14 results on '"Banić, N"'
Search Results
2. Reliability and Stability of Mean Opinion Score for Image Aesthetic Quality Assessment Obtained Through Crowdsourcing
- Author
-
Radeva, P, Furnari, A, Bouatouch, K, Sousa, AA, Ershov, E, Panshin, A, Ermakov, I, Banić, N, Savchik, A, Bianco, S, Radeva, P, Furnari, A, Bouatouch, K, Sousa, AA, Ershov, E, Panshin, A, Ermakov, I, Banić, N, Savchik, A, and Bianco, S
- Abstract
Image quality assessment (IQA) is widely used to evaluate the results of image processing methods. While in recent years the development of objective IQA metrics has seen much progress, there are still many tasks where subjective IQA is significantly more preferred. Using subjective IQA has become even more attractive ever since crowdsourcing platforms such as Amazon Mechanical Turk and Toloka have become available. However, for some specific image processing tasks, there are still some questions related to subjective IQA that have not been solved in a satisfactory way. An example of such a task is the evaluation of image rendering styles where, unlike in the case of distortions, none of the evaluated styles is to be objectively regarded as a priori better or worse. The questions that have not been properly answered up until now are whether the scores for such a task obtained through crowdsourced subjective IQA are reliable and whether they remain stable, i.e., similar if the evaluation is repeated over time. To answer these questions, in this paper first several images and styles are selected and defined, they are then evaluated by using crowdsourced subjective IQA on the Toloka platform, and the obtained scores are numerically analyzed. Experimental results confirm the reliability and stability of the crowdsourced subjective IQA for the problem in question.
- Published
- 2024
3. Removal of methylene blue using tungsten(VI)-oxide immobilized on commercial PVC in the presence of simulated solar radiation
- Author
-
Jagodić, I. D., primary, Uzelac, M. M., additional, Guth, I. O., additional, Lukić-Petrović, S. R., additional, and Banić, N. D., additional
- Published
- 2022
- Full Text
- View/download PDF
4. Analysis of the Human Protein Atlas Weakly Supervised Single-Cell Classification competition
- Author
-
Le, Trang, Winsnes, Casper F., Axelsson, Ulrika, Xu, Hao, Mohanakrishnan Kaimal, Jayasankar, Mahdessian, Diana, Dai, S., Makarov, I. S., Ostankovich, V., Xu, Y., Benhamou, E., Henkel, C., Solovyev, R. A., Banić, N., Bošnjak, V., Bošnjak, A., Miličević, A., Ouyang, Wei, Lundberg, Emma, Le, Trang, Winsnes, Casper F., Axelsson, Ulrika, Xu, Hao, Mohanakrishnan Kaimal, Jayasankar, Mahdessian, Diana, Dai, S., Makarov, I. S., Ostankovich, V., Xu, Y., Benhamou, E., Henkel, C., Solovyev, R. A., Banić, N., Bošnjak, V., Bošnjak, A., Miličević, A., Ouyang, Wei, and Lundberg, Emma
- Abstract
While spatial proteomics by fluorescence imaging has quickly become an essential discovery tool for researchers, fast and scalable methods to classify and embed single-cell protein distributions in such images are lacking. Here, we present the design and analysis of the results from the competition Human Protein Atlas – Single-Cell Classification hosted on the Kaggle platform. This represents a crowd-sourced competition to develop machine learning models trained on limited annotations to label single-cell protein patterns in fluorescent images. The particular challenges of this competition include class imbalance, weak labels and multi-label classification, prompting competitors to apply a wide range of approaches in their solutions. The winning models serve as the first subcellular omics tools that can annotate single-cell locations, extract single-cell features and capture cellular dynamics., QC 20230602
- Published
- 2022
- Full Text
- View/download PDF
5. Illumination estimation challenge: The experience of the first 2 years
- Author
-
Ershov, E, Savchik, A, Semenkov, I, Banić, N, Koščević, K, Subašić, M, Belokopytov, A, Terekhin, A, Senshina, D, Nikonorov, A, Li, Z, Qian, Y, Buzzelli, M, Riva, R, Bianco, S, Schettini, R, Barron, J, Lončarić, S, Nikolaev, D, Ershov, Egor, Savchik, Alex, Semenkov, Ilya, Banić, Nikola, Koščević, Karlo, Subašić, Marko, Belokopytov, Alexander, Terekhin, Arseniy, Senshina, Daria, Nikonorov, Artem, Li, Zhihao, Qian, Yanlin, Buzzelli, Marco, Riva, Riccardo, Bianco, Simone, Schettini, Raimondo, Barron, Jonathan T., Lončarić, Sven, Nikolaev, Dmitry, Ershov, E, Savchik, A, Semenkov, I, Banić, N, Koščević, K, Subašić, M, Belokopytov, A, Terekhin, A, Senshina, D, Nikonorov, A, Li, Z, Qian, Y, Buzzelli, M, Riva, R, Bianco, S, Schettini, R, Barron, J, Lončarić, S, Nikolaev, D, Ershov, Egor, Savchik, Alex, Semenkov, Ilya, Banić, Nikola, Koščević, Karlo, Subašić, Marko, Belokopytov, Alexander, Terekhin, Arseniy, Senshina, Daria, Nikonorov, Artem, Li, Zhihao, Qian, Yanlin, Buzzelli, Marco, Riva, Riccardo, Bianco, Simone, Schettini, Raimondo, Barron, Jonathan T., Lončarić, Sven, and Nikolaev, Dmitry
