A scalable re-ranking method for content-based image retrieval

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Image Re-Ranking Acceleration on GPUs

Huge image collections are becoming available lately. In this scenario, the use of Content-Based Image Retrieval (CBIR) systems has emerged as a promising approach to support image searches. The objective of CBIR systems is to retrieve the most similar images in a collection, given a query image, by taking into account image visual properties such as texture, color, and shape. In these systems, the effectiveness of the retrieval process depends heavily on the accuracy of ranking approaches. Recently, re-ranking approaches have been proposed to improve the effectiveness of CBIR systems by taking into account the relationships among images. The re-ranking approaches consider the relationships among all images in a given dataset. These approaches typically demands a huge amount of computational power, which hampers its use in practical situations. On the other hand, these methods can be massively parallelized. In this paper, we propose to speedup the computation of the RL-Sim algorithm, a recently proposed image re-ranking approach, by using the computational power of Graphics Processing Units (GPU). GPUs are emerging as relatively inexpensive parallel processors that are becoming available on a wide range of computer systems. We address the image re-ranking performance challenges by proposing a parallel solution designed to fit the computational model of GPUs. We conducted an experimental evaluation considering different implementations and devices. Experimental results demonstrate that significant performance gains can be obtained. Our approach achieves speedups of 7x from serial implementation considering the overall algorithm and up to 36x on its core steps.

Semi-supervised learning for relevance feedback on image retrieval tasks

Relevance feedback approaches have been established as an important tool for interactive search, enabling users to express their needs. However, in view of the growth of multimedia collections available, the user efforts required by these methods tend to increase as well, demanding approaches for reducing the need of user interactions. In this context, this paper proposes a semi-supervised learning algorithm for relevance feedback to be used in image retrieval tasks. The proposed semi-supervised algorithm aims at using both supervised and unsupervised approaches simultaneously. While a supervised step is performed using the information collected from the user feedback, an unsupervised step exploits the intrinsic dataset structure, which is represented in terms of ranked lists of images. Several experiments were conducted for different image retrieval tasks involving shape, color, and texture descriptors and different datasets. The proposed approach was also evaluated on multimodal retrieval tasks, considering visual and textual descriptors. Experimental results demonstrate the effectiveness of the proposed approach.

HTS: A new shape descriptor based on Hough Transform

In this paper we propose a novel method for shape analysis called HTS (Hough Transform Statistics), which uses statistics from Hough Transform space in order to characterize the shape of objects in digital images. Experimental results showed that the HTS descriptor is robust and presents better accuracy than some traditional shape description methods. Furthermore, HTS algorithm has linear complexity, which is an important requirement for content based image retrieval from large databases. © 2013 IEEE.

Unsupervised manifold learning using Reciprocal kNN Graphs in image re-ranking and rank aggregation tasks

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

HTS and HTSn: New shape descriptors based on Hough transform statistics

With the widespread proliferation of computers, many human activities entail the use of automatic image analysis. The basic features used for image analysis include color, texture, and shape. In this paper, we propose a new shape description method, called Hough Transform Statistics (HTS), which uses statistics from the Hough space to characterize the shape of objects or regions in digital images. A modified version of this method, called Hough Transform Statistics neighborhood (HTSn), is also presented. Experiments carried out on three popular public image databases showed that the HTS and HTSn descriptors are robust, since they presented precision-recall results much better than several other well-known shape description methods. When compared to Beam Angle Statistics (BAS) method, a shape description method that inspired their development, both the HTS and the HTSn methods presented inferior results regarding the precision-recall criterion, but superior results in the processing time and multiscale separability criteria. The linear complexity of the HTS and the HTSn algorithms, in contrast to BAS, make them more appropriate for shape analysis in high-resolution image retrieval tasks when very large databases are used, which are very common nowadays. (C) 2014 Elsevier Inc. All rights reserved.

Análise de formas planas em imagens digitais: uma nova abordagem baseada na Transformada de Hough

Pós-graduação em Ciência da Computação - IBILCE

JSEG-based image segmentation in computer vision for agricultural mobile robot navigation

This project aims to apply image processing techniques in computer vision featuring an omnidirectional vision system to agricultural mobile robots (AMR) used for trajectory navigation problems, as well as localization matters. To carry through this task, computational methods based on the JSEG algorithm were used to provide the classification and the characterization of such problems, together with Artificial Neural Networks (ANN) for pattern recognition. Therefore, it was possible to run simulations and carry out analyses of the performance of JSEG image segmentation technique through Matlab/Octave platforms, along with the application of customized Back-propagation algorithm and statistical methods in a Simulink environment. Having the aforementioned procedures been done, it was practicable to classify and also characterize the HSV space color segments, not to mention allow the recognition of patterns in which reasonably accurate results were obtained.

OPF-MRF: Optimum-path forest and Markov random fields for contextual-based image classification

Some machine learning methods do not exploit contextual information in the process of discovering, describing and recognizing patterns. However, spatial/temporal neighboring samples are likely to have same behavior. Here, we propose an approach which unifies a supervised learning algorithm - namely Optimum-Path Forest - together with a Markov Random Field in order to build a prior model holding a spatial smoothness assumption, which takes into account the contextual information for classification purposes. We show its robustness for brain tissue classification over some images of the well-known dataset IBSR. © 2013 Springer-Verlag.

