Automated Design of Image Operators that Detect Interest Points

Abstract

This work describes how evolutionary computation can be used to synthesize low-level image operators that detect interesting points on digital images. Interest point detection is an essential part of many modern computer vision systems that solve tasks such as object recognition, stereo correspondence, and image indexing, to name but a few. The design of the specialized operators is posed as an optimization/search problem that is solved with genetic programming (GP), a strategy still mostly unexplored by the computer vision community. The proposed approach automatically synthesizes operators that are competitive with state-of-the-art designs, taking into account an operator's geometric stability and the global separability of detected points during fitness evaluation. The GP search space is defined using simple primitive operations that are commonly found in point detectors proposed by the vision community. The experiments described in this paper extend previous results (Trujillo and Olague, 2006a,b) by presenting 15 new operators that were synthesized through the GP-based search. Some of the synthesized operators can be regarded as improved manmade designs because they employ well-known image processing techniques and achieve highly competitive performance. On the other hand, since the GP search also generates what can be considered as unconventional operators for point detection, these results provide a new perspective to feature extraction research.

The unconstrained automated generation of cell image features for medical diagnosis

“…GP and similar evolutionary algorithms are often used in image processing tasks in particular, where dimensionality is especially critical, and the capacity to extract mathematical descriptions is thus desirable [5,9,13,15,23,24,25]. Flexible representations are highly desirable in several particular areas, especially those in which techniques inspired by human vision might be sub-optimal, for instance, in nonstandard visual tasks such as satellite, multispectral, hyperspectral, or medical imagery [8,21,18].…”

Evolution of visual controllers for obstacle avoidance in mobile robotics

“…Aside from obstacle avoidance, genetic programming has been proved to achieve human-competitive results in image processing systems, e.g. for the detection of interest points, as shown by Olague and his co-workers [27,31,32]. Cooperative coevolution methods (e.g.…”

Advances in Adaptive Composite Filters for Object Recognition

“…Nevertheless, feature based systems suffer from two noteworthy drawbacks. First, they can be computationally expensive 1 ,a n d 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 & Koutroumbas, 2008;Trujillo & Olague, 2008). …”