Advanced search


Knowledge area




173 results, page 1 of 10

Semantic cohesion for image annotation and retrieval

Hugo Jair Escalante Balderas Luis Enrique Sucar Succar Manuel Montes y Gómez (2012)

We present methods for image annotation and retrieval based on semantic cohesion among terms. On the one hand, we propose a region labeling technique that assigns an image the label that maximizes an estimate of semantic cohesion among candidate labels associated to regions in segmented images. On the other hand, we propose document representation techniques based on semantic cohesion among multimodal terms that compose images. We report experimental results that show the effectiveness of the proposed techniques. Additionally, we describe an extension of a benchmark collection for evaluation of the proposed techniques.

Presentamos métodos para la anotación y recuperación de imágenes que se basan en la cohesión semántica entre términos. Por un lado, proponemos una técnica para etiquetar regiones que asigna a cada imagen el conjunto de etiquetas que maximiza un estimado de la cohesión semántica entre estas. Por otro lado, proponemos métodos para representar imágenes anotadas que se basan en la cohesión semántica entre términos multimodales que aparecen en las imágenes. Reportamos resultados experimentales que muestran la efectividad de las técnicas propuestas. Adicionalmente describimos la extensión que realizamos a una colección estándar para la evaluación de los métodos propuestos.

Article

Automatic image annotation Region labeling Multimedia image retrieval Ground truth data creation Anotación automática de imágenes Etiquetado de regiones Recuperación multimodal de imágenes Creación de datos para evaluación CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA MATEMÁTICAS CIENCIA DE LOS ORDENADORES CIENCIA DE LOS ORDENADORES

The segmented and annotated IAPR TC-12 benchmark

HUGO JAIR ESCALANTE BALDERAS CARLOS ARTURO HERNANDEZ GRACIDAS JESUS ANTONIO GONZALEZ BERNAL AURELIO LOPEZ LOPEZ MANUEL MONTES Y GOMEZ EDUARDO FRANCISCO MORALES MANZANARES LUIS ENRIQUE SUCAR SUCCAR LUIS VILLASEÑOR PINEDA (2009)

Automatic image annotation (AIA), a highly popular topic in the field of information retrieval research, has experienced significant progress within the last decade. Yet, the lack of a standardized evaluation platform tailored to the needs of AIA, has hindered effective evaluation of its methods, especially for region-based AIA. Therefore in this paper, we introduce the segmented and annotated IAPR TC-12 benchmark; an extended resource for the evaluation of AIA methods as well as the analysis of their impact on multimedia information retrieval. We describe the methodology adopted for the manual segmentation and annotation of images, and present statistics for the extended collection. The extended collection is publicly available and can be used to evaluate a variety of tasks in addition to image annotation. We also propose a soft measure for the evaluation of annotation performance and identify future research areas in which this extended test collection is likely to make a contribution.

Article

Data set creation Ground truth collection Evaluation metrics Automatic image annotation Image retrieval CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA MATEMÁTICAS CIENCIA DE LOS ORDENADORES

The segmented and annotated IAPR TC-12 benchmark

HUGO JAIR ESCALANTE BALDERAS CARLOS ARTURO HERNANDEZ GRACIDAS JESUS ANTONIO GONZALEZ BERNAL AURELIO LOPEZ LOPEZ MANUEL MONTES Y GOMEZ EDUARDO FRANCISCO MORALES MANZANARES LUIS ENRIQUE SUCAR SUCCAR LUIS VILLASEÑOR PINEDA (2010)

Automatic image annotation (AIA), a highly popular topic in the field of information retrieval research, has experienced significant progress within the last decade. Yet, the lack of a standardized evaluation platform tailored to the needs of AIA, has hindered effective evaluation of its methods, especially for region-based AIA. Therefore in this paper, we introduce the segmented and annotated IAPR TC-12 benchmark; an extended resource for the evaluation of AIA methods as well as the analysis of their impact on multimedia information retrieval. We describe the methodology adopted for the manual segmentation and annotation of images, and present statistics for the extended collection. The extended collection is publicly available and can be used to evaluate a variety of tasks in addition to image annotation. We also propose a soft measure for the evaluation of annotation performance and identify future research areas in which this extended test collection is likely to make a contribution.

