Neural network classifier and multiple hypothesis image segmentation for dietary assessment using calorie calculator

Nowadays, dietary assessment becomes the emerging system for evaluating the person’s food intake. In this paper, the multiple hypothesis image segmentation and feed-forward neural network classifier are proposed for dietary assessment to enhance the performance. Initially, the segmentation is applied to input image which is used to determine the regions where a particular food item is located using salient region detection, multi-scale segmentation, and fast rejection. Then, the significant feature of food items is extracted by the global feature and local feature extraction method. After the features are obtained, the classification is performed for each segmented region using feed-forward neural network model. Finally, the calorie value is computed with the aid of (i) food area volume and (ii) calorie and nutrition measure based on mass value. The outcome of the proposed method attains 96% of accuracy value which provides the better classification performance.     

Microstructure evolution and thermoelectric properties of Te-poor and Te-rich (Bi,Sb)<Subscript>2</Subscript>Te<Subscript>3</Subscript> prepared via solidification

This paper explores in detail, the microstructures and thermoelectric properties of Te-rich and Te-poor (Bi,Sb)₂Te₃ alloys. We show that tuning the composition of ternary Bi–Sb–Te type alloys allows us to synthesize a range of microstructures containing a primary solid solution of (Bi,Sb)₂Te₃ with varying amounts of Te solid solution or a (Bi,Sb)Te compound. Te exists as a constituent of the multilayer domain while (Bi,Sb)Te appears in the thin intercellular regions of the (Bi,Sb)₂Te₃ dendritic cells. The presence of Te imparts an n-type behavior to the composite while the (Bi,Sb)₂Te₃ with a small amount of (Bi,Sb)Te exhibits p-type properties. A maximum ZT value of ≈0.4 at 425 K was achieved, opening up the possibility of using these alloys for thermoelectric device applications.     

Indexing and querying segmented web pages: the BlockWeb Model

We present in this paper a model for indexing and querying web pages, based on the hierarchical decomposition of pages into blocks. Splitting up a page into blocks has several advantages in terms of page design, indexing and querying such as (i) blocks of a page most similar to a query may be returned instead of the page as a whole (ii) the importance of a block can be taken into account, as well as (iii) the permeability of the blocks to neighbor blocks: a block b is said to be permeable to a block b?? in the same page if b?? content (text, image, etc.) can be (partially) inherited by b upon indexing. An engine implementing this model is described including: the transformation of web pages into blocks hierarchies, the definition of a dedicated language to express indexing rules and the storage of indexed blocks into an XML repository. The model is assessed on a dataset of electronic news, and a dataset drawn from web pages of the ImagEval campaign where it improves by 16% the mean average precision of the baseline.     

Moving People Segmentation from Zoomed Dynamic Scenes Containing a Door

The challenge of segmenting the moving object is harder when the background is dynamic and the camera used can change its zoom dynamically. Here, in this paper, we propose a method to detect and segment moving object from a dynamic background, which contains moving multiple-leaf doors. In addition, the proposed algorithm also takes care of dynamic zoom changes that can occur while shooting a scene. The proposed method uses background-rebuilding with discrete door’s position to tackle moving multiple-leaf door backgrounds and image feature comparison to tackle changes in zoom. The experiment results show satisfying segmentation results with high processing speed.     

Joint Estimation of Shape and Reflectance using Multiple Images with Known Illumination Conditions

We propose a generative model based method for recovering both the shape and the reflectance of the surface(s) of a scene from multiple images, assuming that illumination conditions and cameras calibration are known in advance. Based on a variational framework and via gradient descents, the algorithm minimizes simultaneously and consistently a global cost functional with respect to both shape and reflectance. The motivations for our approach are threefold. (1) Contrary to previous works which mainly consider specific individual scenarios, our method applies indiscriminately to a number of classical scenarios; in particular it works for classical stereovision, multiview photometric stereo and multiview shape from shading. It works with changing as well as static illumination. (2) Our approach naturally combines stereo, silhouette and shading cues in a single framework. (3) Moreover, unlike most previous methods dealing with only Lambertian surfaces, the proposed method considers general dichromatic surfaces. We verify the method using various synthetic and real data sets.     

