Adrian S. Barb

Visual-Semantic Modeling in Content-Based Geospatial Information Retrieval Using Associative Mining Techniques

Automatic learning of geospatial intelligence is challenging due to the complexity of articulating knowledge from visual patterns and to the ever-increasing quantities of image data generated on a daily basis. In this setting, human inspection and annotation is subjective and, more importantly, impractical. In this letter, we propose a knowledge-discovery algorithm that uses content-based methods to link low-level image features with high-level visual semantics in an effort to automate the process of retrieving semantically similar images. Our algorithm represents geospatial images by using a high-dimensional feature vector and generates a set of association rules that correlate semantic terms with visual patterns represented by discrete feature intervals. We also provide a mathematical model to customize the relevance of feature measurements to semantic assignments as well as methods of querying by semantics and by example.

Computable visually observed phenotype ontological framework for plants

BackgroundThe ability to search for and precisely compare similar phenotypic appearances within and across species has vast potential in plant science and genetic research. The difficulty in doing so lies in the fact that many visual phenotypic data, especially visually observed phenotypes that often times cannot be directly measured quantitatively, are in the form of text annotations, and these descriptions are plagued by semantic ambiguity, heterogeneity, and low granularity. Though several bio-ontologies have been developed to standardize phenotypic (and genotypic) information and permit comparisons across species, these semantic issues persist and prevent precise analysis and retrieval of information. A framework suitable for the modeling and analysis of precise computable representations of such phenotypic appearances is needed.ResultsWe have developed a new framework called the Computable Visually Observed Phenotype Ontological Framework for plants. This work provides a novel quantitative view of descriptions of plant phenotypes that leverages existing bio-ontologies and utilizes a computational approach to capture and represent domain knowledge in a machine-interpretable form. This is accomplished by means of a robust and accurate semantic mapping module that automatically maps high-level semantics to low-level measurements computed from phenotype imagery. The framework was applied to two different plant species with semantic rules mined and an ontology constructed. Rule quality was evaluated and showed high quality rules for most semantics. This framework also facilitates automatic annotation of phenotype images and can be adopted by different plant communities to aid in their research.ConclusionsThe Computable Visually Observed Phenotype Ontological Framework for plants has been developed for more efficient and accurate management of visually observed phenotypes, which play a significant role in plant genomics research. The uniqueness of this framework is its ability to bridge the knowledge of informaticians and plant science researchers by translating descriptions of visually observed phenotypes into standardized, machine-understandable representations, thus enabling the development of advanced information retrieval and phenotype annotation analysis tools for the plant science community.

Mining image content associations for visual semantic modeling in geospatial information indexing and retrieval

Query methods using visual semantics play an important role in horizontal interoperability of geospatial databases. However, a common practice is to manually label visual semantics of images using text annotations. This approach is subjective and, more importantly, impractical when dealing with large-scale geospatial image databases. In this paper, we propose a knowledge discovery (KDD) framework to link low-level image features with high-level visual semantics in an attempt to automate the process of retrieving semantically similar images. Our framework first extracts association rules that correlate semantic terms with discrete intervals of individual features. It then applies possibility functions to mathematically model visual semantics. Our approach provides a unique way to query image databases using semantics, and to potentially make available a knowledge exchange method for the geospatial community.

Semantics modeling in diagnostic medical image databases using customized fuzzy membership functions

It is widely recognized that fuzzy methods play an important role in image database retrieval, especially in the context of semantic queries. Known approaches that use crisp hierarchical semantic networks have been studied and applied to content-based image retrieval (CBIR) to narrow the gap between semantics and image features. Unfortunately, most of the studies lack the flexibility to adapt to an individuals preferences and/or to establish a general-purpose semantic network for sharing the perceptual understanding. In this paper, we propose a semantic query system for diagnostic image database retrieval that uses physician-defined linguistic variables. Users can obtain more desirable retrieval results by creating new, customized semantic terms, and by modeling a suite of membership functions to reflect their preferences. The system brings an increased versatility for image retrieval, and a great amount of possibilities for customizing the semantic terms using customized fuzzy mappings. Our unique approach provides various query methods that use the semantic terms within the domain of HRCT images of the lung and allows individual users to bring the contribution to the common knowledge base.

A Neotropical Miocene Pollen Database Employing Image-Based Search and Semantic Modeling

Premise of the study: Digital microscopic pollen images are being generated with increasing speed and volume, producing opportunities to develop new computational methods that increase the consistency and efficiency of pollen analysis and provide the palynological community a computational framework for information sharing and knowledge transfer. Methods: Mathematical methods were used to assign trait semantics (abstract morphological representations) of the images of neotropical Miocene pollen and spores. Advanced database-indexing structures were built to compare and retrieve similar images based on their visual content. A Web-based system was developed to provide novel tools for automatic trait semantic annotation and image retrieval by trait semantics and visual content. Results: Mathematical models that map visual features to trait semantics can be used to annotate images with morphology semantics and to search image databases with improved reliability and productivity. Images can also be searched by visual content, providing users with customized emphases on traits such as color, shape, and texture. Discussion: Content- and semantic-based image searches provide a powerful computational platform for pollen and spore identification. The infrastructure outlined provides a framework for building a community-wide palynological resource, streamlining the process of manual identification, analysis, and species discovery.

