Attentional selection in object recognition

A key problem in object recognition is selection, namely, the problem of identifying regions in an image within which to start the recognition process, ideally by isolating regions that are likely to come from a single object. Such a selection mechanism has been found to be crucial in reducing the combinatorial 3e•rch involved in the matching stage of object recognition. Even though selection is of help in recognition, it has largely remained unsolved because of the difficulty in isolating regions belonging to objects under complex imaling conditions involving occlusions, changing illumination, and object appearances. This thesis presents a novel approach to the selection problem by proposing a computational model of visual attentional selection as a paradigm for selection in recognition. In particular, it proposes two modes of attentional selection, namely, attracted and pay attention modes as being appropriate for data and model-driven selection in recognition. An implementation of this model has led to new ways of extracting color, texture and line group information in images, and their subsequent we in isolating areas of the scene likely to contain the model object. Among the specific results in this thesis are: a method of specifying color by perceptual color categories for fast color region segmentation and color-based localization of objects, and a result showing that the recognition of texture patterns on model objects is possible under changes in orientation and occlusions without detailed segmentation. The thesis also presents an evaluation of the proposed model by integrating with a 3D from 2D object recognition system and recording the improvement in performance. These results indicate that attentional selection can significantly overcome the computational bottleneck in object recognition, both due to a reduction in the number of features, and due to a reduction in the number of matches during recognition using the information derived during selection. Finally, these studies have revealed a surprising use of selection, namely, in the partial solution of the pose of a 3D object. Thesis Supervisor: W. Eric L. Grimson Title: Associate Professor of Electrical Engineering and Computer Science A little learning s a dangeru thing; Drink deep, or taste not the Pierian sprng, There sallw draught. intoxicate the brain, And drinking largely sobers us again. Fired at first eight with what the Muse imparts, In fearleus youth we tempt the heights of Arts, White from the bounded leuel of our mind, Short views we take, nor see the lengths behind; But more aduvanced, behold with strange aurp, New distant scenes of endless science rise! So pleased at first the towering Alp. we try, Mount o'er the vales, and seem to tread the sky, Th' eternal snows appear already past, And the first clouds and mountains seem the lut; But, those attained, we tremble to survey The growing labors of the lengthened way, The' incresing prospect tire. our wandering eyes, Hills peep o'er hill., and Alp. on Alp. arise!