Página 4 dos resultados de 471 itens digitais encontrados em 0.054 segundos

Absolute Uniqueness of Phase Retrieval with Random Illumination

Fannjiang, Albert
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
47.60493%
Random illumination is proposed to enforce absolute uniqueness and resolve all types of ambiguity, trivial or nontrivial, from phase retrieval. Almost sure irreducibility is proved for any complex-valued object of a full rank support. While the new irreducibility result can be viewed as a probabilistic version of the classical result by Bruck, Sodin and Hayes, it provides a novel perspective and an effective method for phase retrieval. In particular, almost sure uniqueness, up to a global phase, is proved for complex-valued objects under general two-point conditions. Under a tight sector constraint absolute uniqueness is proved to hold with probability exponentially close to unity as the object sparsity increases. Under a magnitude constraint with random amplitude illumination, uniqueness modulo global phase is proved to hold with probability exponentially close to unity as object sparsity increases. For general complex-valued objects without any constraint, almost sure uniqueness up to global phase is established with two sets of Fourier magnitude data under two independent illuminations. Numerical experiments suggest that random illumination essentially alleviates most, if not all, numerical problems commonly associated with the standard phasing algorithms.; Comment: 21 pages...

Content based video retrieval systems

Patel, B V; Meshram, B B
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 08/05/2012 Português
Relevância na Pesquisa
47.70923%
With the development of multimedia data types and available bandwidth there is huge demand of video retrieval systems, as users shift from text based retrieval systems to content based retrieval systems. Selection of extracted features play an important role in content based video retrieval regardless of video attributes being under consideration. These features are intended for selecting, indexing and ranking according to their potential interest to the user. Good features selection also allows the time and space costs of the retrieval process to be reduced. This survey reviews the interesting features that can be extracted from video data for indexing and retrieval along with similarity measurement methods. We also identify present research issues in area of content based video retrieval systems.; Comment: 18 Pages

Aggregating Deep Convolutional Features for Image Retrieval

Babenko, Artem; Lempitsky, Victor
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 26/10/2015 Português
Relevância na Pesquisa
47.60493%
Several recent works have shown that image descriptors produced by deep convolutional neural networks provide state-of-the-art performance for image classification and retrieval problems. It has also been shown that the activations from the convolutional layers can be interpreted as local features describing particular image regions. These local features can be aggregated using aggregation approaches developed for local features (e.g. Fisher vectors), thus providing new powerful global descriptors. In this paper we investigate possible ways to aggregate local deep features to produce compact global descriptors for image retrieval. First, we show that deep features and traditional hand-engineered features have quite different distributions of pairwise similarities, hence existing aggregation methods have to be carefully re-evaluated. Such re-evaluation reveals that in contrast to shallow features, the simple aggregation method based on sum pooling provides arguably the best performance for deep convolutional features. This method is efficient, has few parameters, and bears little risk of overfitting when e.g. learning the PCA matrix. Overall, the new compact global descriptor improves the state-of-the-art on four common benchmarks considerably.; Comment: accepted for ICCV 2015

Image Retrieval Based on Binary Signature ang S-kGraph

Van, Thanh The; Le, Thanh Manh
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 02/06/2015 Português
Relevância na Pesquisa
47.60493%
In this paper, we introduce an optimum approach for querying similar images on large digital-image databases. Our work is based on RBIR (region-based image retrieval) method which uses multiple regions as the key to retrieval images. This method significantly improves the accuracy of queries. However, this also increases the cost of computing. To reduce this expensive computational cost, we implement binary signature encoder which maps an image to its identification in binary. In order to fasten the lookup, binary signatures of images are classified by the help of S-kGraph. Finally, our work is evaluated on COREL's images.; Comment: 17 pages, 9 figures

