Hierarchical Object Representation Research Articles

Application of Software Engineering Methods in Modeling Business Projects in the Service Sphere

The purpose of the research is to substantiate the prospects for the use of software engineering methods in the development of projects of hotel and restaurant business, as well as to demonstrate the capabilities of modern information technology in the design of large hotel businesses. Research methodology. The method of system analysis, structural modeling, as well as CASE-tools of software engineering, in particular the line of CASE-tools BPwin, AllFusion Process Modeler 7, erwin Data Modeler (Erwin user community 2021), which allows automatically building an IDEF0 model of any complexity, are used. The novelty of the research and the practical significance of the obtained results is the possibilities’ demonstration of software engineering methods during the business projects development in the field of services. Conclusions. Innovations are a decisive factor in determining new management technologies in the hotel and restaurant and tourism business. The development of modern information technologies greatly simplifies the stage of designing business processes through a hierarchical representation of objects in the subject area in the form of graphical structures. This makes it possible to provide group work on the creation of the model with the direct involvement of all analysts and specialists involved in the creation of the project. There are a large number of software products that allow you to automate the construction of graphical models. Today their application in the sphere of services is actual. The article gives an example of using CASE-technology to create a functional model of a modern hotel.

MICaps: Multi-instance capsule network for machine inspection of Munro's microabscess

Munro's Microabscess (MM) is the diagnostic hallmark of psoriasis. Neutrophil detection in the Stratum Corneum (SC) of the skin epidermis is an integral part of MM detection in skin biopsy. The microscopic inspection of skin biopsy is a tedious task and staining variations in skin histopathology often hinder human performance to differentiate neutrophils from skin keratinocytes. Motivated from this, we propose a computational framework that can assist human experts and reduce potential errors in diagnosis. The framework first segments the SC layer, and multiple patches are sampled from the segmented regions which are classified to detect neutrophils. Both UNet and CapsNet are used for segmentation and classification. Experiments show that of the two choices, CapsNet, owing to its robustness towards better hierarchical object representation and localisation ability, appears as a better candidate for both segmentation and classification tasks and hence, we termed our framework as MICaps. The training algorithm explores both minimisation of Dice Loss and Focal Loss and makes a comparative study between the two. The proposed framework is validated with our in-house dataset consisting of 290 skin biopsy images. Two different experiments are considered. Under the first protocol, only 3-fold cross-validation is done to directly compare the current results with the state-of-the-art ones. Next, the performance of the system on a held-out data set is reported. The experimental results show that MICaps improves the state-of-the-art diagnosis performance by 3.27% (maximum) and reduces the number of model parameters by 50%.

Rural Building Detection in High-Resolution Imagery Based on a Two-Stage CNN Model

High-level feature extraction and hierarchical feature representation of image objects with a convolutional neural network (CNN) can overcome the limitations of the traditional building detection models using middle/low-level features extracted from a complex background. Aiming at the drawbacks of manual village location, high cost, and the limited accuracy of building detection in the existing rural building detection models, a two-stage CNN model is proposed in this letter to detect rural buildings in high-resolution imagery. Simulating the hierarchical processing mechanism of human vision, the proposed model is constructed with two CNNs, whose architectures can automatically locate villages and efficiently detect buildings, respectively. This two-stage CNN model effectively reduces the complexity of the background and improves the efficiency of rural building detection. The experiments showed that the proposed model could automatically locate all the villages in the two study areas, achieving a building detection accuracy of 88%. Compared with the existing models, the proposed model was proved to be effective in detecting buildings in rural areas with a complex background.

Articulated Pose Estimation Using Hierarchical Exemplar-Based Models

Exemplar-based models have achieved great success on localizing the parts of semi-rigid objects. However, their efficacy on highly articulated objects such as humans is yet to be explored. Inspired by hierarchical object representation and recent application of Deep Convolutional Neural Networks (DCNNs) on human pose estimation, we propose a novel formulation that incorporates both hierarchical exemplar-based models and DCNNs in the spatial terms. Specifically, we obtain more expressive spatial models by assuming independence between exemplars at different levels in the hierarchy; we also obtain stronger spatial constraints by inferring the spatial relations between parts at the same level. As our method strikes a good balance between expressiveness and strength of spatial models, it is both effective and generalizable, achieving state-of-the-art results on different benchmarks: Leeds Sports Dataset and CUB-200-2011.

Editorial: Hierarchical Object Representations in the Visual Cortex and Computer Vision

Over the past 40 years, Neurobiology and Computational Neuroscience have proved that deeper understanding of visual processes in humans and non-human primates can lead to important advancements in computational perception theories and systems. One of the main difficulties that arises when designing automatic vision systems is developing a mechanism that can recognize—or simply find—an object when faced with all the possible variations that may occur in a natural scene, and with the ease of the primate visual system. The area of the brain in primates that is dedicated to analyzing visual information is the visual cortex. The visual cortex performs a wide variety of complex tasks by means of seemingly simple operations. These operations are applied to several layers of neurons organized into a hierarchy, the layers representing increasingly complex, abstract intermediate processing stages.