Characterization of texture in image of skin lesions by support vector machine

Due to the increased incidence of skin cancer, computational methods based on intelligent approaches have been developed to aid dermatologists in the diagnosis of skin lesions. This paper proposes a method to classify texture in images, since it is an important feature for the successfully identification of skin lesions. For this is defined a feature vector, with the fractal dimension of images through the box-counting method (BCM), which is used with a SVM to classify the texture of the lesions in to non-irregular or irregular. With the proposed solution, we could obtain an accuracy of 72.84%. © 2012 AISTI.

IFTrace: Video segmentation of deformable objects using the Image Foresting Transform

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

O ensino da digestão-nutrição na era das refeições rápidas e do culto ao corpo

Mudanças notáveis nos hábitos alimentares, acompanhadas de práticas fisioculturistas intensas, são a tônica dos dias atuais, com registros de carências nutricionais e de obesidade bastante preocupantes, do ponto de vista da saúde pública, entre crianças, jovens e adultos. Mas o que conhecem as crianças e os adolescentes sobre o processo de digestão-nutrição, os conceitos básicos envolvidos e as condutas alimentares adequadas à boa saúde humana? Como é desenvolvido esse tema nas escolas públicas e particulares de ensino? Tais questionamentos desencadearam um estudo sobre a natureza das práticas desenvolvidas por professores de ciências e biologia e o conhecimento apresentado por alunos de escolas públicas e particulares. Os resultados revelaram inadequação no tratamento metodológico de ensino do processo de digestão e conceitos envolvidos nesse tema, que levam os alunos ao desinteresse e a manterem praticamente inalterados os conhecimentos ordinários que possuem. O processo de digestão e nutrição, bem como suas implicações para a saúde, configuraram-se como fenômenos desvinculados do aluno, à semelhança do que observamos nos livros didáticos por eles utilizados. A dinâmica das inter-relações alimentares entre seres vivos são superficialmente consideradas em ecologia e passam ao largo das adaptações comportamentais, morfológicas e fisiológicas envolvidas. Considerando esses resultados, propõe-se conteúdo baseado em abordagem ecológica, voltado para determinadas atividades experimentais, jogos e interações coevolutivas de seres vivos - aspectos biológicos e sociais, para o despertar de posturas reflexivas e críticas diante das transformações sociais em curso e de nossas necessidades biológicas no que se refere à alimentação e saúde.

Content of essential oil of fennel seeds in two different stages of development

This experiment was carried out at Plant Production Sector, Agronomical Science College-Botucatu, S.P., Brazil, in March, 2000. The aim of this assay was to determine the yield of essential oil of fennel (Foeniculum vulgare Miller) in different stages of development. Essential oils were prepared by hydrodistillation from the seeds using of Clevenger apparatus. The water utilized for the extraction of essential oil was sufficient to cover 100 g of seeds and the mixture was distilled for three hours. The volume of essential oil in the graduated side -arm of Clevenger apparatus was observed. There were no significative difference statistic was observed (Tukey 5%) in percentage (v/m) of oil content, based on dry weight of green seeds compared with dry weight of mature seeds, when they were harvested in two different stages of development. There was significative difference statistic between data obtained of humidity content of green seeds when these were compared with mature seeds. These results shows that others specifics studies about adaptation of fennel in tropical conditions are necessary, because the obtained data were different of data described on literature.

Land cover classification of Lago Grande de Curuai floodplain (Amazon, Brazil) using multi-sensor and image fusion techniques

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Perdas endógenas e coeficientes de absorção aparente e real do magnésio em caprinos

Os objetivos deste trabalho foram determinar a absorção aparente, estimar as perdas endógenas fecais e a absorção real do Mg e determinar a ingestão ad libitum da água de beber e a concentração de Mg no soro sangüíneo de caprinos da raças Anglonubiana (AN) e Saanen (SN). Foram usados doze caprinos, seis de cada raça, com 19,8 kg PV médio. Dietas semipurificadas (baixo teor de Mg) à base de quirera de arroz, glúten de milho e celulose foram suplementadas com MgO, para se obterem os níveis de 0,05 (sem supplementação) 0,20 e 0,35% Mg (%MS). Os níveis de Mg influenciaram os coeficientes de absorção aparente de Mg e Ca, com valores médios de 57,8; 73,9; e 73,2% para Mg e 55,7; 39,6; e 49,5% para Ca, para dietas com níveis 0,05; 0,20; e 0,35% de Mg, respectivamente. Entretanto, para os coeficientes de absorção aparente de P, Na e K, não houve efeito de níveis de Mg na dieta. Os resultados de absorção real de Mg apresentaram interação de níveis de Mg e raças. A média para raça NA, no nível 0,05% Mg, foi de 61,0% e para os níveis 0,20 e 0,35% Mg, 77,2 e 73,2%, respectivamente. Entretanto, para a raça SN, as médias foram 73,3; 75,5; e 76,0%, para os mesmos níveis, sem diferenças. A digestibilidade de matéria seca, proteína bruta e extrato não-nitrogenado diminuiu com os níveis crescentes de Mg nas dietas. As excreções fecais (7,0; 20,8; e 34,4 mg/kg PV0,75.d) e urinárias (3,9; 30,8; e 44,6 mg/kg PV0,75.d) de Mg elevaram-se com o aumento dos níveis crescentes de Mg nas dietas. Houve, também, influência dos níveis de Mg dietético sobre as concentrações de Mg do soro sangüíneo (1,74; 2,23; e 2,80 mg/dL para níveis de 0,05; 0,20; e 0,35% de Mg, respectivamente).