MAST: multi-script annotation toolkit for scenic text

This paper describes a semi-automatic tool for annotation of multi-script text from natural scene images. To our knowledge, this is the maiden tool that deals with multi-script text or arbitrary orientation. The procedure involves manual seed selection followed by a region growing process to segment each word present in the image. The threshold for region growing can be varied by the user so as to ensure pixel-accurate character segmentation. The text present in the image is tagged word-by-word. A virtual keyboard interface has also been designed for entering the ground truth in ten Indic scripts, besides English. The keyboard interface can easily be generated for any script, thereby expanding the scope of the toolkit. Optionally, each segmented word can further be labeled into its constituent characters/symbols. Polygonal masks are used to split or merge the segmented words into valid characters/symbols. The ground truth is represented by a pixel-level segmented image and a '.txt' file that contains information about the number of words in the image, word bounding boxes, script and ground truth Unicode. The toolkit, developed using MATLAB, can be used to generate ground truth and annotation for any generic document image. Thus, it is useful for researchers in the document image processing community for evaluating the performance of document analysis and recognition techniques. The multi-script annotation toolokit (MAST) is available for free download.

Recognition of Kannada characters extracted from scene images

In this paper, we describe a method for feature extraction and classification of characters manually isolated from scene or natural images. Characters in a scene image may be affected by low resolution, uneven illumination or occlusion. We propose a novel method to perform binarization on gray scale images by minimizing energy functional. Discrete Cosine Transform and Angular Radial Transform are used to extract the features from characters after normalization for scale and translation. We have evaluated our method on the complete test set of Chars74k dataset for English and Kannada scripts consisting of handwritten and synthesized characters, as well as characters extracted from camera captured images. We utilize only synthesized and handwritten characters from this dataset as training set. Nearest neighbor classification is used in our experiments.

Large scale features and assessment of spatial scale correspondence between TMPA and IMD rainfall datasets over Indian landmass

Daily rainfall datasets of 10 years (1998-2007) of Tropical Rainfall Measuring Mission (TRMM) Multi-satellite Precipitation Analysis (TMPA) version 6 and India Meteorological Department (IMD) gridded rain gauge have been compared over the Indian landmass, both in large and small spatial scales. On the larger spatial scale, the pattern correlation between the two datasets on daily scales during individual years of the study period is ranging from 0.4 to 0.7. The correlation improved significantly (similar to 0.9) when the study was confined to specific wet and dry spells each of about 5-8 days. Wavelet analysis of intraseasonal oscillations (ISO) of the southwest monsoon rainfall show the percentage contribution of the major two modes (30-50 days and 10-20 days), to be ranging respectively between similar to 30-40% and 5-10% for the various years. Analysis of inter-annual variability shows the satellite data to be underestimating seasonal rainfall by similar to 110 mm during southwest monsoon and overestimating by similar to 150 mm during northeast monsoon season. At high spatio-temporal scales, viz., 1 degrees x1 degrees grid, TMPA data do not correspond to ground truth. We have proposed here a new analysis procedure to assess the minimum spatial scale at which the two datasets are compatible with each other. This has been done by studying the contribution to total seasonal rainfall from different rainfall rate windows (at 1 mm intervals) on different spatial scales (at daily time scale). The compatibility spatial scale is seen to be beyond 5 degrees x5 degrees average spatial scale over the Indian landmass. This will help to decide the usability of TMPA products, if averaged at appropriate spatial scales, for specific process studies, e.g., cloud scale, meso scale or synoptic scale.

Dynamic multi-relational Chinese restaurant process for analyzing influences on users in social media

We study the problem of analyzing influence of various factors affecting individual messages posted in social media. The problem is challenging because of various types of influences propagating through the social media network that act simultaneously on any user. Additionally, the topic composition of the influencing factors and the susceptibility of users to these influences evolve over time. This problem has not been studied before, and off-the-shelf models are unsuitable for this purpose. To capture the complex interplay of these various factors, we propose a new non-parametric model called the Dynamic Multi-Relational Chinese Restaurant Process. This accounts for the user network for data generation and also allows the parameters to evolve over time. Designing inference algorithms for this model suited for large scale social-media data is another challenge. To this end, we propose a scalable and multi-threaded inference algorithm based on online Gibbs Sampling. Extensive evaluations on large-scale Twitter and Face book data show that the extracted topics when applied to authorship and commenting prediction outperform state-of-the-art baselines. More importantly, our model produces valuable insights on topic trends and user personality trends beyond the capability of existing approaches.