Sketch-based 3D Shape Retrieval using Convolutional Neural Networks

Wang, Fang; Kang, Le; Li, Yi
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 14/04/2015 Português
Relevância na Pesquisa
47.534277%
Retrieving 3D models from 2D human sketches has received considerable attention in the areas of graphics, image retrieval, and computer vision. Almost always in state of the art approaches a large amount of "best views" are computed for 3D models, with the hope that the query sketch matches one of these 2D projections of 3D models using predefined features. We argue that this two stage approach (view selection -- matching) is pragmatic but also problematic because the "best views" are subjective and ambiguous, which makes the matching inputs obscure. This imprecise nature of matching further makes it challenging to choose features manually. Instead of relying on the elusive concept of "best views" and the hand-crafted features, we propose to define our views using a minimalism approach and learn features for both sketches and views. Specifically, we drastically reduce the number of views to only two predefined directions for the whole dataset. Then, we learn two Siamese Convolutional Neural Networks (CNNs), one for the views and one for the sketches. The loss function is defined on the within-domain as well as the cross-domain similarities. Our experiments on three benchmark datasets demonstrate that our method is significantly better than state of the art approaches...

New Method for 3D Shape Retrieval

Lakehal, Abdelghni; Beqqali, Omar El
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 07/11/2011 Português
Relevância na Pesquisa
47.60493%
The recent technological progress in acquisition, modeling and processing of 3D data leads to the proliferation of a large number of 3D objects databases. Consequently, the techniques used for content based 3D retrieval has become necessary. In this paper, we introduce a new method for 3D objects recognition and retrieval by using a set of binary images CLI (Characteristic level images). We propose a 3D indexing and search approach based on the similarity between characteristic level images using Hu moments for it indexing. To measure the similarity between 3D objects we compute the Hausdorff distance between a vectors descriptor. The performance of this new approach is evaluated at set of 3D object of well known database, is NTU (National Taiwan University) database.; Comment: 10 pages, 5 figures, publication paper

A Non-Binary Associative Memory with Exponential Pattern Retrieval Capacity and Iterative Learning: Extended Results

Salavati, Amir Hesam; Kumar, K. Raj; Shokrollahi, Amin
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
47.58206%
We consider the problem of neural association for a network of non-binary neurons. Here, the task is to first memorize a set of patterns using a network of neurons whose states assume values from a finite number of integer levels. Later, the same network should be able to recall previously memorized patterns from their noisy versions. Prior work in this area consider storing a finite number of purely random patterns, and have shown that the pattern retrieval capacities (maximum number of patterns that can be memorized) scale only linearly with the number of neurons in the network. In our formulation of the problem, we concentrate on exploiting redundancy and internal structure of the patterns in order to improve the pattern retrieval capacity. Our first result shows that if the given patterns have a suitable linear-algebraic structure, i.e. comprise a sub-space of the set of all possible patterns, then the pattern retrieval capacity is in fact exponential in terms of the number of neurons. The second result extends the previous finding to cases where the patterns have weak minor components, i.e. the smallest eigenvalues of the correlation matrix tend toward zero. We will use these minor components (or the basis vectors of the pattern null space) to both increase the pattern retrieval capacity and error correction capabilities. An iterative algorithm is proposed for the learning phase...

A List of Household Objects for Robotic Retrieval Prioritized by People with ALS (Version 092008)

Choi, Young Sang; Deyle, Travis; Kemp, Charles C.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 12/02/2009 Português
Relevância na Pesquisa
47.684624%
This technical report is designed to serve as a citable reference for the original prioritized object list that the Healthcare Robotics Lab at Georgia Tech released on its website in September of 2008. It is also expected to serve as the primary citable reference for the research associated with this list until the publication of a detailed, peer-reviewed paper. The original prioritized list of object classes resulted from a needs assessment involving 8 motor-impaired patients with amyotrophic lateral sclerosis (ALS) and targeted, in-person interviews of 15 motor-impaired ALS patients. All of these participants were drawn from the Emory ALS Center. The prioritized object list consists of 43 object classes ranked by how important the participants considered each class to be for retrieval by an assistive robot. We intend for this list to be used by researchers to inform the design and benchmarking of robotic systems, especially research related to autonomous mobile manipulation.

