Painting-91: a large scale database for computational painting categorization

Computer analysis of visual art, especially paintings, is an interesting cross-disciplinary research domain. Most of the research in the analysis of paintings involve medium to small range datasets with own specific settings. Interestingly, significant progress has been made in the field of object and scene recognition lately. A key factor in this success is the introduction and availability of benchmark datasets for evaluation. Surprisingly, such a benchmark setup is still missing in the area of computational painting categorization. In this work, we propose a novel large scale dataset of digital paintings. The dataset consists of paintings from 91 different painters. We further show three applications of our dataset namely: artist categorization, style classification and saliency detection. We investigate how local and global features popular in image classification perform for the tasks of artist and style categorization. For both categorization tasks, our experimental results suggest that combining multiple features significantly improves the final performance. We show that state-of-the-art computer vision methods can correctly classify 50 % of unseen paintings to its painter in a large dataset and correctly attribute its artistic style in over 60 % of the cases. Additionally, we explore the task of saliency detection on paintings and show experimental findings using state-of-the-art saliency estimation algorithms.     

Fuzzy decision support system for fertilizer

Fuzzy geographic information systems is a newly emerging field of computational intelligence. It combines fuzzy logic with spatial context. Most of the natural phenomena are fuzzy in nature. They show a degree of uncertainty or vagueness in their extent and attribute, which cannot be expressed by a crisp value. Agriculture is one of the fields of the spatial domain that needs to be described in fuzzy terms. Fertilizer is a key input for the agriculture sector. In this article, the spatial surfaces of fertilizers are developed for the wheat crop using a fuzzy decision support system. The algorithm of our system takes soil nutrients and cropping time as input, applies fuzzy logic on the input values, defuzzifies the fuzzy output to crisp value, and generates a fertilizer surface. The resultant output surface of fertilizer describes the amount of fertilizer needed to cultivate a specific crop in a specified area. The complexity of our algorithm is \(O(mnr)\) , where \(m\) is the height of the raster, \(n\) is the width of the raster, and \(r\) is the number of expert rules.     

Behavioral and physiological responses of cabbage looper,Trichoplusia ni (Hübner), to steam distillates from resistant versus susceptible soybean plants

Soybean plant volatiles, extracted as steam distillates, significantly affected the behavior and biology of the cabbage looper,Trichoplusia ni (Hübner) (Lepidoptera: Noctuidae). Distillates from the susceptible Davis variety attractedT. ni larvae and female adults, whereas those from resistant PI 227687 plants repelled them. When mixed in an artificial diet, steam distillates from PI 227687 plants caused mortality of first-instar larvae. Adults emerging from pupae topically treated with 5 g of such PI 227687 extractable showed developmental abnormalities. Larval feeding was significantly less on Davis leaves treated with PI 227687 volatiles as compared to solvent (acetone) or such Davis extractables. However, Davis volatiles on PI 227687 leaves did not increase larval feeding. HPLC analyses of steam distillates from susceptible Davis versus resistant PI 227687 indicated differences.     

Prediction of the viscosities of liquid mixtures by a group solution model

Group solution models of liquid mixtures have been used previously to predict thermodynamic properties of non-ideal systems. A model of this type has been developed which enables the viscosities of liquid mixtures to be predicted. The concept of an “ideal viscosity” is introduced, and allowance made for the interaction between the groups present and for the structural contributions of differing molecules. Predictions require a knowledge of only the viscosities of the pure components of a mixture. It has been tested for mixtures of alkanes, alcohols and water at 25°C, and gives good agreement with experiment. Experimental viscosities for ethanol/n-hexane, for n-propanol/water, and for four multi-component mixtures at 25°C are presented.     

Role of sand on curing of partex surface by UV radiation

A partex surface was modified by a UV‐curing system with epoxy acrylate (EB‐600). A set of formulations was prepared with oligomer and the trifunctional monomer trimethylol propane triacrylate in different combinations of percentages (1–5%) of sand to study the role of sand in various physical properties of UV‐cured thin films, as well as partex surfaces. Increased pendulum hardness (PH), gloss, adhesion, and abrasion values were obtained by the addition of sand into the partex surfaces. The best results were obtained with the formulation containing 3% sand. An enhanced PH and a decreased percentage of gel content of the UV‐cured film was observed with an increase of the sand concentration. A simulated weathering test was performed with partex surfaces cured by a formulation containing 3% sand in the base coat. The losses of the physical properties were found to be lower over the surface treated with the formulation containing sand. © 2002 Wiley Periodicals, Inc. J Appl Polym Sci 86: 2385–2392, 2002     

