya measure which yields an algorithm robust to initial conditions. Furthermore, we propose a novel flow configuration that accounts for labeling-function variations, unlike existing configurations. This leads to a new max-flow formulation which is dual to the convex relaxed subproblems we obtained. We further prove that such a formulation yields exact and global solutions to the original, nonconvex subproblems. A comprehensive experimental evaluation on the Microsoft GrabCu...