Watermarking Digital Images Based on a Content Based Image Retrieval Technique

Tsolis, Dimitrios K.; Sioutas, Spyros; Papatheodorou, Theodore S.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 17/10/2008 Português
Relevância na Pesquisa
47.57537%
The current work is focusing on the implementation of a robust watermarking algorithm for digital images, which is based on an innovative spread spectrum analysis algorithm for watermark embedding and on a content-based image retrieval technique for watermark detection. The highly robust watermark algorithms are applying "detectable watermarks" for which a detection mechanism checks if the watermark exists or no (a Boolean decision) based on a watermarking key. The problem is that the detection of a watermark in a digital image library containing thousands of images means that the watermark detection algorithm is necessary to apply all the keys to the digital images. This application is non-efficient for very large image databases. On the other hand "readable" watermarks may prove weaker but easier to detect as only the detection mechanism is required. The proposed watermarking algorithm combine's the advantages of both "detectable" and "readable" watermarks. The result is a fast and robust watermarking algorithm.; Comment: 18 pages, 4 figures, 4 tables, submitted to Multimedia Tools and Applications Journal, Springer

Finding More Relevance: Propagating Similarity on Markov Random Field for Image Retrieval

Lu, Peng; Peng, Xujun; Zhu, Xinshan; Wang, Xiaojie
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 26/12/2013 Português
Relevância na Pesquisa
47.60493%
To effectively retrieve objects from large corpus with high accuracy is a challenge task. In this paper, we propose a method that propagates visual feature level similarities on a Markov random field (MRF) to obtain a high level correspondence in image space for image pairs. The proposed correspondence between image pair reflects not only the similarity of low-level visual features but also the relations built through other images in the database and it can be easily integrated into the existing bag-of-visual-words(BoW) based systems to reduce the missing rate. We evaluate our method on the standard Oxford-5K, Oxford-105K and Paris-6K dataset. The experiment results show that the proposed method significantly improves the retrieval accuracy on three datasets and exceeds the current state-of-the-art retrieval performance.

Building a Test Collection for Speech-Driven Web Retrieval

Fujii, Atsushi; Itou, Katunobu
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 12/09/2003 Português
Relevância na Pesquisa
47.58206%
This paper describes a test collection (benchmark data) for retrieval systems driven by spoken queries. This collection was produced in the subtask of the NTCIR-3 Web retrieval task, which was performed in a TREC-style evaluation workshop. The search topics and document collection for the Web retrieval task were used to produce spoken queries and language models for speech recognition, respectively. We used this collection to evaluate the performance of our retrieval system. Experimental results showed that (a) the use of target documents for language modeling and (b) enhancement of the vocabulary size in speech recognition were effective in improving the system performance.

Sparsity assisted solution to the twin image problem in phase retrieval

Gaur, Charu; Mohan, Baranidharan; Khare, Kedar
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 13/07/2015 Português
Relevância na Pesquisa
47.60493%
The iterative phase retrieval problem for complex-valued objects from Fourier transform magnitude data is known to suffer from the twin image problem. In particular, when the object support is centro-symmetric, the iterative solution often stagnates such that the resultant complex image contains the features of both the desired solution and its inverted and complex-conjugated replica. The conventional approach to address the twin image problem is to modify the object support during initial iterations which can possibly lead to elimination of one of the twin images. However, at present there seems to be no deterministic procedure to make sure that the twin image will always be very weak or absent. In this work we make an important observation that the ideal solution without the twin image is typically more sparse (in some suitable transform domain) as compared to the stagnated solution containing the twin image. We further show that introducing a sparsity enhancing step in the iterative algorithm can address the twin image problem without the need to change the object support throughout the iterative process even when the object support is centro-symmetric. In a simulation study, we use binary and gray-scale pure phase objects and illustrate the effectiveness of the sparsity assisted phase recovery in the context of the twin image problem. The results have important implications for a wide range of topics in Physics where the phase retrieval problem plays a central role.

