Copy-Move Forgery Detection (CMFD) Using Deep Learning for Image and Video Forensics.

With the exponential growth of high-quality fake images in social networks and media, it is necessary to develop recognition algorithms for this type of content. One of the most common types of image and video editing consists of duplicating areas of the image, known as the copy-move technique. Traditional image processing approaches manually look for patterns related to the duplicated content, limiting their use in mass data classification. In contrast, approaches based on deep learning have shown better performance and promising results, but they present generalization problems with a high dependence on training data and the need for appropriate selection of hyperparameters. To overcome this, we propose two approaches that use deep learning, a model by a custom architecture and a model by transfer learning. In each case, the impact of the depth of the network is analyzed in terms of precision (P), recall (R) and F1 score. Additionally, the problem of generalization is addressed with images from eight different open access datasets. Finally, the models are compared in terms of evaluation metrics, and training and inference times. The model by transfer learning of VGG-16 achieves metrics about 10% higher than the model by a custom architecture, however, it requires approximately twice as much inference time as the latter.

A dataset of 1050-tampered color and grayscale images (CG-1050).

This paper presents the CG-1050 dataset consisting of 100 original images, 1050 tampered images and their corresponding masks. The dataset is organized into four directories: original images, tampered images, mask images, and a description file. The directory of original images includes 15 color and 85 grayscale images. The directory of tampered images has 1050 images obtained through one of the following type of tampering: copy-move, cut-paste, retouching, and colorizing. The true mask between every pair of original and its tampered image is included in the mask directory (1380 masks). The description file shows the names of the images (i.e., original, tampered and mask), the image description, the photo location, the type of tampering, and the manipulated object in the image. With this dataset, the researchers can train and validate fake image classification methods, either for labelling the tampered image or for forgery pixel-detection.

Educação e sensibilidade: o brincar e o se-movimentar da criança pequena na escola / Education and sensitivity: the play and move yourself the child in school / Educación y sensibilidad: el jugar y el "movimiento" del niño pequeño en la escuela

Este estudo teve como objetivo central investigar como o brincar e o se-movimentar são proporcionados no espaço escolar e de que maneira eles contribuem para a educação da sensibilidade da criança pequena. Foi desenvolvido um estudo de caso que envolveu duas escolas municipais da cidade de Capinzal, SC; uma localizada no interior do município e a outra na cidade. Foi selecionada uma turma de crianças entre 4 e 6 anos de idade em cada escola, que totalizaram 40 crianças. Constatou-se que o brincar e o se-movimentar nas escolas estudadas acontecem muitas vezes por intermédio do controle dos professores, sempre com o intuito de promover uma competição e de chegar a um resultado final. Portanto, nas escolas investigadas, o incentivo à construção de situações que possibilitem o desenvolvimento da sensibilidade recebe pouca importância, o que compromete significativamente a educação da sensibilidade dessas crianças e limita o poder de criação.

Thus, this study had as main objective to investigate about the ways as the play and the move yourself are proposed in the school environment and how they contribute for the sensibility education to the child. First, it was developed a theorical research about the subjets and the fundamental authors, that suply the base for the second part of the study. This other step was an empirical study that involved two municipal schools from the city of Capinzal, SC; one located in the countryside and the other one downtown. It was chosen a class of chuildren from 4 to 6 years old in each school, that totaling 40 children. Therefore, in the investigated schools, the stimulus to situations construction that enable the sensibility development receives little importance, what commits meaningly the sensibility education of these children and limits the creation' power.

Este estudio tuvo como objetivo central investigar cómo el juego y el movimiento se proporcionan en el espacio escolar y de qué manera contribuyen a la educación de la sensibilidad del niño pequeño. Se desarrolló un estudio de caso que involucró dos escuelas municipales de la ciudad de Capinzal, SC; una ubicada en el interior del municipio y la otra en la ciudad. Se seleccionó una clase de niños entre 4 y 6 años de edad en cada escuela, que totalizaron 40 niños. Se constató que el jugar y el mudanza en las escuelas estudiadas ocurren muchas veces por intermedio del control de los profesores, siempre con el propósito de promover una competición y de llegar a un resultado final. Por lo tanto, en las escuelas investigadas, el incentivo a la construcción de situaciones que posibiliten el desarrollo de la sensibilidad recibe poca importancia, lo que compromete significativamente la educación de la sensibilidad de esos niños y limita el poder de creación.

Evaluation of Fracture Resistance of Orthodontic Mini-implants in the Transmucosal Profile Region.

