Invariant multi-scale object categorisation and recognition

Object recognition requires that templates with canonical views are stored in memory. Such templates must somehow be normalised. In this paper we present a novel method for obtaining 2D translation, rotation and size invariance. Cortical simple, complex and end-stopped cells provide multi-scale maps of lines, edges and keypoints. These maps are combined such that objects are characterised. Dynamic routing in neighbouring neural layers allows feature maps of input objects and stored templates to converge. We illustrate the construction of group templates and the invariance method for object categorisation and recognition in the context of a cortical architecture, which can be applied in computer vision.

Golf destinations' brand personality: the case of the Algarve

The purpose of this research is to develop and validate a measurement scale to assess golf destinations’ brand personality and therefore to perceive the destination personality of the Algarve as a golf destination. Based on literature review on human personality, brand personality, destination brand image and marketing scales validation procedures, an initial 36 unrepeated items were the base for a survey instrument. Those items were generated from the literature, from the results of individual interviews with experts in tourism and golf in the Algarve and from promotional texts in golf- related websites. After content validation, the items were allocated into categories of attributes by a panel of expert judges. A survey was then applied to a convenient sample of 600 golf players in the Algarve, and 545 (valid) questionnaires were analysed to refine the scale. Golf players assessed the components of the relational brand personality (functional, symbolic and experiential) as well as the Algarve as a golf destination. A taxonomy of brand personality was developed and tested in the Algarve as it is recognized as one of the world best golf destination. The developed taxonomy of brand personality was assessed in two ways: 1) through the overall perception of the Algarve as a golf destination and 2) through the perception of specific attributes of the destination grouped into three main categories (functional, symbolic and experiential). Therefore, two multi-dimensional brand personality models were estimated by using structural equation modelling. Findings of this study indicate that golf players ascribe personality characteristics to destinations. The brand personality of the Algarve is translated into three main dimensions enjoyableness, distinctiveness and friendliness when tourists/golf players reveal their overall perception of the destination. The brand personality of golf destination Algarve is reflected in the dimensions reliability, hospitality, uniqueness and attractiveness when tourists assess the components of the relational brand personality. Refined scales consisting of 10 and 12 items were finally derived meeting both reliability and validity requirements. This study does not replicate Aaker’s (1997) personality dimensions and very little parallelism can be drawn with Aaker’s (1997) brand personality scale since only three items from her scale were validated in both models: friendly and cheerful, (sincerity), reliable (competence). The same is verified concerning the ‘Big-five’. The human personality traits (HPT) validated to describe golf destinations personality are only four helpful, pleasant (agreeableness), relaxed (emotional stability), and innovative (intellect or openness). As far as destination image descriptors (DID) are concerned, the items appealing, relaxed and safe were validated, while traits suggested by the interviews and website promotional texts such as calm, natural, spectacular, unique, welcoming, and the best (destination-specific traits) appear to be appropriate to describe the personality of a golf destination. The results suggest that the overall perception of the Algarve´s brand personality is described by the dimensions enjoyableness, distinctiveness and friendliness. Moreover, the relational perspective revealed that the functional attributes of the destination are described by the dimension reliablility, while the symbolic attributes are described by the dimensions hospitablility and uniqueness and finally its experiential attributes are described by the dimension attractiveness. These results show that a golf destination´s brand personality should not just be based on good golf practices. Theoretical and practical implications are discussed in the context of destination brand personality.

Multi-scale keypoints in V1 and face detection

End-stopped cells in cortical area V1, which combine out- puts of complex cells tuned to different orientations, serve to detect line and edge crossings (junctions) and points with a large curvature. In this paper we study the importance of the multi-scale keypoint representa- tion, i.e. retinotopic keypoint maps which are tuned to different spatial frequencies (scale or Level-of-Detail). We show that this representation provides important information for Focus-of-Attention (FoA) and object detection. In particular, we show that hierarchically-structured saliency maps for FoA can be obtained, and that combinations over scales in conjunction with spatial symmetries can lead to face detection through grouping operators that deal with keypoints at the eyes, nose and mouth, especially when non-classical receptive field inhibition is employed. Al- though a face detector can be based on feedforward and feedback loops within area V1, such an operator must be embedded into dorsal and ventral data streams to and from higher areas for obtaining translation-, rotation- and scale-invariant face (object) detection.

Face recognition by cortical multi-scale line and edge representations

Empirical studies concerning face recognition suggest that faces may be stored in memory by a few canonical representations. Models of visual perception are based on image representations in cortical area V1 and beyond, which contain many cell layers for feature extraction. Simple, complex and end-stopped cells provide input for line, edge and keypoint detection. Detected events provide a rich, multi-scale object representation, and this representation can be stored in memory in order to identify objects. In this paper, the above context is applied to face recognition. The multi-scale line/edge representation is explored in conjunction with keypoint-based saliency maps for Focus-of-Attention. Recognition rates of up to 96% were achieved by combining frontal and 3/4 views, and recognition was quite robust against partial occlusions.

Face normalization using multi-scale cortical keypoints

Empirical studies concerning face recognition suggest that faces may be stored in memory by a few canonical representations. Models of visual perception are based on image representations in cortical area V1 and beyond, which contain many cell layers for feature extractions. Simple, complex and end-stopped cells tuned to different spatial frequencies (scales) and/or orientations provide input for line, edge and keypoint detection. This yields a rich, multi-scale object representation that can be stored in memory in order to identify objects. The multi-scale, keypoint-based saliency maps for Focus-of-Attention can be explored to obtain face detection and normalization, after which face recognition can be achieved using the line/edge representation. In this paper, we focus only on face normalization, showing that multi-scale keypoints can be used to construct canonical representations of faces in memory.

Building the what and where systems: multi-scale lines, edges and keypoints

Computer vision for realtime applications requires tremendous computational power because all images must be processed from the first to the last pixel. Ac tive vision by probing specific objects on the basis of already acquired context may lead to a significant reduction of processing. This idea is based on a few concepts from our visual cortex (Rensink, Visual Cogn. 7, 17-42, 2000): (1) our physical surround can be seen as memory, i.e. there is no need to construct detailed and complete maps, (2) the bandwidth of the what and where systems is limited, i.e. only one object can be probed at any time, and (3) bottom-up, low-level feature extraction is complemented by top-down hypothesis testing, i.e. there is a rapid convergence of activities in dendritic/axonal connections.

Integrated multi-scale architecture of the cortex with application to computer vision

Tese de dout., Engenharia Electrónica e de Computadores, Faculdade de Ciência e Tecnologia, Universidade do Algarve, 2007

Recognition of facial expressions by cortical multi-scale line and edge coding

Empirical studies concerning face recognition suggest that faces may be stored in memory by a few canonical representations. Models of visual perception are based on image representations in cortical area V1 and beyond, which contain many cell layers for feature extraction. Simple, complex and end-stopped cells provide input for line, edge and keypoint detection. Detected events provide a rich, multi-scale object representation, and this representation can be stored in memory in order to identify objects. In this paper, the above context is applied to face recognition. The multi-scale line/edge representation is explored in conjunction with keypoint-based saliency maps for Focus-of-Attention. Recognition rates of up to 96% were achieved by combining frontal and 3/4 views, and recognition was quite robust against partial occlusions.