Página 16 dos resultados de 471 itens digitais encontrados em 0.052 segundos

PLANT LEAF IDENTIFICATION BASED ON VOLUMETRIC FRACTAL DIMENSION

BACKES, Andre Ricardo; CASANOVA, Dalcimar; BRUNO, Odemir Martinez
Fonte: WORLD SCIENTIFIC PUBL CO PTE LTD Publicador: WORLD SCIENTIFIC PUBL CO PTE LTD
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
366.25605%
Texture is an important visual attribute used to describe the pixel organization in an image. As well as it being easily identified by humans, its analysis process demands a high level of sophistication and computer complexity. This paper presents a novel approach for texture analysis, based on analyzing the complexity of the surface generated from a texture, in order to describe and characterize it. The proposed method produces a texture signature which is able to efficiently characterize different texture classes. The paper also illustrates a novel method performance on an experiment using texture images of leaves. Leaf identification is a difficult and complex task due to the nature of plants, which presents a huge pattern variation. The high classification rate yielded shows the potential of the method, improving on traditional texture techniques, such as Gabor filters and Fourier analysis.; Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq); CNPq; National Council for Scientific and Technological Development, Brazil; National Council for Scientific and Technological Development, Brazil[306628/2007-4]; FAPESP[2006/54367-9]; Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP); Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP); FAPESP[2006/53972-6]; FAPESP State of Sao Paulo Research Foundation[2006/54367-9]; Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP); Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP); FAPESP State of Sao Paulo Research Foundation[2006/53972-6]

Gray Level Co-Occurrence Matrices: Generalisation and Some New Features

Sebastian V, Bino; Unnikrishnan, A.; Balakrishnan, Kannan
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 22/05/2012 Português
Relevância na Pesquisa
366.25605%
Gray Level Co-occurrence Matrices (GLCM) are one of the earliest techniques used for image texture analysis. In this paper we defined a new feature called trace extracted from the GLCM and its implications in texture analysis are discussed in the context of Content Based Image Retrieval (CBIR). The theoretical extension of GLCM to n-dimensional gray scale images are also discussed. The results indicate that trace features outperform Haralick features when applied to CBIR.; Comment: 7 pages, 3 figures

Face Synthesis (FASY) System for Generation of a Face Image from Human Description

Halder, Santanu; Bhattacharjee, Debotosh; Nasipuri, Mita; Basu, Dipak Kumar; Kundu, Mahantapas
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 21/05/2010 Português
Relevância na Pesquisa
366.25605%
This paper aims at generating a new face based on the human like description using a new concept. The FASY (FAce SYnthesis) System is a Face Database Retrieval and new Face generation System that is under development. One of its main features is the generation of the requested face when it is not found in the existing database, which allows a continuous growing of the database also.

Pairwise Rotation Hashing for High-dimensional Features

Ishikawa, Kohta; Sato, Ikuro; Ambai, Mitsuru
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 29/01/2015 Português
Relevância na Pesquisa
366.25605%
Binary Hashing is widely used for effective approximate nearest neighbors search. Even though various binary hashing methods have been proposed, very few methods are feasible for extremely high-dimensional features often used in visual tasks today. We propose a novel highly sparse linear hashing method based on pairwise rotations. The encoding cost of the proposed algorithm is $\mathrm{O}(n \log n)$ for n-dimensional features, whereas that of the existing state-of-the-art method is typically $\mathrm{O}(n^2)$. The proposed method is also remarkably faster in the learning phase. Along with the efficiency, the retrieval accuracy is comparable to or slightly outperforming the state-of-the-art. Pairwise rotations used in our method are formulated from an analytical study of the trade-off relationship between quantization error and entropy of binary codes. Although these hashing criteria are widely used in previous researches, its analytical behavior is rarely studied. All building blocks of our algorithm are based on the analytical solution, and it thus provides a fairly simple and efficient procedure.; Comment: 16 pages, 8 figures, wrote at Mar 2014

Freehand Sketch Recognition Using Deep Features

Sarvadevabhatla, Ravi Kiran; Babu, R. Venkatesh
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
366.25605%
Freehand sketches often contain sparse visual detail. In spite of the sparsity, they are easily and consistently recognized by humans across cultures, languages and age groups. Therefore, analyzing such sparse sketches can aid our understanding of the neuro-cognitive processes involved in visual representation and recognition. In the recent past, Convolutional Neural Networks (CNNs) have emerged as a powerful framework for feature representation and recognition for a variety of image domains. However, the domain of sketch images has not been explored. This paper introduces a freehand sketch recognition framework based on "deep" features extracted from CNNs. We use two popular CNNs for our experiments -- Imagenet CNN and a modified version of LeNet CNN. We evaluate our recognition framework on a publicly available benchmark database containing thousands of freehand sketches depicting everyday objects. Our results are an improvement over the existing state-of-the-art accuracies by 3% - 11%. The effectiveness and relative compactness of our deep features also make them an ideal candidate for related problems such as sketch-based image retrieval. In addition, we provide a preliminary glimpse of how such features can help identify crucial attributes (e.g. object-parts) of the sketched objects.; Comment: Submitted to ICIP-2015...

