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.
We present the Region of Interest Autoencoder (ROIAE), a combined supervised and reconstruction model for the automatic visual detection of objects. More specifically, we augment the detection loss function with a reconstruction loss that targets only foreground examples. This allows us to exploit more effectively the information available in the sparsely populated foreground training data used in...
Many of the existing methods for learning joint embedding of images and text use only supervised information from paired images and its textual attributes. Taking advantage of the recent success of unsupervised learning in deep neural networks, we propose an end-to-end learning framework that is able to extract more robust multi-modal representations across domains. The proposed method combines representation...
This paper proposes an end-to-end learning framework for multiview stereopsis. We term the network SurfaceNet. It takes a set of images and their corresponding camera parameters as input and directly infers the 3D model. The key advantage of the framework is that both photo-consistency as well geometric relations of the surface structure can be directly learned for the purpose of multiview stereopsis...
The deep learning neural network is a recent development that has become the subject of research in the computer vision and remote sensing disciplines. Super resolution (SR) images can be obtained using deep neural network methods that achieve a higher performance than all previous traditional methods. Here, in this study, the objective is to describe existing deep learning methods for SR satellite...
Restricted Boltzmann Machines (RBMs) have received special attention in the last decade due to their outstanding results in number of applications, such as face and human motion recognition, and collaborative filtering, among others. However, one of the main concerns about RBMs is related to the number of hidden units, which is application-dependent. Infinite RBM (iRBM) was proposed as an alternative...
This paper presents a new technique to solve the single image super resolution reconstruction problem based on multiple extreme learning machine regressors, called here MELM. The MELM employs a feature space of low resolution images, divided in subspaces, and one regressor is trained for each one. In the training task, we employ a color dataset containing 91 images, with approximately 5.3 million...
This paper presents a novel method for fault detection and location in modular five-level converters (MFLC) based on stacked sparse autoencoder (SSAE). SSAE is composed of multiple SAE and a softmax classifier. The capacitor voltage signals of all sub-modules (SMs) in the MFLC circuit are combined into a multi-channel signal. By moving window along the multi-channel signal, a set of signal segments...
Face sketch synthesis plays an important role in both law enforcement and digital entertainment. The existing methods for sketch synthesis always suffer from noising and blurring effect. To resolve these problems, a nonsubsampled Shearlet transform (NSST) based detail enhancement strategy is proposed. The exemplar-based method is firstly adopted to synthesize the primary sketch, then the final sketch...
Image enhancement is a common pre-processing step before the extraction of biometric features from a fingerprint sample. This can be essential especially for images of low image quality. An ideal fingerprint image enhancement should intend to improve the end-to-end biometric performance, i.e. the performance achieved on biometric features extracted from enhanced fingerprint samples. We use a model...
There have been significant progresses in single image super-resolution (SR) using deep convolutional neural network. In this paper, we propose a modified deep convolutional neural network model incorporated with image texture priors for single image SR. The model consist of a particular feature extraction layer followed by image reconstruction process, aiming to centralize on the image texture information...
Recently, very deep convolutional neural networks (CNNs) have been attracting considerable attention in image restoration. However, as the depth grows, the longterm dependency problem is rarely realized for these very deep models, which results in the prior states/layers having little influence on the subsequent ones. Motivated by the fact that human thoughts have persistency, we propose a very deep...
Recent studies have shown that the performance of single-image super-resolution methods can be significantly boosted by using deep convolutional neural networks. In this study, we present a novel single-image super-resolution method by introducing dense skip connections in a very deep network. In the proposed network, the feature maps of each layer are propagated into all subsequent layers, providing...
The success of various applications including robotics, digital content creation, and visualization demand a structured and abstract representation of the 3D world from limited sensor data. Inspired by the nature of human perception of 3D shapes as a collection of simple parts, we explore such an abstract shape representation based on primitives. Given a single depth image of an object, we present...
This paper presents a new method for the reconstruction of images from samples located at non-integer mesh positions. This is a common scenario for many image processing applications such as multi-image super-resolution, frame-rate up-conversion, or virtual view synthesis in multi-camera systems. The proposed method consists of an iterative procedure that employs adaptive denoising in order to reduce...
Compressed sensing (CS) is a signal processing framework for efficiently reconstructing a signal from a small number of measurements, obtained by linear projections of the signal. Block-based CS is a lightweight CS approach that is mostly suitable for processing very high-dimensional images and videos: it operates on local patches, employs a low-complexity reconstruction operator and requires significantly...
With the ability to reconstruct signals from a highly incomplete number of samples, Compressive Sensing (CS) has been proposed in bandwidth-constrained scenarios like remote sensing, where signals exist some degree of redundancy. In CS, reconstruction approaches are of great importance. However, current reconstruction approaches are of highly computational complexity because they use greedy or convex...
In this paper, we explore the use of recent conditional generative adversarial network framework for image to image translation applied to the domain of heterogeneous face sketch synthesis. Since the inception of the adversarial framework in 2014, great success has been noted with several variants till date. Further, we introduce a new dataset for composite sketch images. In particular we explore...
The fuzzy restricted Boltzmann machine (FRBM) is demonstrated to have better generative and discriminative capabilities than traditional RBM. We now further investigate and compare the generative ability of DBN with FRBM on image reconstruction. The DBN is pre-trained by stacking RBMs layer by layer and then fine-tuned by the wake-sleep algorithm. Then the FRBM, RBM and DBN are compared in detail...
In recent years, several new methods for missing data estimation have been developed. Real world datasets possess the properties of big data being volume, velocity and variety. With an increase in volume which includes sample size and dimensionality, existing imputation methods have become less effective and accurate. Much attention has been given to narrow Artificial Intelligence frameworks courtesy...
This paper presents the first photometric registration pipeline for Mixed Reality based on high quality illumination estimation using convolutional neural networks (CNNs). For easy adaptation and deployment of the system, we train the CNNs using purely synthetic images and apply them to real image data. To keep the pipeline accurate and efficient, we propose to fuse the light estimation results from...
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.