Applications of PathFinder Network Scaling for Improving the Ranking of Satellite Images

Content-based image retrieval techniques, although promising for handling large quantities of geospatial image data, are prone to creating overfitted models. This is due to the fact that supervised models most often capture patterns of existing observations and not those related to the whole population. This results in models that do not generalize well to new, undiscovered images. This article proposes a methodology to reduce overfitting when ranking high-resolution satellite images by domain semantics. Our approach uses PathFinder Network Scaling ensemble methods. We generate cross-fold co-occurrence measures for relevance of feature subspaces to each semantic. Each matrix is then reduced using the PathFinder network scaling algorithm. Irrelevant nodes are removed using node strength metrics resulting in an optimized model for ranking by semantic that generalizes better to new images. The results show that, when using this approach, the quality of ranking by semantic can be significantly improved. Mean Average Precision (MAP) of ranking over cross-fold experiments increased by 13.2% while standard deviation of MAP was reduced by 16.8% relative to experiments without PathFinder network scaling.

User-specific semantics for modeling content-based geospatial knowledge

Modern technology enables organizations to build huge geospatial data repositories. But collecting and storing information is not sufficient if it is not backed-up by accurate and flexible methods of extracting knowledge encapsulated in data. Image analysts use individualized models to represent visual patterns found in images. These models may not coincide with the models created by computer algorithms. To be successful, computer systems need to adapt to the subjective views of image analysts. In this article we introduce a novel method for fast query customization that provides users with individualized computer models to assign semantics to visual patterns in images. These models are evolved according to user input by adjusting possibility functions that mathematically map the assignment of semantics into low-level features. Our approach provides a flexible method for querying image databases using semantics, and potentially provides a knowledge exchange method for the geospatial community.

Semantic integration and knowledge exchange for diagnostic medical image databases

Information technology offers great opportunities to radiologists to utilize their expertise in decision support and training. Collaborative approaches in these areas enable physicians to access relevant cases diagnosed by experts from other health care groups. Unfortunately, there is little agreement on a single model of semantic representation and information exchange. In this context, semantic interoperability among heterogeneous groups plays an important role in a collaborative setting. In this paper, we propose a model for semantics integration and knowledge exchange in collaborative environments that feature heterogeneous semantics integration. It provides a computational and visual mechanism to associate synonymous semantics of visual abnormalities related to lung pathologies. We also offer a solution for system level communication that improves the retrieval precision using peer domain expertise. From our experiments we obtained a high degree of matching between different semantics that describe the same visual pattern of lung pathology. Also, our experiments show that, using the knowledge exchange mechanism, the default system setting adjusts well over time to increase the retrieval precision for new users.

Genetic Optimization for Associative Semantic Ranking Models of Satellite Images by Land Cover

Associative methods for content-based image ranking by semantics are attractive due to the similarity of generated models to human models of understanding. Although they tend to return results that are better understood by image analysts, the induction of these models is difficult to build due to factors that affect training complexity, such as coexistence of visual patterns in same images, over-fitting or under-fitting and semantic representation differences among image analysts. This article proposes a methodology to reduce the complexity of ranking satellite images for associative methods. Our approach employs genetic operations to provide faster and more accurate models for ranking by semantic using low level features. The added accuracy is provided by a reduction in the likelihood to reach local minima or to overfit. The experiments show that, using genetic optimization, associative methods perform better or at similar levels as state-of-the-art ensemble methods for ranking. The mean average precision (MAP) of ranking by semantic was improved by 14% over similar associative methods that use other optimization techniques while maintaining smaller size for each semantic model.

Associative semantic ranking of satellite images using PathFinder Network Scaling ensemble methods

This article proposes a methodology to reduce overfitting when ranking high-resolution satellite images by domain semantics. Our approach uses PathFinder Network Scaling ensemble methods. We generate cross-fold co-occurrence matrices for relevance of feature subspaces to each semantic. Each matrix is then reduced using the PathFinder network scaling algorithm. Irrelevant nodes are removed using node strength metrics resulting in an optimized model for ranking by semantic that generalizes better to new images. The experiments show that, when using this approach, the quality of ranking by semantic can be significantly improved. Results show that Mean Average Precision (MAP) of ranking over cross-fold experiments increased by a 13.2% while standard deviation of MAP was reduced by 16.8% relatively to experiments without PathFinder network scaling.