Article

Data set creation Ground truth collection Evaluation metrics Automatic image annotation Image retrieval CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA MATEMÁTICAS CIENCIA DE LOS ORDENADORES CIENCIA DE LOS ORDENADORES

An energy-based model for region-labeling

Hugo Jair Escalante Balderas Manuel Montes y Gómez Luis Enrique Sucar Succar (2011)

This paper introduces an energy-based model (EBM) for region labeling that takes advantage of both context and semantics present in segmented images.The proposed method refines the output of multiclass classification methods that are based on the one-vs-all (OVA) formulation. Intuitively, the EBM maximizes the semantic cohesion among labels assigned to neighboring regions; that is, a tradeoff between label-association information and the predictions from the base classifier. Additionally, we study the suitability of OVA classification for the region labeling task. We report experimental results of our methods in 12 heterogeneous data sets that have been used for the evaluation of different tasks besides region labeling. On the one hand, our results reveal that the OVA approach offers an important potential of improvement in terms of labeling performance that can be exploited by refinement techniques similar to ours. On the other hand, experimental results show that our EBM improves the labeling provided by the base classifier. The EBM is highly efficient and it can be applied without modifications to different data sets. The heterogeneity of the considered databases shows the generality of our approach and its robustness to different scenarios. Our results are superior to other techniques that have been tested in the same collections. Furthermore, results on image retrieval show that the labels generated with our EBM can be helpful for annotation-based image retrieval.

Article

Region labeling Energy-based modeling Random forest Image annotation Object recognition CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA MATEMÁTICAS CIENCIA DE LOS ORDENADORES CIENCIA DE LOS ORDENADORES

Multi-class particle swarm model selection for automatic image annotation

Hugo Jair Escalante Balderas Manuel Montes y Gómez Luis Enrique Sucar Succar (2012)

This article describes the application of particle swarm model selection (PSMS) to the problem of automatic image annotation (AIA). PSMS can be considered a black-box tool for the selection of effective classifiers in binary classification problems. We face the AIA problem as one of multi-class classification, considering a one-vs-all (OVA) strategy. OVA makes a multi-class problem into a series of binary classification problems, each of which deals with whether a region belongs to a particular class or not. We use PSMS to select the models that compose the OVA classifier and propose a new technique for making multi-class decisions from the selected classifiers. This way, effective classifiers can be obtained in acceptable times; specific methods for preprocessing, feature selection and classification are selected for each class; and, most importantly, very good annotation performance can be obtained. We present experimental results in six data sets that give evidence of the validity of our approach; to the best of our knowledge the results reported herein are the best obtained so far in the data sets we consider. It is important to emphasize that despite the application domain we consider is AIA, nothing restricts us of applying the methods described in this article to any other multi-class classification problem.

Article

Classification Particle swarm optimization Particle swarm model selection Machine learning Image annotation Object recognition CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA MATEMÁTICAS CIENCIA DE LOS ORDENADORES CIENCIA DE LOS ORDENADORES

Multimodal indexing based on semantic cohesion for image retrieval

Hugo Jair Escalante Balderas Manuel Montes y Gómez Luis Enrique Sucar Succar (2012)

This paper introduces two novel strategies for representing multimodal images with application to multimedia image retrieval. We consider images that are composed of both text and labels: while text describes the image content at a very high semantic level (e.g., making reference to places, dates or events), labels provide a mid-level description of the image (i.e., in terms of the objects that can be seen in the image). Accordingly, the main assumption of this work is that by combining information from text and labels we can develop very effective retrieval methods. We study standard information fusion techniques for combining both sources of information. However, whereas the performance of such techniques is highly competitive, they cannot capture effectively the content of images. Therefore, we propose two novel representations for multimodal images that attempt to exploit the semantic cohesion among terms from different modalities. Such representations are based on distributional term representations widely used in computational linguistics. Under the considered representations the content of an image is modeled by a distribution of co-occurrences over terms or of occurrences over other images, in such a way that the representation can be considered an expansion of the multimodal terms in the image. We report experimental results using the SAIAPR TC12 benchmark on two sets of topics used in ImageCLEF competitions with manually and automatically generated labels. Experimental results show that the proposed representations outperform significantly both, standard multimodal techniques and unimodal methods. Results on manually assigned labels provide an upper bound in the retrieval performance that can be obtained, whereas results with automatically generated labels are encouraging. The novel representations are able to capture more effectively the content of multimodal images. We emphasize that although we have applied our representations to multimedia image retrieval the same formulation can be adopted for modeling other multimodal documents (e.g., videos).

