Zoe Falomir

Describing Images Using Qualitative Models and Description Logics

Abstract Our approach describes any digital image qualitatively by detecting regions/objects inside it and describing their visual characteristics (shape and colour) and their spatial characteristics (orientation and topology) by means of qualitative models. The description obtained is translated into a description logic (DL) based ontology, which gives a formal and explicit meaning to the qualitative tags representing the visual features of the objects in the image and the spatial relations between them. For any image, our approach obtains a set of individuals that are classified using a DL reasoner according to the descriptions of our ontology.

Automation of Food Questionnaires in Medical Studies

Applications for automating the most commonly used dietary surveys in nutritional research, Food Frequency Questionnaires (FFQs) and 24 h Dietary Recalls (24HDRs), are reviewed in this paper. A comprehensive search of electronic databases was carried out and findings were classified by a group of experts in nutrition and computer science into: (i) Computerized Questionnaires and Web-based Questionnaires; (ii) FFQs and 24HDRs and combinations of both; and (iii) interviewer-administered or self-administered questionnaires. A discussion on the classification made and the works reported is included. Finally, works that apply innovative technologies are outlined and the future trends for automating questionnaires in nutrition are identified.

Object replacement and object composition in a creative cognitive system. Towards a computational solver of the Alternative Uses Test

In creative problem solving, humans perform object replacement and object composition to improvise tools in order to carry out tasks in everyday situations. In this paper, an approach to perform Object Replacement and Object Composition (OROC) inside a Creative Cognitive framework (CreaCogs) is proposed. Multi-feature correspondence is used to define similarity between objects in an everyday object domain. This enables the cognitive system OROC to perform creative replacement of objects and creative object composition. The generative properties of OROC are analysed and proof-of-concept experiments with OROC are reported. An evaluation of the results is carried out by human judges and compared to human performance in the Alternative Uses Test.

A model for the qualitative description of images based on visual and spatial features

An approach that provides a qualitative description of any image is presented in this paper. The main visual features (shape and colour) and the main spatial features (fixed orientation, relative orientation and topology) of each object within the image are described. This approach has been tested in two real scenarios that involve agents and human interaction: (i) images captured by the webcam of a mobile robot while it navigates, and (ii) images of tile compositions captured by an industrial camera used to select tile pieces to be used in assembling tile mosaics. In both scenarios, promising results have been obtained.

comRAT-C

A cognitive system (comRAT-C) solving the Remote Associates Test (RAT) is implemented.comRAT-C gives results comparable to human normative data results.A hypothesis on human answer preference is quantified. Empirical support is provided.Cognitive difficulty of RAT correlates with comRAT-C probability of finding answer. Discovering the processes and types of knowledge organization which are involved in the creative process is a challenge up to this date. Human creativity is usually measured by psychological tests, such as the Remote Associates Test (RAT). In this paper, an approach based on a specific type of knowledge organization and processes which enables automatic solving of RAT queries is implemented (comRAT) as a part of a more general cognitive theoretical framework for creative problem-solving (CreaCogs). This aims to study: (a) whether a convergence process can be used to solve such queries and (b) if frequency of appearance of the test items in language data may influence knowledge association or discovery in solving such problems.The comRAT uses a knowledge base of language data extracted from the Corpus of Contemporary American English. The results obtained are compared to results obtained in empirical tests with humans. In order to explain why some answers might be preferred over others, frequencies of appearance of the queries and solutions are analyzed. The difficulty encountered by humans when solving RAT queries is expressed in response times and percentage of participants solving the query, and a significant moderate correlation between human data on query difficulty and the data provided by this approach is obtained.

Logics based on qualitative descriptors for scene understanding

Abstract An approach for scene understanding based on qualitative descriptors, domain knowledge and logics is proposed in this paper. Qualitative descriptors, qualitative models of shape, colour, topology and location are used for describing any object in the scene. Two kinds of domain knowledge are provided: (i) categorizations of objects according to their qualitative descriptors, and (ii) semantics for describing the affordances, mobility and other functional properties of target objects. First order logics are obtained for reasoning and scene understanding. Tests were carried out at the Interact@Cartesium scenario and promising results were obtained.

Qualitative distances and qualitative image descriptions for representing indoor scenes in robotics

Patterns of qualitative concepts are extracted from robot sensors in order to describe the shapes, colours, spatial orientations and topology situations of natural landmarks in the robot environment and also the distance to them. Those qualitative patterns are obtained at a low level sensor data processing and without using training on datasets or learning techniques. A qualitative distance integration approach is parametrized and applied to detect glass windows and mirrors. Corners and columns are detected by the laser sensor and described qualitatively as relevant landmarks. Images taken by the robot camera are described qualitatively for completing the description of the objects located in the robot environment. Experimentation carried out shows that the integration of the information provided enhances the robot perception.

Measures of Similarity Between Objects Based on Qualitative Shape Descriptions

Abstract A computational approach for comparing qualitative shape descriptions (QSDs) of objects within digital images is presented. First, the dissimilarity of qualitative features of shape is measured: (i) intuitively using conceptual neighborhood diagrams; and (ii) mathematically using interval distances. Then, a similarity measure between QSDs is defined and tested using images of different categories of the MPEG-7-CE-Shape-1 library, images of tiles used to build mosaics, and a collection of Clipart images. The results obtained show the effectiveness of the similarity measure defined, which is invariant to translations, rotations and scaling, and which implicitly manages deformation of shape parts and incompleteness.

Qualitative distances and qualitative description of images for indoor scene description and recognition in robotics

This thesis is focused on reducing the gap between the acquisition of low-level information by robot sensors and the need of obtaining high-level information for enhancing human--machine communication and for applying logical reasoning processes. To this end, approaches for qualitative and semantic image description and qualitative distance sensor interpretation were developed. Experimentation was carried out on different robotic platforms showing useful applications.

A model for colour naming and comparing based on conceptual neighbourhood. An application for comparing art compositions

A computational model for Qualitative Colour Description, named the QCD model, is defined using the Hue, Saturation and Luminance colour space. This model can name rainbow colours, pale, light and dark colours, and colours in the grey scale, and it has been parameterised by participants of a study in two universities in Spain: University Jaume I and University of Sevilla. The relational structure of the QCD model is analysed by means of a conceptual neighbourhood diagram and it is used to formulate a measure of similarity for solving absolute and relative comparisons of qualitative colours. Moreover, a similarity measure between colour compositions, called SimQCDI, is also developed. A survey test on several art compositions is carried out and the results obtained by the participants are analysed and compared to the computational results provided by the SimQCDI. Also, a comparison to the standard RGB Colour Histogram similarity method is carried out, which shows that the proposed similarity is more intuitive and that the results obtained are similar with respect to quantification. Finally, the cognitive adequacy of the QCD model is also analysed.