Measurement Based Impromptu Deployment of a Multi-Hop Wireless Relay Network

We study the problem of optimal sequential (''as-you-go'') deployment of wireless relay nodes, as a person walks along a line of random length (with a known distribution). The objective is to create an impromptu multihop wireless network for connecting a packet source to be placed at the end of the line with a sink node located at the starting point, to operate in the light traffic regime. In walking from the sink towards the source, at every step, measurements yield the transmit powers required to establish links to one or more previously placed nodes. Based on these measurements, at every step, a decision is made to place a relay node, the overall system objective being to minimize a linear combination of the expected sum power (or the expected maximum power) required to deliver a packet from the source to the sink node and the expected number of relay nodes deployed. For each of these two objectives, two different relay selection strategies are considered: (i) each relay communicates with the sink via its immediate previous relay, (ii) the communication path can skip some of the deployed relays. With appropriate modeling assumptions, we formulate each of these problems as a Markov decision process (MDP). We provide the optimal policy structures for all these cases, and provide illustrations of the policies and their performance, via numerical results, for some typical parameters.

Surface freshwater storage and variability in the Amazon basin from multi-satellite observations, 1993-2007

The amount of water stored and moving through the surface water bodies of large river basins (river, floodplains, wetlands) plays a major role in the global water and biochemical cycles and is a critical parameter for water resources management. However, the spatiotemporal variations of these freshwater reservoirs are still widely unknown at the global scale. Here, we propose a hypsographic curve approach to estimate surface freshwater storage variations over the Amazon basin combining surface water extent from a multi-satellite-technique with topographic data from the Global Digital Elevation Model (GDEM) from Advance Spaceborne Thermal Emission and Reflection Radiometer (ASTER). Monthly surface water storage variations for 1993-2007 are presented, showing a strong seasonal and interannual variability, and are evaluated against in situ river discharge and precipitation. The basin-scale mean annual amplitude of similar to 1200 km(3) is in the range of previous estimates and contributes to about half of the Gravity Recovery And Climate Experiment (GRACE) total water storage variations. For the first time, we map the surface water volume anomaly during the extreme droughts of 1997 (October-November) and 2005 (September-October) and found that during these dry events the water stored in the river and floodplains of the Amazon basin was, respectively, similar to 230 (similar to 40%) and 210 (similar to 50%) km(3) below the 1993-2007 average. This new 15 year data set of surface water volume represents an unprecedented source of information for future hydrological or climate modeling of the Amazon. It is also a first step toward the development of such database at the global scale.

RAPID HUMAN ACTION RECOGNITION IN H.264/AVC COMPRESSED DOMAIN FOR VIDEO SURVEILLANCE

This paper discusses a novel high-speed approach for human action recognition in H. 264/AVC compressed domain. The proposed algorithm utilizes cues from quantization parameters and motion vectors extracted from the compressed video sequence for feature extraction and further classification using Support Vector Machines (SVM). The ultimate goal of our work is to portray a much faster algorithm than pixel domain counterparts, with comparable accuracy, utilizing only the sparse information from compressed video. Partial decoding rules out the complexity of full decoding, and minimizes computational load and memory usage, which can effect in reduced hardware utilization and fast recognition results. The proposed approach can handle illumination changes, scale, and appearance variations, and is robust in outdoor as well as indoor testing scenarios. We have tested our method on two benchmark action datasets and achieved more than 85% accuracy. The proposed algorithm classifies actions with speed (>2000 fps) approximately 100 times more than existing state-of-the-art pixel-domain algorithms.

Finding hidden females in a crowd: Mate recognition in fig wasps

Multi-species mating aggregations are crowded environments within which mate recognition must occur. Mating aggregations of fig wasps can consist of thousands of individuals of many species that attain sexual maturity simultaneously and mate in the same microenvironment, i.e, in syntopy, within the close confines of an enclosed globular inflorescence called a syconium - a system that has many signalling constraints such as darkness and crowding. All wasps develop within individual galled flowers. Since mating mostly occurs when females are still confined within their galls,, male wasps have the additional burden of detecting conspecific females that are ``hidden'' behind barriers consisting of gall walls. In Ficus racemosa, we investigated signals used by pollinating fig wasp males to differentiate conspecific females from females of other syntopic fig wasp species. Male Ceratosolen fusciceps could detect conspecific females using cues from galls containing females, empty galls, as well as cues from gall volatiles and gall surface hydrocarbons. In many figs, syconia are pollinated by single foundress wasps, leading to high levels of wasp inbreeding due to sibmating. In F. racemosa, as most syconia contain many foundresses, we expected male pollinators to prefer non-sib females to female siblings to reduce inbreeding. We used galls containing females from non-natal figs as a proxy for non-sibs and those from natal figs as a proxy for sibling females. We found that males preferred galls of female pollinators from natal figs. However, males were undecided when given a choice between galls containing non-pollinator females from natal syconia and pollinator females from non-natal syconia, suggesting olfactory imprinting by the natal syconial environment. (C) 2013 Elsevier Masson SAS. All rights reserved.

