The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
One-shot learning is a challenging problem where the aim is to recognize a class identified by a single training image. Given the practical importance of one-shot learning, it seems surprising that the rich information present in the class tag itself has largely been ignored. Most existing approaches restrict the use of the class tag to finding similar classes and transferring classifiers or metrics...
In most state-of-the-art hashing-based visual search systems, local image descriptors of an image are first aggregated as a single feature vector. This feature vector is then subjected to a hashing function that produces a binary hash code. In previous work, the aggregating and the hashing processes are designed independently. In this paper, we propose a novel framework where feature aggregating and...
We address the problem of large scale image geo-localization where the location of an image is estimated by identifying geo-tagged reference images depicting the same place. We propose a novel model for learning image representations that integrates context-aware feature reweighting in order to effectively focus on regions that positively contribute to geo-localization. In particular, we introduce...
Deep convolutional neural networks (CNNs) based face recognition approaches have been dominating the field. The success of CNNs is attributed to their ability to learn rich image representations. But training CNNs relies on estimating millions of parameters and requires a very large number of annotated training images. A widely-used alternative is to fine-tune the CNN that has been pre-trained using...
In this paper a novel CNN-based approach in the Content Based Image Retrieval domain that exploits supervised learning is proposed. We employ a deep CNN model to derive feature representations from the activations of the deepest layers and we refine the weights of the utilized layers in order to produce better image descriptors using information obtained from the available data labels. To this end,...
In this paper, a new object recognition framework is presented. The framework includes a variety of object recognition approaches based on Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and the K-nearest neighbor (K-NN). A color image vector representation model is also introduced. Based on the representation model, color Eigenspace is constructed using PCA and LDA for feature...
In this work, four well known convolutional neural networks (CNNs) that were pretrained on the ImageNet database are applied for the computer assisted diagnosis of celiac disease based on endoscopic images of the duodenum. The images are classified using three different transfer learning strategies and a experimental setup specifically adapted for the classification of endoscopic imagery. The CNNs...
Convolutional neural networks (convnets) have shown excellent results in various image classification tasks. Part of the success can be attributed to good image representations that are extracted using convolutional layers of the network. In this paper we consider convnets from the perspective of feature extraction for remote sensing image classification. We analyze the impact of convolutional feature...
Coral reefs exhibit significant within-class variations, complex between-class boundaries and inconsistent image clarity. This makes coral classification a challenging task. In this paper, we report the application of generic CNN representations combined with hand-crafted features for coral reef classification to take advantage of the complementary strengths of these representation types. We extract...
This paper proposes a CNN-based retrieval framework that uses Siamese network to learn a CNN model for image feature extraction. Model training and testing stages often use the same similarity metric. But this paper adopts a contrastive loss function with different distance metrics to fine-tune a pre-trained CNN model, and applies different distance metrics in testing stage. Through experimenting...
Feature encoding is a crucial step in BOW image representation. The standard BOW model assigns each image feature to the nearest visual-word without making a distinction between the features that are assigned to the same words. This hard feature assignment leads to high quantization errors and degrades the learning capacity of the classifiers in image classification. We propose a fuzzy feature encoding...
Data representation plays an important role in a classifier's accuracy. A given dataset may lead to better results by simply applying a change of basis while keeping the original number of parameters. In this paper, Gabor Filter based image representation has been exploited for object classification. First, Gabor filter based convolution is computed for features extraction, then down-sampling is performed...
The paper introduces to the digitization and features extraction processes of large volume of imaging documents and stored as images using mechanisms of big data and cloud technology. So, layout analysis, image representation, feature extraction and transformation huge amount of the prepared document images are presented in this paper. Accordingly, an efficient way reliable and highly clustering functionality...
Semantic event recognition based only on image-based cues is a challenging problem in computer vision. In order to capture rich information and exploit important cues like human poses, human garments and scene categories, we propose the Deep Spatial Pyramid Ensemble framework, which is mainly based on our previous work, i.e., Deep Spatial Pyramid (DSP). DSP could build universal and powerful image...
This work introduces an image retrieval framework based on using deep convolutional neural networks (CNN) as a local feature extractor. Motivated by the great success of CNN in recognition tasks, one may be tempted to simply adopt the output of CNN as a global image representation for retrieval. This straightforward approach, however, has proved deficient, because it can be vulnerable to various image...
Deep Neural Networks (DNN) are now the state-of-the-art for many image and object recognition tasks, as illustrated by their performance on standard benchmarks. The success of DNNs is attributed to their ability to learn rich mid-level image representations, as opposed to hand-designed low-level features used in other image analysis methods. Typically a large dataset of unlabeled images is used for...
In this paper we explore the role of scale for improved feature learning in convolutional networks. We propose multi-neighborhood convolutional networks, designed to learn image features at different levels of detail. Utilizing nonlinear scale-space models, the proposed multi-neighborhood model can effectively capture fine-scale image characteristics (i.e., appearance) using a small-size neighborhood,...
A training protocol for learning deep neural networks, called greedy layer-wise training, is applied to the evolution of a hierarchical, feed-forward Genetic Programming based system for feature construction and object recognition. Results on a popular handwritten digit recognition benchmark clearly demonstrate that two layers of feature transformations improves generalisation compared to a single...
Recently, many deep networks are proposed to learn hierarchical image representation to replace traditional hand-designed features. To enhance the ability of the generative model to tackle discriminative computer vision tasks (e.g. image classification), we propose a hierarchical deconvolutional network with two biologically inspired properties incorporated, i.e., non-negative sparsity and selectivity...
Spatial Pyramid Matching (SPM) has become a standard in bag-of-words (BoW) image representation, regardless of the features used in the process. With most research focusing on other part of the BoW pipeline, the arrangement of spatial windows in SPM remains untouched except by few works. This paper takes into consideration the idea that not all spatial windows in SPM are needed, and proposes two systematic...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.