Article

Multimedia image retrieval Image annotation Distributional term representations Semantic cohesion modeling CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA MATEMÁTICAS CIENCIA DE LOS ORDENADORES CIENCIA DE LOS ORDENADORES

Secretion of an argonaute protein by a parasitic nematode and the evolution of its siRNA guides

Wang-ngai Chow Georgios Koutsovoulos CESARE MOISES OVANDO VAZQUEZ Kyriaki Neophytou JOSE ROBERTO BERMUDEZ BARRIENTOS Dominik Laetsch Elaine Robertson Sujai Kumar Julie M Claycomb Mark Blaxter Cei Abreu_Goodger Amy Buck (2019)

"Extracellular RNA has been proposed to mediate communication between cells and organisms however relatively little is understood regarding how specific sequences are selected for export. Here, we describe a specific Argonaute protein (exWAGO) that is secreted in extracellular vesicles (EVs) released by the gastrointestinal nematode Heligmosomoides bakeri, at multiple copies per EV. Phylogenetic and gene expression analyses demonstrate exWAGO orthologues are highly conserved and abundantly expressed in related parasites but highly diverged in free-living genus Caenorhabditis. We show that the most abundant small RNAs released from the nematode parasite are not microRNAs as previously thought, but rather secondary small interfering RNAs (siRNAs) that are produced by RNA-dependent RNA Polymerases. The siRNAs that are released in EVs have distinct evolutionary properties compared to those resident in free-living or parasitic nematodes. Immunoprecipitation of exWAGO demonstrates that it specifically associates with siRNAs from transposons and newly evolved repetitive elements that are packaged in EVs and released into the host environment. Together this work demonstrates molecular and evolutionary selectivity in the small RNA sequences that are released in EVs into the host environment and identifies a novel Argonaute protein as the mediator of this."

Article

Web server RNA Annotation BIOLOGÍA Y QUÍMICA CIENCIAS DE LA VIDA BIOQUÍMICA BIOQUÍMICA

Análisis y clasificación de firmas espectrales utilizando técnicas de aprendizaje automático.

ANA PATRICIA (2019)

The study of spectral signatures makes it possible to identify different objects of earth and sky, present in digital images. The elements that are in it make it have a particular feature, it is analogous to a fingerprint. Researcher’s study its spectral signature, which is made up of the physical, chemical, biological and wavelength properties of electromagnetic energy. It has multiple applications in different areas, such as geoscience and astronomy. In geoscience, the spectra are captured by satellites, once the solar radiation has penetrated the atmosphere, each type of surface interacts with the radiation in a way that absorbs wavelengths and reflects different ones. In astronomy, the spectra of the stars are captured by sensors, the electromagnetic radiation that comes from the stars emits wavelengths of the spectrum and several absorption lines. In relation to the study of stellar spectra, the National Institute of Astrophysics, Optics, and Electronics has at its disposal the set of digitized images of the astronomical plates that were taken with Schmidt Camera of Tonantzintla, from 1944 to 1994, during this period observations, it sampled the entire center of the galaxy and one of its poles. The collection of digitized images has been used in other works; researchers have dedicated to the study of stellar spectra, visually and automatically. With respect to automatic methods, in the present thesis work, a set of data is proposed, obtained from algorithms of extraction and selection of feature which results in the spectral signature of each stellar object. In this way, classification of stellar spectra of the proposed data set was made, using machine learning. The objective is to classify the largest number of stellar spectra and increase the classes and subclasses reported in previous works. To finish with the proposed, the results are reported up to 90.32% accuracy, for the main classes and subclasses of spectral type.