Compositionality and lexical alignment of multi-word terms

The automatic compilation of bilingual lists of terms from specialized comparable corpora using lexical alignment has been successful for single-word terms (SWTs), but remains disappointing for multi-word terms (MWTs). The low frequency and the variability of the syntactic structures of MWTs in the source and the target languages are the main reported problems. This paper defines a general framework dedicated to the lexical alignment of MWTs from comparable corpora that includes a compositional translation process and the standard lexical context analysis. The compositional method which is based on the translation of lexical items being restrictive, we introduce an extended compositional method that bridges the gap between MWTs of different syntactic structures through morphological links. We experimented with the two compositional methods for the French–Japanese alignment task. The results show a significant improvement for the translation of MWTs and advocate further morphological analysis in lexical alignment.     

Cancellation of bulging effect on mould level in continuous casting: Experimental validation

During the continuous casting of steel, several disturbances occur and affect all the parts of the caster, including the mould where the molten steel has to be stable for good quality of the final product. Especially at high casting velocities, the bulging generates important level fluctuations which cannot be efficiently rejected by the classical controllers. To address these problems, this paper proposes an architecture combining disturbances estimation and compensation techniques. It operates as an additional module and does not need any change of the main controller currently implemented. The entire structure has been tested successfully through several simulations and by means of intensive water model experiments.     

Temperature sensor based on the Er green upconverted emission in a fluorotellurite glass

The temperature dependence of the green upconverted emission from the two thermally coupled ²H_11/2 and ⁴S_3/2 levels of the Er³⁺ ion in a fluorotellurite glass has been analyzed as a function of the optically active ion concentration in order to check its availability as a temperature sensor. The infrared-to-green upconverted emission have been observed by the naked eyes after a cw laser diode excitation at 800 nm. The fluorescence intensity ratio between the thermally coupled emitting levels as well as the temperature sensitivity has been experimentally obtained up to 540 K. A better behaviour as a temperature sensor has been obtained for the less Er³⁺ concentrated glass with a maximum sensitivity of 54 × 10⁻⁴ K⁻¹ at 540 K, one of the highest found in rare-earth doped transparent materials.     

Antichains and compositional algorithms for LTL synthesis

In this paper, we present new monolithic and compositional algorithms to solve the LTL realizability problem. Those new algorithms are based on a reduction of the LTL realizability problem to a game whose winning condition is defined by a universal automaton on infinite words with a k-co-Büchi acceptance condition. This acceptance condition asks that runs visit at most k accepting states, so it implicitly defines a safety game. To obtain efficient algorithms from this construction, we need several additional ingredients. First, we study the structure of the underlying automata constructions, and we show that there exists a partial order that structures the state space of the underlying safety game. This partial order can be used to define an efficient antichain algorithm. Second, we show that the algorithm can be implemented in an incremental way by considering increasing values of k in the acceptance condition. Finally, we show that for large LTL formulas that are written as conjunctions of smaller formulas, we can solve the problem compositionally by first computing winning strategies for each conjunct that appears in the large formula. We report on the behavior of those algorithms on several benchmarks. We show that the compositional algorithms are able to handle LTL formulas that are several pages long.     

Objective selection of suitable unit cell size in data-driven modeling of mineral prospectivity

In GIS-based data-driven modeling of mineral prospectivity, a suitably fine unit cell size is used for spatial representation of known occurrences of mineral deposits of the type sought (D) in a study area (T). However, until now, the unit cell size is chosen subjectively. In this paper, a methodology is proposed for objective selection of the most suitable unit cell size for data-driven modeling of mineral prospectivity using a raster-based GIS. A set of choices of suitable unit cell sizes is first derived via point pattern analysis of a set of known occurrences of mineral deposits of the type sought. Then, (a) the lower limit of a set of choices of suitable unit cell sizes is considered and defined according to the map scales from which spatial data for mineral prospectivity mapping were derived, and (b) the upper limit of the same set of choices of suitable unit cell sizes is considered (and revised as necessary) based on knowledge of spatial extents of mineral deposits of the type sought or via analysis of reflexive nearest neighbour points. Finally, it is shown that fractal analysis of spatial contrast between unit cells containing D and unit cells not containing D in T provides for objective selection of the most suitable unit cell size. In a case study application of the weight-of-evidence method to mineral prospectivity mapping, using the most suitable unit cell size, found via the proposed methodology, results in spatial evidence weights and weight uncertainties that are nearly identical to those derived by using the finest (i.e., lower limit) unit cell size. In contrast to using the most suitable unit cell size, using coarser unit cell sizes result in higher positive weights, lower negative weights and higher weight uncertainties of spatial evidence of mineral prospectivity. The proposed methodology for objective selection of the most suitable unit cell size in data-driven modeling of mineral prospectivity using a raster-based GIS is robust and can easily be implemented.