Exploring dictionary-based semantic relatedness in labeled tree data

The increase in the volume and heterogeneity of semistructured data based application scenarios has demanded for next-generation methods that are able to effectively couple syntactic with semantic information in data management and mining tasks.The focus of this paper is on the development of methods for determining semantic relatedness in tree-shaped semistructured data and on the assessment of the impact of these methods on structural sense ranking in such data. By exploiting key features of a lexical knowledge base like WordNet, namely ontological relations and concept definitions, we propose a twofold approach that takes into account the particular form of labeled tree data as a conceptual hierarchical representation of real-world objects. We infer indirect relationships between tag concepts and exploit an interleaved search through different concept hierarchies in order to extend semantic relatedness measures originally conceived for plain-text data to deal with labeled tree data instances. We also develop a structural sense ranking framework which employs a context graph built on the tag concepts and the structural relations among tags in the tree data. Experimental evidence on a large real-world collection of Wikipedia articles has shown that the proposed methods can effectively detect and maximize semantic relatedness in tree-structured data, and can be profitably used to perform structural sense ranking.

Active improvement of hierarchical object features under budget constraints

When we think of an object in a supervised learning setting, we usually perceive it as a collection of fixed attribute values. Although this setting may be suited well for many classification tasks, we propose a new object representation and therewith a new challenge in data mining; an object is no longer described by one set of attributes but is represented in a hierarchy of attribute sets in different levels of quality. Obtaining a more detailed representation of an object comes with a cost. This raises the interesting question of which objects we want to enhance under a given budget and cost model. This new setting is very useful whenever resources like computing power, memory or time are limited. We propose a new active adaptive algorithm (AAA) to improve objects in an iterative fashion. We demonstrate how to create a hierarchical object representation and prove the effectiveness of our new selection algorithm on these datasets.

Mental visualization of objects from cross-sectional images

We extended the classic anorthoscopic viewing procedure to test a model of visualization of 3D structures from 2D cross-sections. Four experiments were conducted to examine key processes described in the model, localizing cross-sections within a common frame of reference and spatiotemporal integration of cross sections into a hierarchical object representation. Participants used a hand-held device to reveal a hidden object as a sequence of cross-sectional images. The process of localization was manipulated by contrasting two displays, in situ vs. ex situ, which differed in whether cross sections were presented at their source locations or displaced to a remote screen. The process of integration was manipulated by varying the structural complexity of target objects and their components. Experiments 1 and 2 demonstrated visualization of 2D and 3D line-segment objects and verified predictions about display and complexity effects. In Experiments 3 and 4, the visualized forms were familiar letters and numbers. Errors and orientation effects showed that displacing cross-sectional images to a remote display (ex situ viewing) impeded the ability to determine spatial relationships among pattern components, a failure of integration at the object level.

Learning the Compositional Nature of Visual Object Categories for Recognition

Real-world scene understanding requires recognizing object categories in novel visual scenes. This paper describes a composition system that automatically learns structured, hierarchical object representations in an unsupervised manner without requiring manual segmentation or manual object localization. A central concept for learning object models in the challenging, general case of unconstrained scenes, large intraclass variations, large numbers of categories, and lacking supervision information is to exploit the compositional nature of our (visual) world. The compositional nature of visual objects significantly limits their representation complexity and renders learning of structured object models statistically and computationally tractable. We propose a robust descriptor for local image parts and show how characteristic compositions of parts can be learned that are based on an unspecific part vocabulary shared between all categories. Moreover, a Bayesian network is presented that comprises all the compositional constituents together with scene context and object shape. Object recognition is then formulated as a statistical inference problem in this probabilistic model.

Adaptive medial-axis approximation for sphere-tree construction

Hierarchical object representations play an important role in performing efficient collision handling. Many different geometric primitives have been used to construct these representations, which allow areas of interaction to be localized quickly. For time-critical algorithms, there are distinct advantages to using hierarchies of spheres, known as sphere-trees, for object representation. This article presents a novel algorithm for the construction of sphere-trees. The algorithm presented approximates objects, both convex and non-convex, with a higher degree of fit than existing algorithms. In the lower levels of the representations, there is almost an order of magnitude decrease in the number of spheres required to represent the objects to a given accuracy.