Deep Learning Representation using Autoencoder for 3D Shape Retrieval

Zhu, Zhuotun; Wang, Xinggang; Bai, Song; Yao, Cong; Bai, Xiang
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 25/09/2014 Português
Relevância na Pesquisa
47.60493%
We study the problem of how to build a deep learning representation for 3D shape. Deep learning has shown to be very effective in variety of visual applications, such as image classification and object detection. However, it has not been successfully applied to 3D shape recognition. This is because 3D shape has complex structure in 3D space and there are limited number of 3D shapes for feature learning. To address these problems, we project 3D shapes into 2D space and use autoencoder for feature learning on the 2D images. High accuracy 3D shape retrieval performance is obtained by aggregating the features learned on 2D images. In addition, we show the proposed deep learning feature is complementary to conventional local image descriptors. By combing the global deep learning representation and the local descriptor representation, our method can obtain the state-of-the-art performance on 3D shape retrieval benchmarks.; Comment: 6 pages, 7 figures, 2014ICSPAC

Storing and Indexing Plan Derivations through Explanation-based Analysis of Retrieval Failures

Ihrig, L. H.; Kambhampati, S.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 31/10/1997 Português
Relevância na Pesquisa
47.636226%
Case-Based Planning (CBP) provides a way of scaling up domain-independent planning to solve large problems in complex domains. It replaces the detailed and lengthy search for a solution with the retrieval and adaptation of previous planning experiences. In general, CBP has been demonstrated to improve performance over generative (from-scratch) planning. However, the performance improvements it provides are dependent on adequate judgements as to problem similarity. In particular, although CBP may substantially reduce planning effort overall, it is subject to a mis-retrieval problem. The success of CBP depends on these retrieval errors being relatively rare. This paper describes the design and implementation of a replay framework for the case-based planner DERSNLP+EBL. DERSNLP+EBL extends current CBP methodology by incorporating explanation-based learning techniques that allow it to explain and learn from the retrieval failures it encounters. These techniques are used to refine judgements about case similarity in response to feedback when a wrong decision has been made. The same failure analysis is used in building the case library, through the addition of repairing cases. Large problems are split and stored as single goal subproblems. Multi-goal problems are stored only when these smaller cases fail to be merged into a full solution. An empirical evaluation of this approach demonstrates the advantage of learning from experienced retrieval failure.; Comment: See http://www.jair.org/ for any accompanying files

Minimizing the Number of Matching Queries for Object Retrieval

Niedermayer, Johannes; Kröger, Peer
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
47.60493%
To increase the computational efficiency of interest-point based object retrieval, researchers have put remarkable research efforts into improving the efficiency of kNN-based feature matching, pursuing to match thousands of features against a database within fractions of a second. However, due to the high-dimensional nature of image features that reduces the effectivity of index structures (curse of dimensionality), due to the vast amount of features stored in image databases (images are often represented by up to several thousand features), this ultimate goal demanded to trade query runtimes for query precision. In this paper we address an approach complementary to indexing in order to improve the runtimes of retrieval by querying only the most promising keypoint descriptors, as this affects matching runtimes linearly and can therefore lead to increased efficiency. As this reduction of kNN queries reduces the number of tentative correspondences, a loss of query precision is minimized by an additional image-level correspondence generation stage with a computational performance independent of the underlying indexing structure. We evaluate such an adaption of the standard recognition pipeline on a variety of datasets using both SIFT and state-of-the-art binary descriptors. Our results suggest that decreasing the number of queried descriptors does not necessarily imply a reduction in the result quality as long as alternative ways of increasing query recall (by thoroughly selecting k) and MAP (using image-level correspondence generation) are considered.

Learning High-level Image Representation for Image Retrieval via Multi-Task DNN using Clickthrough Data

Bai, Yalong; Yang, Kuiyuan; Yu, Wei; Ma, Wei-Ying; Zhao, Tiejun
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
47.60493%
Image retrieval refers to finding relevant images from an image database for a query, which is considered difficult for the gap between low-level representation of images and high-level representation of queries. Recently further developed Deep Neural Network sheds light on automatically learning high-level image representation from raw pixels. In this paper, we proposed a multi-task DNN learned for image retrieval, which contains two parts, i.e., query-sharing layers for image representation computation and query-specific layers for relevance estimation. The weights of multi-task DNN are learned on clickthrough data by Ring Training. Experimental results on both simulated and real dataset show the effectiveness of the proposed method.

