Terms Of Elementary Operations Research Articles

Visual scanning as a reference framework for interactive representation design

When designing a representation, the designer implicitly formulates a sequence of visual tasks required to understand and use the representation effectively. This paper aims at making the sequence of visual tasks explicit in order to help designers elicit their design choices. In particular, we present a set of concepts to systematically analyse what a user must theoretically do to decipher representations. The analysis consists of a decomposition of the activity of scanning into elementary visualization operations. We show how the analysis applies to various existing representations, and how expected benefits can be expressed in terms of elementary operations. The set of elementary operations form the basis of a shared language for representation designers. The decomposition highlights the challenges encountered by a user when deciphering a representation and helps designers to exhibit possible flaws in their design, justify their choices, and compare designs. We also show that interaction with a representation can be considered as facilitation to perform the elementary operations. Categories and subject descriptors H.5.2 User Interfaces – evaluation/methodology, screen design. General terms design, human factors

Visual Learning by Evolutionary and Coevolutionary Feature Synthesis

In this paper, we present a novel method for learning complex concepts/hypotheses directly from raw training data. The task addressed here concerns data-driven synthesis of recognition procedures for real-world object recognition. The method uses linear genetic programming to encode potential solutions expressed in terms of elementary operations, and handles the complexity of the learning task by applying cooperative coevolution to decompose the problem automatically at the genotype level. The training coevolves feature extraction procedures, each being a sequence of elementary image processing and computer vision operations applied to input images. Extensive experimental results show that the approach attains competitive performance for three-dimensional object recognition in real synthetic aperture radar imagery.