Generation of collision-free 5-axis tool paths using a haptic surface

An intuitive man–machine interface for generating 5-axis tool paths is described in the paper. The system is based on a 5 degree-of-freedom force feedback haptic system, which is used to interface a human with an impenetrable 3D part. In the process of feeling the object, the user ‘teaches’ a milling machine to machine a virtual 3D object. The tool path generation has two phases: recording of access directions at the surface of the object and the post-processing phase. During the recording phase, three functions are carried out simultaneously: first, a fast collision detection algorithm, using hierarchical object representation, to drive the haptic system; second, visual feedback to show the regions that have been accessed by the tool; and third, a system to capture the access directions of the tool as the user touches the object. The post-processing phase involves the use of information generated in the recording phase to generate 5-axis tool paths. First, the access directions at the surface of the part are interpolated; and second, any residual collisions are detected and eliminated. We show the results of the tool path generation for two parts. The system can help an expert user generate, correct and tweak tool paths.

The interaction of spatial reference frames and hierarchical object representations: evidence from figure copying in hemispatial neglect.

In copying or drawing a figure, patients with hemispatial neglect following right parietal lobe lesions typically produce an adequate representation of parts on the right of the figure while omitting the corresponding features on the left. The neglect of information occupying contralateral locations is influenced by multiple spatial reference frames and by the hierarchical structure of the object(s) in the figure. The present work presents a computational characterization of the interaction among these influences to account for the way in which neglect manifests in copying. Empirical data are initially collected from brain-damaged and normal control subjects during two figure-copying tasks in which the hierarchical complexity and orientation of the displays to be copied are manipulated. In the context of the model, neglect is simulated by a "lesion" (monotonic drop-off along gradient from right to left) that can affect performance in both object- and viewer-centered reference frames. The effect of neglect in both these frames, coupled with the hierarchical representation of the object(s), provides a coherent account of the copying behavior of the patients and may be extended to account for the copying performance of other patients across a range of objects and scences.

3D collision detection: a survey

Many applications in Computer Graphics require fast and robust 3D collision detection algorithms. These algorithms can be grouped into four approaches: space–time volume intersection, swept volume interference, multiple interference detection and trajectory parameterization. While some approaches are linked to a particular object representation scheme (e.g., space–time volume intersection is particularly suited to a CSG representation), others do not. The multiple interference detection approach has been the most widely used under a variety of sampling strategies, reducing the collision detection problem to multiple calls to static interference tests. In most cases, these tests boil down to detecting intersections between simple geometric entities, such as spheres, boxes aligned with the coordinate axes, or polygons and segments. The computational cost of a collision detection algorithm depends not only on the complexity of the basic interference test used, but also on the number of times this test is applied. Therefore, it is crucial to apply this test only at those instants and places where a collision can truly occur. Several strategies have been developed to this end: (1) to find a lower time bound for the first collision, (2) to reduce the pairs of primitives within objects susceptible of interfering, and (3) to cut down the number of object pairs to be considered for interference. These strategies rely on distance computation algorithms, hierarchical object representations, orientation-based pruning criteria, and space partitioning schemes. This paper tries to provide a comprehensive survey of all these techniques from a unified viewpoint, so that well-known algorithms are presented as particular instances of general approaches.

A video segmentation algorithm for hierarchical object representations and its implementation

This paper describes a segmentation algorithm for generating hierarchical object representations of images and image sequences. Starting from an object model, we describe the structure of the corresponding segmentation algorithm including all analysis methods applied. Besides the well-known color and motion analysis, we also show how to utilize shape information. Furthermore, we discuss the tradeoff between reducing the computational complexity and the quality of the segmentation results. Last, we present the implementation concept for our analysis model, which uses a special toolbox model. The toolbox provides a set of addressing schemes that are needed by low-level video processing tools. The low-level tools are functions that apply a single operation to all pixels in one frame. Using these addressing functions makes it easy to implement new video processing tools, which, when combined, form new analysis methods. The toolbox exists in C-code and is partially transferred into VHDL.

Geometric reasoning for machining features using convex decomposition

A convex decomposition called the alternating sum of volumes with partitioning (ASVP) is a hierarchical volumetric representation of solid objects obtained from the boundary information. Form features intrinsic to the shape of solid objects can be recognized using ASVP decomposition. As the form-feature decomposition is compact and faithful to the shape of the object, it includes both positive and negative form-feature components. In the paper, conversion procedures from the form-feature decomposition into features useful for machining applications are described. The decomposition is accomplished by taking the complement of the halfspace abstraction of the positive components using the original faces, and combining this with the parent negative components. The resulting negative-feature decomposition represents the removal volume. Alternative decompositions of the removal volume are also obtained by exploiting the geometric information maintained in the decomposition.

A hypergraph-based hierarchial data structure and its applications

A new data structure, which combines a hierarchical organization with a hypergraph-based representation, is presented. This structure, called a structured hypergraph, is a hierarchy of hypergraphs and combines the two concepts of modular decomposition and of description of an entity at different levels of abstraction. Two basic transformations, called refinement and abstraction, are described. These latter are the basic tools for defining and modifying a structured hypergraph. Applications of this structure as a hardware system model, as a description of the symbol table of modular language, as a hierarchical representation of solid objects, and as a model of computer networks are discussed.