Gangs are a serious threat to the public safety in the United States. We have developed a system known as Gang Graffiti Automatic Recognition and Interpretation (GARI) to help law enforcement identify, track, and analyze gang activities. Gang graffiti components are the segmented graffiti content including symbols, digits, and characters. In this paper, we propose a deep convolutional neural network to classify the graffiti components. We make a comparison between our proposed deep learning method and our previous traditional method. Experimental results show the proposed method reaches 89.3% accuracy with dropout regularization.
Image classification has attracted more and more interest over the recent years. Consequently, a number of excellent non-parametric classification algorithms, such as collaborative representation based classification (CRC), have emerged and achieved superior performance to parametric classification algorithms. However, for fine-grained image classification task, both the class specific attributes and the shared attributes play significant roles in describing the image. CRC scheme does not consider the characteristics and merely utilizes all attributes without separation to represent an image. In this paper, we propose a hybrid collaborative representation based classification method to describe an image from perspective of the shared features, as well as the class specific features. Moreover, to reduce the representation error and obtain precise description, we learn a dictionary for hybrid collaborative representation with the training samples. We conduct extensive experiments on fine-grained image datasets to verify the superior performance of our proposed algorithm compared with the conventional approaches.
Nowadays, it is still difficult to adapt Convolutional Neural Network (CNN) based models for deployment on embedded devices. The heavy computation and large memory footprint of CNN models become the main burden in real application. In this paper, we propose a "Sparse Shrink" algorithm to prune an existing CNN model. By analyzing the importance of each channel via sparse reconstruction, the algorithm is able to prune redundant feature maps accordingly. The resulting pruned model thus directly saves computational resource. We have evaluated our algorithm on CIFAR-100. As shown in our experiments, we can reduce 56.77% parameters and 73.84% multiplication in total with only minor decrease in accuracy. These results have demonstrated the effectiveness of our "Sparse Shrink" algorithm.