A Review of Research on Devnagari Character Recognition

Dongre, V J; Mankar, V H
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 12/01/2011 Português
Relevância na Pesquisa
366.25605%
English Character Recognition (CR) has been extensively studied in the last half century and progressed to a level, sufficient to produce technology driven applications. But same is not the case for Indian languages which are complicated in terms of structure and computations. Rapidly growing computational power may enable the implementation of Indic CR methodologies. Digital document processing is gaining popularity for application to office and library automation, bank and postal services, publishing houses and communication technology. Devnagari being the national language of India, spoken by more than 500 million people, should be given special attention so that document retrieval and analysis of rich ancient and modern Indian literature can be effectively done. This article is intended to serve as a guide and update for the readers, working in the Devnagari Optical Character Recognition (DOCR) area. An overview of DOCR systems is presented and the available DOCR techniques are reviewed. The current status of DOCR is discussed and directions for future research are suggested.; Comment: 8 pages, 1 Figure, 8 Tables, Journal paper

Weakly Supervised Learning of Objects, Attributes and their Associations

Shi, Zhiyuan; Yang, Yongxin; Hospedales, Timothy M.; Xiang, Tao
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 31/03/2015 Português
Relevância na Pesquisa
366.25605%
When humans describe images they tend to use combinations of nouns and adjectives, corresponding to objects and their associated attributes respectively. To generate such a description automatically, one needs to model objects, attributes and their associations. Conventional methods require strong annotation of object and attribute locations, making them less scalable. In this paper, we model object-attribute associations from weakly labelled images, such as those widely available on media sharing sites (e.g. Flickr), where only image-level labels (either object or attributes) are given, without their locations and associations. This is achieved by introducing a novel weakly supervised non-parametric Bayesian model. Once learned, given a new image, our model can describe the image, including objects, attributes and their associations, as well as their locations and segmentation. Extensive experiments on benchmark datasets demonstrate that our weakly supervised model performs at par with strongly supervised models on tasks such as image description and retrieval based on object-attribute associations.; Comment: 14 pages, Accepted to ECCV 2014

Supervised Learning of Semantics-Preserving Hashing via Deep Neural Networks for Large-Scale Image Search

Yang, Huei-Fang; Lin, Kevin; Chen, Chu-Song
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 01/07/2015 Português
Relevância na Pesquisa
366.25605%
This paper presents a supervised deep hashing approach that constructs binary hash codes from labeled data for large-scale image search. We assume that semantic labels are governed by a set of latent attributes in which each attribute can be on or off, and classification relies on these attributes. Based on this assumption, our approach, dubbed supervised semantics-preserving deep hashing (SSDH), constructs hash functions as a latent layer in a deep network in which binary codes are learned by the optimization of an objective function defined over classification error and other desirable properties of hash codes. With this design, SSDH has a nice property that classification and retrieval are unified in a single learning model, and the learned binary codes not only preserve the semantic similarity between images but also are efficient for image search. Moreover, SSDH performs joint learning of image representations, hash codes, and classification in a pointwised manner and thus is naturally scalable to large-scale datasets. SSDH is simple and can be easily realized by a slight modification of an existing deep architecture for classification; yet it is effective and outperforms other unsupervised and supervised hashing approaches on several benchmarks and one large dataset comprising more than 1 million images.

Pose Embeddings: A Deep Architecture for Learning to Match Human Poses

Mori, Greg; Pantofaru, Caroline; Kothari, Nisarg; Leung, Thomas; Toderici, George; Toshev, Alexander; Yang, Weilong
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 01/07/2015 Português
Relevância na Pesquisa
366.25605%
We present a method for learning an embedding that places images of humans in similar poses nearby. This embedding can be used as a direct method of comparing images based on human pose, avoiding potential challenges of estimating body joint positions. Pose embedding learning is formulated under a triplet-based distance criterion. A deep architecture is used to allow learning of a representation capable of making distinctions between different poses. Experiments on human pose matching and retrieval from video data demonstrate the potential of the method.

Image Annotation Incorporating Low-Rankness, Tag and Visual Correlation and Inhomogeneous Errors

Hou, Yuqing
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 29/08/2015 Português
Relevância na Pesquisa
366.25605%
Tag-based image retrieval (TBIR) has drawn much attention in recent years due to the explosive amount of digital images and crowdsourcing tags. However, TBIR is still suffering from the incomplete and inaccurate tags provided by users, posing a great challenge for tag-based image management applications. In this work, we proposed a novel method for image annotation, incorporating several priors: Low-Rankness, Tag and Visual Correlation and Inhomogeneous Errors. Highly representative CNN feature vectors are adopt to model the tag-visual correlation and narrow the semantic gap. And we extract word vectors for tags to measure similarity between tags in the semantic level, which is more accurate than traditional frequency-based or graph-based methods. We utilize the accelerated proximal gradient (APG) method to solve our model efficiently. Extensive experiments conducted on multiple benchmark datasets demonstrate the effectiveness and robustness of the proposed method.

