Spatial-Taxon Information Granules as Used in Iterative Fuzzy-Decision-Making for Image Segmentation

@inproceedings{Barghout2015SpatialTaxonIG,
  title={Spatial-Taxon Information Granules as Used in Iterative Fuzzy-Decision-Making for Image Segmentation},
  author={Lauren Barghout},
  year={2015}
}
An image conveys multiple meanings depending on the viewing context and the level of granularity at which the viewer perceptually organizes the scene. [] Key Method Human input determines the granularity of the query and consensus regarding spatial-taxon regions. The methods of concept algebra developed for computing with words [42] [48] are applied to spatial-taxons. Tools from the study of chaotic systems, such as tools for avoiding iteration problems, are explained in the context of fuzzy inference.

Hypernym and Spatial-Taxon Hierarchy. A Cognitive Informatics & Fuzzy Logic Approach to Combining Linguistic and Image Taxonomies

  • L. Barghout
  • Computer Science
    2018 IEEE 17th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)
  • 2018
This paper uses fuzzy granularization and fuzzy perceptualization as proposed by Zadeh 2002 to explore image annotation by using ZadeH's Restriction-centered Theory of Truth and Meaning as proposed in 2013.

Meaning and Uncertainty Inherent in Understanding Images, Spatial-Taxon Hierarchy, Word Annotation and Relevant Context

The results support the fuzzy spatial-taxon hierarchy of human scene perception described by other works, show that word descriptions depend on spatial- Taxon designation and that long tail word distributions require unbounded possibility with semantic uncertainty (type 2 fuzzy sets) for the word counts in the probability distribution.

Using the 5th dimensions of human visual perception to inspire automated edge and texture segmentation: A fuzzy spatial-taxon approach

  • L. Barghout
  • Computer Science
    2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)
  • 2016
A novel definition of edges is introduced, based on human hierarchical scene perception, which provides edges more aligned with human intuition of what edges should look like and is consistent with the finding of neurons responsive to proto-object boundaries in the visual cortex.

A general approach to compute the relevance of middle-level input features

This work proposes a novel general framework to construct explanations for the behaviour of Machine Learning (ML) models in terms of middle-level features, in the context of eXplainable Artificial Intelligence (XAI).

Improving seismic fault detection by super-attribute-based classification

Fault interpretation is one of the routine processes used for subsurface structure mapping and reservoir characterization from 3D seismic data. Various techniques have been developed for

An Efficient Approach to Fruit Classification and Grading using Deep Convolutional Neural Network

This paper focuses on developing a standalone system capable of classifying 3 types of fruit and taking apple as test case of grading, trained using the Inception V3 model, thus enabling it to distinguish fruit images.

Comparison of Digital Image Analysis and Conventional Microscopy in Evaluating Erythrocyte Morphology in Peripheral Blood Smears

The validated image recognition software is an acceptable diagnostic test in determining erythrocyte morphology in peripheral blood smears and its integration can potentially minimize hands-on time and improve the diagnostic laboratory workflow.

Classification within a small domain

The results showed that it is possible to make a conversational interface which is able to classify intents provided only a small training set, and consequently low accuracy, this conversational interfaces is not a suitable option for important tasks, but can be used for some non-critical classification tasks.

Algorithms for Sparse Support Vector Machines

This paper derives two closely related algorithms that achieve much better sparsity without loss of classification power and presents an alternative that replaces penalties by sparse-set constraints.

Performance Enhancement of Face Recognition in Smart TV Using Symmetrical Fuzzy-Based Quality Assessment

Experimental results showed that the performance of face recognition using the proposed method was better than that of conventional methods in terms of accuracy.

References

SHOWING 1-10 OF 61 REFERENCES

Visual Taxometric Approach to Image Segmentation Using Fuzzy-Spatial Taxon Cut Yields Contextually Relevant Regions

A fuzzy-logic-natural-vision-processing engine that implements a novel approach to image segmentation by assuming a standardized natural-scene-perception-taxonomy comprised of a hierarchy of nested spatial-taxons is demonstrated.

Empirical data on the configural architecture of human scene perception and linguistic labels using natural images and ambiguous figures

Both local and configural processes play a role in the figure-ground organization of scenes. Local factors include bottom-up edge segmentation that enables small regions to be fused into figural

Pictures and names: Making the connection

Normalized cuts and image segmentation

  • Jianbo ShiJ. Malik
  • Computer Science
    Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1997
This work treats image segmentation as a graph partitioning problem and proposes a novel global criterion, the normalized cut, for segmenting the graph, which measures both the total dissimilarity between the different groups as well as the total similarity within the groups.

Color image segmentation

  • Yining DengB. S. ManjunathH. Shin
  • Computer Science
    Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)
  • 1999
In this work, a new approach to fully automatic color image segmentation, called JSEG, is presented, where colors in the image are quantized to several representing classes that can be used to differentiate regions in the photo, thus forming a class-map of the image.

Toward a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic

  • L. Zadeh
  • Computer Science
    Fuzzy Sets Syst.
  • 1997

Granular computing: an introduction

  • W. Pedrycz
  • Computer Science
    Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference (Cat. No. 01TH8569)
  • 2001
The intent of the paper is to elaborate on the fundamentals of granular computing and put the entire area in a certain perspective while not moving into specific algorithmic details.

Toward a Theory of Granular Computing for Human-Centered Information Processing

This study expands on earlier research exploring the foundations of GrC and casting it as a structured combination of algorithmic and non- algorithmic information processing that mimics human, intelligent synthesis of knowledge from information.

Outline of a New Approach to the Analysis of Complex Systems and Decision Processes

  • L. Zadeh
  • Computer Science
    IEEE Trans. Syst. Man Cybern.
  • 1973
By relying on the use of linguistic variables and fuzzy algorithms, the approach provides an approximate and yet effective means of describing the behavior of systems which are too complex or too ill-defined to admit of precise mathematical analysis.

Of Holes and Wholes: The Perception of Surrounded Regions

Three types of factors were tested and found to influence perception of holes versus objects in a fully enclosed region and their implications for perceptual organization are discussed.
...