As a typical deep-learning model, Convolutional Neural Networks (CNNs) can be exploited to automatically extract features from\nimages using the hierarchical structure inspired by mammalian visual system. For image classification tasks, traditional CNN\nmodels employ the softmax function for classification. However, owing to the limited capacity of the softmax function, there\nare some shortcomings of traditional CNN models in image classification. To deal with this problem, a new method combining\nBiomimetic Pattern Recognition (BPR) with CNNs is proposed for image classification. BPR performs class recognition by a union\nof geometrical cover sets in a high-dimensional feature space and therefore can overcome some disadvantages of traditional pattern\nrecognition.The proposed method is evaluated on three famous image classification benchmarks, that is, MNIST, AR, and CIFAR-\n10. The classification accuracies of the proposed method for the three datasets are 99.01%, 98.40%, and 87.11%, respectively, which\nare much higher in comparison with the other four methods in most cases
Loading....