**Section 3**

**Optical Correlators, and Artificial Neural Networks** 

88 Advances in Object Recognition Systems

Snodgrass, J. G., & Vanderwart, M. (1980). A standardized set of 260 pictures: norms for

Surridge, A., Osorio, D., & Mundy, N. (2003). Evolution and selection of trichromatic vision

Tanaka, J., Luu, P., Weisbrod, M., & Kiefer, M. (1999). Tracking the time course of object categorization using event-related potentials. *Neuroreport, 10*, 829-835. Tanaka, J., & Presnell, L. (1999). Color diagnosticity in object recognition. *Perception &* 

Tanaka, J., Weiskopf, D., & Williams, P. (2001). The role of color in high-level vision. *Trends* 

Therriault, D. J., Yaxley, R. H., & Zwaan, R. A. (2009). The role of color diagnosticity in object recognition and representation. *Cognitive Processing, 10*, 335-342. Uttl, B., Graf, P., & Santacruz, P. (2006). Object color effects identification and repetition

Wang, G., & Kameda, S. (2005). Event-related potential component associated with the

Wang, G., & Suemitsu, K. (2007). Object recognition learning differentiates the

Wurm, L. H., Legge, G. E., Isenberg, L. M., & Luebker, A. (1993). Color improves object

Yokoyama, S. (2000). Molecular evolution of vertebrate visual pigments. *Progress in Retinal* 

Zeki, S., Aglioti, S., McKeefry, D., & Berlucchi, G. (1999). The neurological basis of conscious

Zeki, S., & Bartels, A. (1999). The clinical and functional measurement of cortical (in)activity

Zeki, S., & Marini, L. (1998). Three cortical stages of colour processing in the human brain.

Zeki, S., Watson, J., Lueck, C. J., Friston, K., Kennard, C., & Frackowiak, R. (1991). A direct

*Philosophical Transactions of the Royal Society, 354*, 1371-1382.

representations of objects at the ERP component N1. *Clinical Neurophysiology, 118*,

recognition in normal and low vision. *Journal of Experimental Psychology: Human* 

color perception in a blind patient. *Proceedings of the National Academy of Sciences, 96*,

subdivisions (V4 and V4a) of the human colour centre in the visual brain, with special reference to the two subdivisions (V4 and V4a) of the human colour centre.

demonstration of functional specialization in human visual cortex. *Journal of* 

recognition of three-dimensional objects. *Neuroreport, 16*, 767-771.

*Experimental Psychology: Learning, Memory and Cognition, 6*, 174-215.

in primates. *Trends in Ecology and Evolution, 18*, 198-205.

priming. *Scandinavian Journal of Psychology, 47*, 313-325.

*Psychophysics, 61*, 1140-1153.

372-380.

14124-14129.

*Brain, 121*, 1669-1685.

*Neuroscience, 11*, 641-649.

*in Cognitive Sciences, 5*, 211-215.

*Perception and Performance, 19*, 899-911.

*and Eye Research, 19*, 385-419.

name agreement, image agreement, familiarity, and visual complexity. *Journal of* 

**0**

**5**

*México*

**Advances in Adaptive Composite**

Victor H. Diaz-Ramirez1, Leonardo Trujillo2 and Sergio Pinto-Fernandez1

The problem of object recognition is one of the most common problems that is addressed by researchers and engineers that want to develop artificial vision or image analysis systems. In order to recognize an object within an image or video sequence we must basically solve two different but related tasks. Firstly, it is essential to detect the target object within the scene image, and secondly its exact location within the image must be estimated. While the general concept of object recognition is straightforward, even a brief review of modern literature reveals a wide range of proposals and systems (Goudail & Refregier, 2004; Szeliski, 2010). However, one of the most common and successful approaches are local feature-based systems that normally employ two basic steps (Lowe, 2004; Tuytelaars & Mikolajczyk, 2008). First, object features are extracted from the scene image, and afterwards a classification step is used to determine if the observed features belong to the target object; a process known as feature matching. Feature-based systems have achieved very good results and are widely used in many application domains. Nevertheless, feature based systems suffer from two noteworthy drawbacks. First, they can be computationally expensive1, and second their overall performance depends upon some ad-hoc decisions that might require optimization (Brown et al., 2011; Olague & Trujillo, 2011; Pérez & Olague, 2008; Theodoridis

An attractive alternative to feature-based systems is given by correlation filtering algorithms, an approach that has been intensively investigated over the last decades (Vijaya-Kumar et al., 2005). A correlation filter is basically a linear system whose output is the maximum-likelihood estimator of the targets coordinates in the observed scene (Goudail & Refregier, 2004; Refregier, 1999). In other words, detection is carried out by searching for correlation peaks in the system output, and the coordinates of these peaks provide the position estimates that localize the objects within the scene. An advantage of correlation filtering is that it possesses a strong mathematical foundation. Moreover, the design process of correlation filters usually considers the optimization of various performance criteria (Vijaya-Kumar & Hassebrook,

<sup>1</sup> While some implementations can achieve very high frame rates, they nevertheless are far behind the almost instantaneous results that optical-electronic systems can achieve with correlation filters such as

**1. Introduction**

& Koutroumbas, 2008; Trujillo & Olague, 2008).

those described in this chapter.

**Filters for Object Recognition**

<sup>1</sup>*Instituto Politecnico Nacional - CITEDI*

<sup>2</sup>*Instituto Tecnologico de Tijuana*
