Binarization plays a key role in the automatic information retrieval from document images. This process is usually performed in the first stages of documents analysis systems, and serves as a basis for subsequent steps. Hence it has to be robust in order to allow the full analysis workflow to be successful. Several methods for document image binarization have been proposed so far, most of which are based on hand-crafted image processing strategies. Recently, Convolutional Neural Networks have shown an amazing performance in many disparate duties related to computer vision. In this paper we discuss the use of convolutional auto-encoders devoted to learning an end-to-end map from an input image to its selectional output, in which activations indicate the likelihood of pixels to be either foreground or background. Once trained, documents can therefore be binarized by parsing them through the model and applying a global threshold. This approach has proven to outperform existing binarization strategies in a number of document types.

While standing as one of the most widely considered and successful supervised classification algorithms, the k-Nearest Neighbor (kNN) classifier generally depicts a poor efficiency due to being an instance-based method. In this sense, Approximated Similarity Search (ASS) stands as a possible alternative to improve those efficiency issues at the expense of typically lowering the performance of the classifier. In this paper we take as initial point an ASS strategy based on clustering. We then improve its performance by solving issues related to instances located close to the cluster boundaries by enlarging their size and considering the use of Deep Neural Networks for learning a suitable representation for the classification task at issue. Results using a collection of eight different datasets show that the combined use of these two strategies entails a significant improvement in the accuracy performance, with a considerable reduction in the number of distances needed to classify a sample in comparison to the basic kNN rule.instance at issue is not part of the cluster being examined, we include it inside the cluster, thus approaching the space partitioning to something similar to a fuzzy clustering; (iv) this process is done for each of the clusters obtained.This strategy increases the likelihood of making all the k-nearest neighbors of a given test instance fall in the same cluster. Also note that both the clustering 50 process and the proposed enlargement are done as a preprocessing stage, thus not affecting the efficiency of the classification process. As it shall be later experimentally checked, this process of increasing the cluster size approaches the brute-force kNN scenario in terms of accuracy with far less computational cost. 55Furthermore, recent advances in feature learning, namely deep learning, have made a breakthrough in the ability to learn suitable features for classification.That is, instead of resorting to hand-crafted features extracted, the models are trained to infer out of the raw input signal the most suitable features for the task at hand. This representational learning is performed by means of Deep 60 Neural Networks (DNN), consisting of a number of layers which are able to

The automatic classification of ships from aerial images is a considerable challenge. Previous works have usually applied image processing and computer vision techniques to extract meaningful features from visible spectrum images in order to use them as the input for traditional supervised classifiers. We present a method for determining if an aerial image of visible spectrum contains a ship or not. The proposed architecture is based on Convolutional Neural Networks (CNN), and it combines neural codes extracted from a CNN with a k-Nearest Neighbor method so as to improve performance. The kNN results are compared to those obtained with the CNN Softmax output. Several CNN models have been configured and evaluated in order to seek the best hyperparameters, and the most suitable setting for this task was found by using transfer learning at different levels. A new dataset (named MASATI) composed of aerial imagery with more than 6000 samples has also been created to train and evaluate our architecture. The experimentation shows a success rate of over 99% for our approach, in contrast with the 79% obtained with traditional methods in classification of ship images, also outperforming other methods based on CNNs. A dataset of images (MWPU VHR-10) used in previous works was additionally used to evaluate the proposed approach. Our best setup achieves a success ratio of 86% with these data, significantly outperforming previous state-of-the-art ship classification methods.

Abstract-This paper presents a system for the detection of ships and oil spills using side-looking airborne radar (SLAR) images. The proposed method employs a two-stage architecture composed of three pairs of convolutional neural networks (CNNs). Each pair of networks is trained to recognize a single class (ship, oil spill, and coast) by following two steps: a first network performs a coarse detection, and then, a second specialized CNN obtains the precise localization of the pixels belonging to each class. After classification, a postprocessing stage is performed by applying a morphological opening filter in order to eliminate small look-alikes, and removing those oil spills and ships that are surrounded by a minimum amount of coast. Data augmentation is performed to increase the number of samples, owing to the difficulty involved in obtaining a sufficient number of correctly labeled SLAR images. The proposed method is evaluated and compared to a single multiclass CNN architecture and to previous state-of-the-art methods using accuracy, precision, recall, F-measure, and intersection over union. The results show that the proposed method is efficient and competitive, and outperforms the approaches previously used for this task.