Bayes Merging of Multiple Vocabularies for Scalable Image Retrieval

Zheng, Liang; Wang, Shengjin; Zhou, Wengang; Tian, Qi
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
47.60493%
The Bag-of-Words (BoW) representation is well applied to recent state-of-the-art image retrieval works. Typically, multiple vocabularies are generated to correct quantization artifacts and improve recall. However, this routine is corrupted by vocabulary correlation, i.e., overlapping among different vocabularies. Vocabulary correlation leads to an over-counting of the indexed features in the overlapped area, or the intersection set, thus compromising the retrieval accuracy. In order to address the correlation problem while preserve the benefit of high recall, this paper proposes a Bayes merging approach to down-weight the indexed features in the intersection set. Through explicitly modeling the correlation problem in a probabilistic view, a joint similarity on both image- and feature-level is estimated for the indexed features in the intersection set. We evaluate our method through extensive experiments on three benchmark datasets. Albeit simple, Bayes merging can be well applied in various merging tasks, and consistently improves the baselines on multi-vocabulary merging. Moreover, Bayes merging is efficient in terms of both time and memory cost, and yields competitive performance compared with the state-of-the-art methods.; Comment: 8 pages...

Fast Automatic Video Retrieval using Web Images

Han, Xintong; Singh, Bharat; Morariu, Vlad I.; Davis, Larry S.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 10/12/2015 Português
Relevância na Pesquisa
47.60493%
We describe a real-time video retrieval framework based on short text input in which weakly labelled training samples from the web are obtained, after the query is known. Concept discovery methods in such a setting train hundreds of detectors at test time and apply them to every frame in the video database. Hence, they are not practical for use in a text based video retrieval setting. We show that an efficient visual representation for a new query can be constructed on-line that enables matching against the test set in real-time. We evaluate a few combinations of encoding, pooling, and matching schemes that are efficient and find that such a system can be built with surprisingly simple and well-known components. We are not only able to construct and apply query models in real-time, but with the help of a re-ranking scheme, we also outperform state-of-the-art methods by a significant margin.

Event Retrieval Using Motion Barcodes

Ben-Artzi, Gil; Werman, Michael; Peleg, Shmuel
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
47.60493%
We introduce a simple and effective method for retrieval of videos showing a specific event, even when the videos of that event were captured from significantly different viewpoints. Appearance-based methods fail in such cases, as appearances change with large changes of viewpoints. Our method is based on a pixel-based feature, "motion barcode", which records the existence/non-existence of motion as a function of time. While appearance, motion magnitude, and motion direction can vary greatly between disparate viewpoints, the existence of motion is viewpoint invariant. Based on the motion barcode, a similarity measure is developed for videos of the same event taken from very different viewpoints. This measure is robust to occlusions common under different viewpoints, and can be computed efficiently. Event retrieval is demonstrated using challenging videos from stationary and hand held cameras.

Experiments of Distance Measurements in a Foliage Plant Retrieval System

Kadir, Abdul; Nugroho, Lukito Edi; Susanto, Adhi; Santosa, Paulus Insap
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 20/11/2013 Português
Relevância na Pesquisa
47.60493%
One of important components in an image retrieval system is selecting a distance measure to compute rank between two objects. In this paper, several distance measures were researched to implement a foliage plant retrieval system. Sixty kinds of foliage plants with various leaf color and shape were used to test the performance of 7 different kinds of distance measures: city block distance, Euclidean distance, Canberra distance, Bray-Curtis distance, x2 statistics, Jensen Shannon divergence and Kullback Leibler divergence. The results show that city block and Euclidean distance measures gave the best performance among the others.; Comment: 14 pages, International Journal of Signal Processing, Image Processing and Pattern Recognition Vol. 5, No. 2, June, 2012