Face segregation and recognition by cortical multi-scale line and edge coding

Models of visual perception are based on image representations in cortical area V1 and higher areas which contain many cell layers for feature extraction. Basic simple, complex and end-stopped cells provide input for line, edge and keypoint detection. In this paper we present an improved method for multi-scale line/edge detection based on simple and complex cells. We illustrate the line/edge representation for object reconstruction, and we present models for multi-scale face (object) segregation and recognition that can be embedded into feedforward dorsal and ventral data streams (the “what” and “where” subsystems) with feedback streams from higher areas for obtaining translation, rotation and scale invariance.

An integrated framework for combining gist vision with object segregation categorisation and recognition

There are roughly two processing systems: (1) very fast gist vision of entire scenes, completely bottom-up and data driven, and (2) Focus-of-Attention (FoA) with sequential screening of specific image regions and objects. The latter system has to be sequential because unnormalised input objects must be matched against normalised templates of canonical object views stored in memory, which involves dynamic routing of features in the visual pathways.

Cortical object segregation and categorization by multi-scale line and edge coding

In this paper we present an improved scheme for line and edge detection in cortical area V1, based on responses of simple and complex cells, truly multi-scale with no free parameters. We illustrate the multi-scale representation for visual reconstruction, and show how object segregation can be achieved with coarse-to-finescale groupings. A two-level object categorization scenario is tested in which pre-categorization is based on coarse scales only, and final categorization on coarse plus fine scales. Processing schemes are discussed in the framework of a complete cortical architecture.

Region segregation and saliency using colour information

Saliency maps determine the likelihood that we focus on interesting areas of scenes or images. These maps can be built using several low-level image features, one of which having a particular relevance: colour. In this paper we present a new computational model, based only on colour features, which provides a sound basis for saliency maps for static images and video, plus region segregation and cues for local gist vision.

A new combined joules supercritical rankine cycle exergetic analysis and optimization

The application of a supercritical Rankine cycle in combined cycles does not happen in today’s thermoelectric power stations. Nevertheless, the most recent development in gas turbines, that allows a high efficiency and high exhaust gases temperatures, and the improvement of high pressure and temperature alloys, makes this cycle possible. This study’s intent is to prove the viability of this combined cycle, since it can break the 60% efficiency barrier, which is the plafond in actual power stations. To attain this target, several configurations for this cycle have been simulated, optimized and analyzed [1]. The simulations were done with the computational program IPSEpro [2] and the optimizations were effectuated with software developed for the effect, using the DFP method [3]. In parallel with the optimization that claims the cycle’s efficiency maximization, an exergetic analysis was also made [4] to all the cycle components. In opposite to what happens in subcritical combined cycles, it was demonstrated that in supercritical combined cycles the higher efficiency takes place with a single steam pressure in the heat recovery steam generator (HRSG).

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

Combined disaggregation of agricultural land uses, livestock numbers and crops' production: an entropy approach

This paper presents several combined agricultural data disaggregation models in order to recover the farms' land uses, the livestock numbers and main crops' productions. The proposed approach estimates incomplete information at disaggregated level through entropy, using an information prior, and generating information for a combined calculation use of data in the estimation of other variables. The models were applied to the region of Algarve, to some rural pilot areas (Salir-Ameixial-Cachopo and Alcoutim) for livestock data, since this data in some Algarve's inland areas is needed for a European forest fire prevention project, and to the agrarian zones in a more complex framework. The results are promising. They were validated, in cross reference to real data, having proven to be valid and reliable. The total error was small and a considerable level of information heterogeneity was recovered. The total error was about 27,9% for the counties' land uses and 21% for the agrarian zones, and for the livestock it was also acceptable. The level of heterogeneity recovered was always higher than 50%, revealing some improvements regarding previous studies.

Object segregation and local gist vision using low-level geometry

Multi-scale representations of lines, edges and keypoints on the basis of simple, complex and end-stopped cells can be used for object categorisation and recognition (Rodrigues and du Buf, 2009 BioSystems 95 206-226). These representations are complemented by saliency maps of colour, texture, disparity and motion information, which also serve to model extremely fast gist vision in parallel with object segregation. We present a low-level geometry model based on a single type of self-adjusting grouping cell, with a circular array of dendrites connected to edge cells located at several angles.