El estudio de firmas espectrales, hace posible la identificación de distintos objetos de la tierra y del cielo, presentes en imágenes digitales. Los elementos que en ella se encuentran la hacen poseer características particulares que contiene información sobre la materia con la que interaccionó; es análoga a una huella digital. Los investigadores estudian firmas espectrales, que representan propiedades físicas, químicas y biológicas, a través de su interacción con la radiación emite determinadas longitudes de onda del espectro electromagnético. Tiene múltiples aplicaciones en diferentes áreas, tales como la geociencia y la astronomía. En geociencia, los espectros son captados por satélites. Una vez que la radiación solar ha traspasado la atmósfera, cada tipo de superficie interactúa con la radiación de manera que absorbe longitudes de onda y refleja otras diferentes. En astronomía, los espectros estelares son captados por sensores. La radiación electromagnética que proviene de las estrellas en las que llega poca o ninguna radiación, es emitida en determinadas longitudes de onda del espectro y tiene líneas de absorción. En relación con el estudio de espectros estelares, el Instituto Nacional de Astrofísica, Óptica y Electrónica tiene a su resguardo el acervo de imágenes digitalizadas de las placas astronómicas que fueron tomadas con la Cámara Schmidt de Tonantzintla, desde 1944 hasta 1994, durante este período se realizaron observaciones del cielo, donde se muestreo todo el centro de la galaxia y uno de sus polos. El acervo de imágenes digitalizadas, se ha utilizado en otros trabajos; investigadores se han dedicado al estudio de espectros estelares, tanto de forma visual como automática. Con respecto a métodos automáticos, en el presente trabajo de tesis se propone un conjunto de datos, obtenido de algoritmos de extracción y selección de características que da como resultado la firma espectral de cada objeto estelar. De este modo, se realizó una clasificación de espectros estelares del conjunto de datos propuesto, utilizando técnicas de aprendizaje automático. El objetivo es clasificar el mayor número de espectros estelares e incrementar las clases y subclases reportadas en trabajos previos. Para finalizar con lo propuesto, se reportan los resultados hasta un 90.32% de exactitud, para las clases y subclases principales de tipo espectral.

Master thesis

Techniques Learning Automatic CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA CIENCIAS DE LA TIERRA Y DEL ESPACIO CIENCIAS DEL ESPACIO CIENCIAS DEL ESPACIO

FPGA-based educational platform for real-time image processing experiments

JUAN MANUEL RAMIREZ CORTES MARIA DEL PILAR GOMEZ GIL VICENTE ALARCON AQUINO Jorge Martinez_Carballido EMMANUEL MORALES FLORES (2010)

In this paper, an implementation of an educational platform for real-time linear and morphological image filtering using a FPGA NexysII, Xilinx®, Spartan 3E, is described. The system is connected to a USB port of a personal computer, which in that way form a powerful and low-cost design station for educational purposes. The FPGA-based system is accessed through a MATLAB graphical user interface, which handles the communication setup and data transfer. The system allows the students to perform comparisons between results obtained from MATLAB simulations and FPGA-based real-time processing. Concluding remarks derived from course evaluations and lab reports are presented.

Article

Image Processing Hardware Education Filtering CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA FÍSICA ELECTRÓNICA ELECTRÓNICA

Modeling of The Determinants of The Image of The Destination As A Subsystem of The Peri-Urban Mobility Policies, The Transport of Zero Emissions of Carbon Dioxide To The Atmosphere And The Habitus of Transfer

FRANCISCO RUBEN SANDOVAL VAZQUEZ JOSE MARCOS BUSTOS AGUAYO MARGARITA JUAREZ NAJERA ALFREDO BARRERA MARIA LUISA QUINTERO SOTO Cruz García Lirios (2018)

The objective of the present work was to establish an exploratory factorial structure of the peri-urban mobility habitus. A non-experimental study was carried out with a non-probabilistic selection of 345 users of the metro public transportation system of Mexico City. The results show that the motivation of the trip is the determinant of the image of the destination, agreeing with the most recent findings, but complementary to the studies carried out around the habitus of peri-urban mobility.

Article

mobility emissions transport habitus image BIOLOGÍA Y QUÍMICA