A feature construction method for general object recognition

This paper presents a novel approach for object detection using a feature construction method called Evolution-COnstructed (ECO) features. Most other object recognition approaches rely on human experts to construct features. ECO features are automatically constructed by uniquely employing a standard genetic algorithm to discover series of transforms that are highly discriminative. Using ECO features provides several advantages over other object detection algorithms including: no need for a human expert to build feature sets or tune their parameters, ability to generate specialized feature sets for different objects, and no limitations to certain types of image sources. We show in our experiments that ECO features perform better or comparable with hand-crafted state-of-the-art object recognition algorithms. An analysis is given of ECO features which includes a visualization of ECO features and improvements made to the algorithm. •We propose a new method for feature construction called Evolution-COnstructed (ECO) features.•ECO features remove the need for a human expert to model objects for recognition.•ECO features compete well against state-of-the-art object recognition methods.•We show examples of what information ECO features are finding in the training images.