Calligraphy (the special art of drawing characters with a brush specially made by the Chinese) is an integral part Chinese culture, and detecting calligraphy highly significant. At present, there are still some challenges in detection ancient calligraphy. In this paper, we interested character problem focusing on boundary. We chose High-Resolution Net (HRNet) as feature extraction backbone netw...

Machine learning and computer vision have driven many of the greatest advances in the modeling of Deep Convolutional Neural Networks (DCNNs). Nowadays, most of the research has been focused on improving recognition accuracy with better DCNN models and learning approaches. The recurrent convolutional approach is not applied very much, other than in a few DCNN architectures. On the other hand, In...

The classification of imbalanced datasets has recently attracted significant attention due to its implications in several real-world use cases. In such scenarios, the datasets have skewed class distributions while very few data instances are associated with certain classes. The classifiers developed on such datasets tend to favor the majority classes and are biased against the minority class. D...

In this paper we propose an ensemble of local and deep features for object classification. We also compare and contrast effectiveness of feature representation capability of various layers of convolutional neural network. We demonstrate with extensive experiments for object classification that the representation capability of features from deep networks can be complemented with information capt...

Very deep convolutional neural networks (CNNs) yield state of the art results on a wide variety of visual recognition problems. A number of state of the the art methods for image recognition are based on networks with well over 100 layers and the performance vs. depth trend is moving towards networks in excess of 1000 layers. In such extremely deep architectures the vanishing or exploding gradi...

In this work, we focus on the problem of image instance retrieval with deep descriptors extracted from pruned Convolutional Neural Networks (CNN). The objective is to heavily prune convolutional edges while maintaining retrieval performance. To this end, we introduce both data-independent and data-dependent heuristics to prune convolutional edges, and evaluate their performance across various c...

The present paper discusses the use of deep learning techniques, in particular a convolutional neural network, which is trained to identify, in an image, a surgical cutting tool located on a plane. Initially a database is established regarding the tool with different rotations and after this, the base structure of the convolutional network for its training is determined. It is possible to obtai...