Multi-site downscaling of maximum and minimum daily temperature using support vector machine

Climate change impact assessment studies involve downscaling large-scale atmospheric predictor variables (LSAPVs) simulated by general circulation models (GCMs) to site-scale meteorological variables. This article presents a least-square support vector machine (LS-SVM)-based methodology for multi-site downscaling of maximum and minimum daily temperature series. The methodology involves (1) delineation of sites in the study area into clusters based on correlation structure of predictands, (2) downscaling LSAPVs to monthly time series of predictands at a representative site identified in each of the clusters, (3) translation of the downscaled information in each cluster from the representative site to that at other sites using LS-SVM inter-site regression relationships, and (4) disaggregation of the information at each site from monthly to daily time scale using k-nearest neighbour disaggregation methodology. Effectiveness of the methodology is demonstrated by application to data pertaining to four sites in the catchment of Beas river basin, India. Simulations of Canadian coupled global climate model (CGCM3.1/T63) for four IPCC SRES scenarios namely A1B, A2, B1 and COMMIT were downscaled to future projections of the predictands in the study area. Comparison of results with those based on recently proposed multivariate multiple linear regression (MMLR) based downscaling method and multi-site multivariate statistical downscaling (MMSD) method indicate that the proposed method is promising and it can be considered as a feasible choice in statistical downscaling studies. The performance of the method in downscaling daily minimum temperature was found to be better when compared with that in downscaling daily maximum temperature. Results indicate an increase in annual average maximum and minimum temperatures at all the sites for A1B, A2 and B1 scenarios. The projected increment is high for A2 scenario, and it is followed by that for A1B, B1 and COMMIT scenarios. Projections, in general, indicated an increase in mean monthly maximum and minimum temperatures during January to February and October to December.

Exploring Transfer Learning Approaches for Head Pose Classification from Multi-view Surveillance Images

Head pose classification from surveillance images acquired with distant, large field-of-view cameras is difficult as faces are captured at low-resolution and have a blurred appearance. Domain adaptation approaches are useful for transferring knowledge from the training (source) to the test (target) data when they have different attributes, minimizing target data labeling efforts in the process. This paper examines the use of transfer learning for efficient multi-view head pose classification with minimal target training data under three challenging situations: (i) where the range of head poses in the source and target images is different, (ii) where source images capture a stationary person while target images capture a moving person whose facial appearance varies under motion due to changing perspective, scale and (iii) a combination of (i) and (ii). On the whole, the presented methods represent novel transfer learning solutions employed in the context of multi-view head pose classification. We demonstrate that the proposed solutions considerably outperform the state-of-the-art through extensive experimental validation. Finally, the DPOSE dataset compiled for benchmarking head pose classification performance with moving persons, and to aid behavioral understanding applications is presented in this work.

Surface Freshwater Storage Variations in the Orinoco Floodplains Using Multi-Satellite Observations

Variations in surface water extent and storage are poorly characterized from regional to global scales. In this study, a multi-satellite approach is proposed to estimate the water stored in the floodplains of the Orinoco Basin at a monthly time-scale using remotely-sensed observations of surface water from the Global Inundation Extent Multi-Satellite (GIEMS) and stages from Envisat radar altimetry. Surface water storage variations over 2003-2007 exhibit large interannual variability and a strong seasonal signal, peaking during summer, and associated with the flood pulse. The volume of surface water storage in the Orinoco Basin was highly correlated with the river discharge at Ciudad Bolivar (R = 0.95), the closest station to the mouth where discharge was estimated, although discharge lagged one month behind storage. The correlation remained high (R = 0.73) after removing seasonal effects. Mean annual variations in surface water volume represented similar to 170 km(3), contributing to similar to 45% of the Gravity Recovery and Climate Experiment (GRACE)-derived total water storage variations and representing similar to 13% of the total volume of water that flowed out of the Orinoco Basin to the Atlantic Ocean.