A Miniature-Based Image Retrieval System

Islam, Md. Saiful; Ali, Md. Haider
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 19/08/2010 Português
Relevância na Pesquisa
366.25605%
Due to the rapid development of World Wide Web (WWW) and imaging technology, more and more images are available in the Internet and stored in databases. Searching the related images by the querying image is becoming tedious and difficult. Most of the images on the web are compressed by methods based on discrete cosine transform (DCT) including Joint Photographic Experts Group(JPEG) and H.261. This paper presents an efficient content-based image indexing technique for searching similar images using discrete cosine transform features. Experimental results demonstrate its superiority with the existing techniques.; Comment: 9 pages, 4 figures, 4 tables

Cross-Modal Learning via Pairwise Constraints

He, Ran; Zhang, Man; Wang, Liang; Ji, Ye; Yin, Qiyue
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 28/11/2014 Português
Relevância na Pesquisa
366.25605%
In multimedia applications, the text and image components in a web document form a pairwise constraint that potentially indicates the same semantic concept. This paper studies cross-modal learning via the pairwise constraint, and aims to find the common structure hidden in different modalities. We first propose a compound regularization framework to deal with the pairwise constraint, which can be used as a general platform for developing cross-modal algorithms. For unsupervised learning, we propose a cross-modal subspace clustering method to learn a common structure for different modalities. For supervised learning, to reduce the semantic gap and the outliers in pairwise constraints, we propose a cross-modal matching method based on compound ?21 regularization along with an iteratively reweighted algorithm to find the global optimum. Extensive experiments demonstrate the benefits of joint text and image modeling with semantically induced pairwise constraints, and show that the proposed cross-modal methods can further reduce the semantic gap between different modalities and improve the clustering/retrieval accuracy.; Comment: 12 pages, 5 figures, 70 references

Multiple Measurements and Joint Dimensionality Reduction for Large Scale Image Search with Short Vectors - Extended Version

Radenovic, Filip; Jegou, Herve; Chum, Ondrej
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 13/04/2015 Português
Relevância na Pesquisa
366.25605%
This paper addresses the construction of a short-vector (128D) image representation for large-scale image and particular object retrieval. In particular, the method of joint dimensionality reduction of multiple vocabularies is considered. We study a variety of vocabulary generation techniques: different k-means initializations, different descriptor transformations, different measurement regions for descriptor extraction. Our extensive evaluation shows that different combinations of vocabularies, each partitioning the descriptor space in a different yet complementary manner, results in a significant performance improvement, which exceeds the state-of-the-art.; Comment: Extended version of the ICMR 2015 paper

Simultaneous Feature Learning and Hash Coding with Deep Neural Networks

Lai, Hanjiang; Pan, Yan; Liu, Ye; Yan, Shuicheng
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 13/04/2015 Português
Relevância na Pesquisa
369.7336%
Similarity-preserving hashing is a widely-used method for nearest neighbour search in large-scale image retrieval tasks. For most existing hashing methods, an image is first encoded as a vector of hand-engineering visual features, followed by another separate projection or quantization step that generates binary codes. However, such visual feature vectors may not be optimally compatible with the coding process, thus producing sub-optimal hashing codes. In this paper, we propose a deep architecture for supervised hashing, in which images are mapped into binary codes via carefully designed deep neural networks. The pipeline of the proposed deep architecture consists of three building blocks: 1) a sub-network with a stack of convolution layers to produce the effective intermediate image features; 2) a divide-and-encode module to divide the intermediate image features into multiple branches, each encoded into one hash bit; and 3) a triplet ranking loss designed to characterize that one image is more similar to the second image than to the third one. Extensive evaluations on several benchmark image datasets show that the proposed simultaneous feature learning and hash coding pipeline brings substantial improvements over other state-of-the-art supervised or unsupervised hashing methods.; Comment: This paper has been accepted to IEEE International Conference on Pattern Recognition and Computer Vision (CVPR)...

