Abstract
Co-occurrence features are effective for ob ject classification because observing co-occurrence of two events is far more informative than observing occurrence of each event separately. For example, a color co-occurrence histogram captures co-occurrence of pairs of colors at a given distance while a color histogram just expresses frequency of each color. As one of such co-occurrence features, CoHOG (co-occurrence his- tograms of oriented gradients) has been proposed and a method using CoHOG with a linear classifier has shown a comparable performance with state-of-the-art pedestrian detection methods. According to recent stud- ies, it has been suggested that combining heterogeneous features such as texture, shape, and color is useful for ob ject classification. There- fore, we introduce three heterogeneous features based on co-occurrence called color-CoHOG, CoHED, and CoHD, respectively. Each heteroge- neous features are evaluated on the INRIA person dataset and the Ox- ford 17/102 category flower datasets. The experimental results show that color-CoHOG is effective for the INRIA person dataset and CoHED is effective for the Oxford flower datasets. By combining above heteroge- neous features, the proposed method achieves comparable classification performance to state-of-the-art methods on the above datasets. The re- sults suggest that the proposed method using heterogeneous features can be used as an off-the-shelf method for various ob ject classification tasks.