Genetic Programming for Object Detection
J. Winkeler, Bangalore S Manjunath · 1996
This paper examines genetic programming as a machine learning technique in the context of object detection. Object detection is performed on image features and on gray-scale images themselves, with different goals. The generality of the solutions discovered, over the training set and over a wider range of images, is tested in both cases. Using genetic programming as a means of testing the utility of algorithms is also explored. Two programs generated using different features are hierarchically combined, improving the results to 1.4% false negatives on an untrained image, while saving processing. 1. Introduction How can one formulate a general method for detecting specific objects in a cluttered scene? A general solution is impossible since the algorithms will be target specific. Any strategy for detecting faces in an image, for example, cannot be expected to detect airplanes as well. Just like a person, a computer needs different strategies to detect different objects. Machine learnin...