Automated Flower Classification over a Large Number of Classes

TLDR

The study builds on the Varma and Ray kernel‑weighting method, previously achieving state‑of‑the‑art results on large datasets like Caltech 101/256, and addresses a 103‑class flower dataset with high inter‑class similarity and low intra‑class variation. The authors aim to determine whether combining multiple visual features can enhance classification accuracy on a large, highly similar flower dataset. They introduce a 103‑class flower dataset, extract four complementary features (shape/texture, boundary shape, petal spatial distribution, colour), and fuse them with a multiple‑kernel SVM framework. The optimal kernel combination boosts accuracy from 55.1 % with the best single feature to 72.8 % overall.

Abstract

We investigate to what extent combinations of features can improve classification performance on a large dataset of similar classes. To this end we introduce a 103 class flower dataset. We compute four different features for the flowers, each describing different aspects, namely the local shape/texture, the shape of the boundary, the overall spatial distribution of petals, and the colour. We combine the features using a multiple kernel framework with a SVM classifier. The weights for each class are learnt using the method of Varma and Ray, which has achieved state of the art performance on other large dataset, such as Caltech 101/256. Our dataset has a similar challenge in the number of classes, but with the added difficulty of large between class similarity and small within class similarity. Results show that learning the optimum kernel combination of multiple features vastly improves the performance, from 55.1% for the best single feature to 72.8% for the combination of all features.