Structure Preserving Large Imagery Reconstruction

Shen, Ju; Yang, Jianjun; Taha-abusneineh, Sami; Payne, Bryson; Hitz, Markus
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 12/09/2014 Português
Relevância na Pesquisa
366.25605%
With the explosive growth of web-based cameras and mobile devices, billions of photographs are uploaded to the internet. We can trivially collect a huge number of photo streams for various goals, such as image clustering, 3D scene reconstruction, and other big data applications. However, such tasks are not easy due to the fact the retrieved photos can have large variations in their view perspectives, resolutions, lighting, noises, and distortions. Fur-thermore, with the occlusion of unexpected objects like people, vehicles, it is even more challenging to find feature correspondences and reconstruct re-alistic scenes. In this paper, we propose a structure-based image completion algorithm for object removal that produces visually plausible content with consistent structure and scene texture. We use an edge matching technique to infer the potential structure of the unknown region. Driven by the estimated structure, texture synthesis is performed automatically along the estimated curves. We evaluate the proposed method on different types of images: from highly structured indoor environment to natural scenes. Our experimental results demonstrate satisfactory performance that can be potentially used for subsequent big data processing, such as image localization...

Knowledge Discovery in the SCADA Databases Used for the Municipal Power Supply System

Kamaev, Valery; Finogeev, Alexey; Finogeev, Anton; Shevchenko, Sergey
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 07/12/2014 Português
Relevância na Pesquisa
366.25605%
This scientific paper delves into the problems related to the develop-ment of intellectual data analysis system that could support decision making to manage municipal power supply services. The management problems of mu-nicipal power supply system have been specified taking into consideration modern tendencies shown by new technologies that allow for an increase in the energy efficiency. The analysis findings of the system problems related to the integrated computer-aided control of the power supply for the city have been given. The consideration was given to the hierarchy-level management decom-position model. The objective task targeted at an increase in the energy effi-ciency to minimize expenditures and energy losses during the generation and transportation of energy carriers to the Consumer, the optimization of power consumption at the prescribed level of the reliability of pipelines and networks and the satisfaction of Consumers has been defined. To optimize the support of the decision making a new approach to the monitoring of engineering systems and technological processes related to the energy consumption and transporta-tion using the technologies of geospatial analysis and Knowledge Discovery in databases (KDD) has been proposed. The data acquisition for analytical prob-lems is realized in the wireless heterogeneous medium...

Orientation covariant aggregation of local descriptors with embeddings

Tolias, Giorgos; Furon, Teddy; Jégou, Hervé
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
369.7336%
Image search systems based on local descriptors typically achieve orientation invariance by aligning the patches on their dominant orientations. Albeit successful, this choice introduces too much invariance because it does not guarantee that the patches are rotated consistently. This paper introduces an aggregation strategy of local descriptors that achieves this covariance property by jointly encoding the angle in the aggregation stage in a continuous manner. It is combined with an efficient monomial embedding to provide a codebook-free method to aggregate local descriptors into a single vector representation. Our strategy is also compatible and employed with several popular encoding methods, in particular bag-of-words, VLAD and the Fisher vector. Our geometric-aware aggregation strategy is effective for image search, as shown by experiments performed on standard benchmarks for image and particular object retrieval, namely Holidays and Oxford buildings.; Comment: European Conference on Computer Vision (2014)

Advances in Human Action Recognition: A Survey

Cheng, Guangchun; Wan, Yiwen; Saudagar, Abdullah N.; Namuduri, Kamesh; Buckles, Bill P.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 23/01/2015 Português
Relevância na Pesquisa
369.7336%
Human action recognition has been an important topic in computer vision due to its many applications such as video surveillance, human machine interaction and video retrieval. One core problem behind these applications is automatically recognizing low-level actions and high-level activities of interest. The former is usually the basis for the latter. This survey gives an overview of the most recent advances in human action recognition during the past several years, following a well-formed taxonomy proposed by a previous survey. From this state-of-the-art survey, researchers can view a panorama of progress in this area for future research.

Statistical mechanics of neural networks and combinatorial optimization problems

Morabito, David L.
Fonte: Rochester Instituto de Tecnologia Publicador: Rochester Instituto de Tecnologia
Tipo: Tese de Doutorado
Português
Relevância na Pesquisa
369.7336%
Local learning neural networks have long been limited by their inability to store correlated patterns. A common parameter used to specify the capacity of a network is

ThumbScan: A lightweight thumbnail search tool

Elinski, Joseph
Fonte: Rochester Instituto de Tecnologia Publicador: Rochester Instituto de Tecnologia
Tipo: Tese de Doutorado
Português
Relevância na Pesquisa
369.7336%
Since the introduction of Windows 95B, Microsoft users have been able to select a thumbnail view of any system folder. This option prompts the operating system to create a miniature preview of each file. By default, these generated images are archived to a local thumbnail database for quick system retrieval. Once an image is placed in the database, it will never be removed. By viewing the contents of thumbnail databases, a forensic investigator can easily examine the past and present media of a given system. Though this cache is not a perfect record, it is a good indicator of media storage locations and habits. For these reasons, we present ThumbScan, an automated search tool for locating and analyzing the archived thumbnails of modern Windows systems.