Carbon fiber from natural biopolymer Bombyx mori silk fibroin with iodine treatment

Carbon fibers were prepared from silk fibers after an iodine treatment and the carbon yield, fiber morphology, structure and mechanical properties were investigated. A single or multi-step carbonization process was used for the preparation. In the single step process, silk fibroin (SF) fibers were heated from 25 to 800 °C with a heating rate of 5 °C min⁻¹ under Ar atmosphere. However, the carbon fiber obtained was partially melted and was too fragile to handle. For better performance, SF fibers were treated with iodine vapor at 100 °C for 12 h and untreated and iodinated SF fibers were heated from 25 to 800 °C by a multi-step carbonization process, which was defined based on the optimum thermal degradation rate of silk. In this multi-step process, the carbon fibers obtained from iodinated SF were structurally intact and stable in appearance, and the carbon yield achieved was ca. 36 wt.%, much higher than the value for untreated SF. X-ray diffraction, Raman spectroscopy and transmission electron microscopic observation revealed that the obtained carbon fibers from both untreated and iodinated SFs had a basically amorphous structure. The strength of carbon fibers prepared from iodinated SF using the multi-step carbonization was considerably increased compared to that of untreated SF. According to viscoelastic measurement, by heating above 280 °C the iodine introduced intermolecular cross-linking of the SF, and its melt flow was inhibited which produced a higher yield and better performance of the carbon fiber.     

Investigations on the Three Commercial Species of Rosaceae

Physico-chemical properties of the seed oils of three species of Rosaceae family, namely Prunus armeniaca (apricot), Prunus cerasifera (prune), and Prunus persica (peach) have been determined. Fatty acid composition of the oils and amino acids composition of seed cake proteins have also been determined and their utility in every day life has been discussed.     

Pre‐necking and post‐necking relaxation and creep behavior of polycarbonate: A phenomenological study

Experiments have been performed to investigate the mechanical response of unfilled polycarbonate vis‐à‐vis the influence of prior deformation on stress relaxation and creep. Piecewise linear deformation histories, which involve strain‐controlled tensile loading of a specimen to a maximum load and partial unloading to a target strain/stress point as prologue to a relaxation test, have been shown to qualitatively influence the recorded stress‐time behavior. In particular, the stress magnitude during relaxation first increases and is then followed by a decrease. Analogously, in creep tests during unloading, the strain might decrease and then increase. Time characteristics for this U‐turn in the deformation response are influenced by the placement of the test. The influence of prior specimen conditioning on this phenomenon is investigated by comparing test data from virgin samples to that of specimens having high (～85%) inelastic strain from prior tensile elongation. Findings suggest that the observed persistence in the occurrence of this reversal effect for both types of specimens is evidence of the need to incorporate this behavior into the fold of material modeling. Additionally, this novel relaxation and creep behavior has been observed in other amorphous (poly(phenylene oxide)) and crystalline (high‐density polyethylene) polymers. Polym. Eng. Sci. 44:1783–1791, 2004. © 2004 Society of Plastics Engineers.     

Mathematical modeling of reverse osmosis systems

The present investigation pertains to modeling of seawater desalination system. A simulation model was developed and verified for a small-scale reverse osmosis system. The proposed model combines material balances on the feed tank, membrane module andproduct tank with membrane mass transfer models. Finally a comprehensive simulation model has been developed incorporating the effect of mass transfer inhibition The model is non-linear differential equation representing the feed concentration as a function of operating time and space. The solution of the simultaneous differential equations was obtained using the fourth order Runge-Kutta method, due to self starting and stability. The model was verified using the experimental data from the literature [17,24]. Parameter sensitivity was carried out to select the proper step size. The simulation was run for over 1000 11 enabling a prediction of operational performance at high overall system recoveries.     

Oxidation of Branched Chain Fatty Acids by Chromic Acid

The kinetics of oxidation of isobutyric and isovaleric acids by chromic acid in sulphuric acid medium have been studied. The end product acetic acid is supposed to be derived from the ketones which are the initial oxidation products of the corresponding branched chain fatty acids. The influence of acetic acid on the oxidation velocity has been examined and a marked effect on the rate constants with increasing acetic acid concentration has been observed. A mechanism involving the electrophilic attack of the oxidant on the tertiary carbon atom of the fatty acid to yield a carbonium ion has been postulated.