AIM: This study sought to compare the fracture resistance of three trademarked orthodontic mini-implants in the transmucosal profile region. Thirty-six mini-implants of three different brands, separated into groups I, II and III, were tested. Each group consisted of 12 mini-implants of 6 mm in length. The mean diameter and length of the transmucosal profile of the mini-implants were 1.90 and 2.0 mm in group I, 1.77 and 1.0 mm in group II and 1.50 and 1.0 mm in group III, respectively. The tests were performed on a universal testing machine in compression mode, with a 2,000 kgf load, a speed of 4.0 mm per minute and a chisel-shaped active tip, which acted cross-sectionally on the transmucosal profile. Single-criterion analysis of variance was used to compare the three brands. A significance level of 5% and test power of 80% were adopted. The mean fracture resistance achieved by the mini-implants was 172.03 ± 25.59 N for group I, 162.35 ± 30.81 N for group II and 139.69 ± 42.99 N for group III. There was no statistically significant difference in mean fracture resistance among the tested mini-implant brands. CONCLUSION: The transmucosal profile diameter does not seem to be a deciding factor in the choice of mini-implants to minimize the risk of fractures. CLINICAL SIGNIFICANCE: Although being an in vitro study it is possible to believe that this new brand has a very satisfactory resistance to fracture and enables its use with great efficiency.

Eco-etología básica del caracol rosa Strombus gigas (Mesogastropoda: Strombidae), en Xel-Há, Yucatán, Caribe mexicano / Basic eco-ethology of the queen conch, Strombus gigas (Mesogastropoda: Strombidae) in Xel-Há, Yucatán, Mexican Caribbean

The queen conch Strombus gigas is an important fishery in the Caribbean, whose populations are currently overexploited. Since the decade of 1980 there have been several studies on aquaculture, resource management and area rehabilitation. However, little is known about its behavior in a natural environment and the influence of environmental parameters. Monthly surveys, from January to November 2012 were conducted in in Xel Ha, to observe and quantify six behaviors of S. gigas: rest, feeding, movement, burying, copulation and spawning. The observations were made every hour from 8h to 17h by free diving through three transects with three replicates each. Each behavior was observed 90 times each month. Salinity, temperature and dissolved oxygen were registered at the bottom. We found the highest number of snails at rest in July and the lowest in March and September. Feeding and movements had a peak in August. Most buried in October and November. Copulation was first observed on March with a peak in June and July to October’s spawning. In daytime observations restingt had a peak at 8h; feeding and moving at 12 to 17h. Copulation and spawning did not have a clear pattern. Variations between months and hours (resting, feeding, moving and buried) were significant (p<0.05). Resting correlated with temperature and being buried with oxygen level (r=-0.5803; p=0.0536). Feeding and moving correlated with temperature and salinity. These results should be useful for the conservation, restoration and aquaculture programs. Rev. Biol. Trop. 62 (Suppl. 3): 215-222. Epub 2014 September 01.

El caracol rosa Strombus gigas tiene importancia pesquera en el Caribe, cuyas poblaciones se encuentran sobreexplotadas. Desde la década de 1980 se han desarrollado estudios de acuacultura, manejo del recurso y rehabilitación de áreas con la finalidad de proteger e incrementar sus poblaciones. Sin embargo, poco se sabe sobre el comportamiento del caracol rosa en su medio natural y la influencia de los parámetros ambientales. Mensualmente de enero a noviembre de 2012 en la caleta de Xel Há se observaron y cuantificaron seis comportamientos de S. gigas: reposo, alimentación, movimiento, cópula, enterrados y desove. Las observaciones se realizaron cada hora de 8h a 17h por medio de buceo libre en tres transectos con tres repeticiones cada uno. Cada comportamiento fue observado 90 veces cada mes. Se registraron datos de salinidad, temperatura y oxígeno disuelto en el fondo. El comportamiento anual de S. gigas presentó el mayor número de caracoles en reposo en julio. La alimentación y el movimiento tuvieron un máximo en agosto. La mayoría de caracoles enterrados se encontró en octubre y noviembre. La cópula comenzó a observarse en marzo con un máximo en junio y el desove de julio a octubre. En las observaciones diurnas e independientemente de los meses, el reposo tuvo un pico a las 8h, alimentación a las 12 y movimiento a las 17h. La cópula y el desove no presentaron un patrón en su comportamiento. Existieron variaciones significativas entre meses y horas (reposo, alimentación, movimiento y enterrado) (p<0.05). El reposo se correlacionó con la temperatura y los enterrados con el oxígeno (r=-0.5803; p=0.0536). La alimentación con temperatura, salinidad y oxígeno. El movimiento con temperatura y salinidad. Estos resultados son útiles para programas de conservación, restauración y cultivo de la especie.