Development of a global inundation map at high spatial resolution from topographic downscaling of coarse-scale remote sensing data

Large-scale estimates of the area of terrestrial surface waters have greatly improved over time, in particular through the development of multi-satellite methodologies, but the generally coarse spatial resolution (tens of kms) of global observations is still inadequate for many ecological applications. The goal of this study is to introduce a new, globally applicable downscaling method and to demonstrate its applicability to derive fine resolution results from coarse global inundation estimates. The downscaling procedure predicts the location of surface water cover with an inundation probability map that was generated by bagged derision trees using globally available topographic and hydrographic information from the SRTM-derived HydroSHEDS database and trained on the wetland extent of the GLC2000 global land cover map. We applied the downscaling technique to the Global Inundation Extent from Multi-Satellites (GIEMS) dataset to produce a new high-resolution inundation map at a pixel size of 15 arc-seconds, termed GIEMS-D15. GIEMS-D15 represents three states of land surface inundation extents: mean annual minimum (total area, 6.5 x 10(6) km(2)), mean annual maximum (12.1 x 10(6) km(2)), and long-term maximum (173 x 10(6) km(2)); the latter depicts the largest surface water area of any global map to date. While the accuracy of GIEMS-D15 reflects distribution errors introduced by the downscaling process as well as errors from the original satellite estimates, overall accuracy is good yet spatially variable. A comparison against regional wetland cover maps generated by independent observations shows that the results adequately represent large floodplains and wetlands. GIEMS-D15 offers a higher resolution delineation of inundated areas than previously available for the assessment of global freshwater resources and the study of large floodplain and wetland ecosystems. The technique of applying inundation probabilities also allows for coupling with coarse-scale hydro-climatological model simulations. (C) 2014 Elsevier Inc All rights reserved.

Compressed domain human action recognition in H.264/AVC video streams

This paper discusses a novel high-speed approach for human action recognition in H.264/AVC compressed domain. The proposed algorithm utilizes cues from quantization parameters and motion vectors extracted from the compressed video sequence for feature extraction and further classification using Support Vector Machines (SVM). The ultimate goal of the proposed work is to portray a much faster algorithm than pixel domain counterparts, with comparable accuracy, utilizing only the sparse information from compressed video. Partial decoding rules out the complexity of full decoding, and minimizes computational load and memory usage, which can result in reduced hardware utilization and faster recognition results. The proposed approach can handle illumination changes, scale, and appearance variations, and is robust to outdoor as well as indoor testing scenarios. We have evaluated the performance of the proposed method on two benchmark action datasets and achieved more than 85 % accuracy. The proposed algorithm classifies actions with speed (> 2,000 fps) approximately 100 times faster than existing state-of-the-art pixel-domain algorithms.

Spectral Clustering with Jensen-type kernels and their multi-point extensions

Motivated by multi-distribution divergences, which originate in information theory, we propose a notion of `multipoint' kernels, and study their applications. We study a class of kernels based on Jensen type divergences and show that these can be extended to measure similarity among multiple points. We study tensor flattening methods and develop a multi-point (kernel) spectral clustering (MSC) method. We further emphasize on a special case of the proposed kernels, which is a multi-point extension of the linear (dot-product) kernel and show the existence of cubic time tensor flattening algorithm in this case. Finally, we illustrate the usefulness of our contributions using standard data sets and image segmentation tasks.

Biological application of multi-component nanowires in hybrid devices powered by F-1-ATPase motors

In this paper, construction of hybrid device by integrating nanowires with F1-ATPase motors is described. The nickel nanowires and multi-segment nanowires, including gold and nickel, were fabricated by electrochemical deposition in nanoporous templates. The nickel nanowires functionalized by biotinylated peptide can be assembled directly onto F1-ATPase motors to act as the propellers. If the multicomponent nanowires, including gold and nickel, were selectively functionalized by the thiol group modified ssDNA and the synthetic peptide, respectively, the biotinylated F1- ATPase motors can be attached to the biotinylated peptide on nickel segment of the nanowires. Then, the multi-component nanowires can also be used as the propellers, and one may observe the rotations of the multi-component nanowires driven by F1-ATPase motors. Therefore, introduction of multiple segments along the length of a nanowire can lead to a variety of multiple chemical functionalities, which can be selectively bound to cells and special biomolecules. This method provides an insight for the construction of other hybrid devices with its controlling arrangement of different biomolecule on designed nanometer scale structures.