- Abstract
Illumination estimation is the essential step of computational color constancy, one of the core parts of various image processing pipelines of modern digital cameras. Having an accurate and reliable illumination estimation is important for reducing the illumination influence on the image colors. To motivate the generation of new ideas and the development of new algorithms in this field, two challenges on illumination estimation were conducted. The main advantage of testing a method on a challenge over testing it on some of the known datasets is the fact that the ground‐truth illuminations for the challenge test images are unknown up until the results have been submitted, which prevents any potential hyperparameter tuning that may be biased. The First illumination estimation challenge (IEC#1) had only a single task, global illumination estimation. The second illumination estimation challenge (IEC#2) was enriched with two additional tracks that encompassed indoor and two‐illuminant illumination estimation. Other main features of it are a new large dataset of images (about 5000) taken with the same camera sensor model, a manual markup accompanying each image, diverse content with scenes taken in numerous countries under a huge variety of illuminations extracted by using the SpyderCube calibration object, and a contest‐like markup for the images from the Cube++ dataset. This article focuses on the description of the past two challenges, algorithms which won in each track, and the conclusions that were drawn based on the results obtained during the first and second challenge that can be useful for similar future developments.
- Published
- 2021
6. Illumination estimation challenge: The experience of the first 2 years
- Author
-
Riccardo Riva, Artem Nikonorov, Alex Savchik, Dmitry P. Nikolaev, Simone Bianco, Arseniy P. Terekhin, Sven Lončarić, Karlo Koscevic, Marco Buzzelli, Yanlin Qian, Marko Subasic, Daria Senshina, Raimondo Schettini, Egor I. Ershov, Ilya Semenkov, Alexander Belokopytov, Zhihao Li, Nikola Banic, Jonathan T. Barron, Ershov, E, Savchik, A, Semenkov, I, Banić, N, Koščević, K, Subašić, M, Belokopytov, A, Terekhin, A, Senshina, D, Nikonorov, A, Li, Z, Qian, Y, Buzzelli, M, Riva, R, Bianco, S, Schettini, R, Barron, J, Lončarić, S, and Nikolaev, D
- Subjects
Estimation ,Color constancy ,Computer science ,business.industry ,multiple illumination ,General Chemical Engineering ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Color balance ,Human Factors and Ergonomics ,General Chemistry ,white balancing ,challenge ,color constancy ,illumination estimation ,mixed illumination ,Computer vision ,Artificial intelligence ,business - Abstract
Illumination estimation is the essential step of computational color constancy, one of the core parts of various image processing pipelines of modern digital cameras. Having an accurate and reliable illumination estimation is important for reducing the illumination influence on the image colors. To motivate the generation of new ideas and the development of new algorithms in this field, two challenges on illumination estimation were conducted. The main advantage of testing a method on a challenge over testing it on some of the known datasets is the fact that the ground- truth illuminations for the challenge test images are unknown up until the results have been submitted, which prevents any potential hyperparameter tuning that may be biased. The First illumination estimation challenge (IEC#1) had only a single task, global illumination estimation. The second illumination estimation challenge (IEC#2) was enriched with two additional tracks that encompassed indoor and two-illuminant illumination estimation. Other main features of it are a new large dataset of images (about 5000) taken with the same camera sensor model, a manual markup accompanying each image, diverse content with scenes taken in numerous countries under a huge variety of illuminations extracted by using the SpyderCube calibration object, and a contest- like markup for the images from the Cube++ dataset. This article focuses on the description of the past two challenges, algorithms which won in each track, and the conclusions that were drawn based on the results obtained during the first and second challenge that can be useful for similar future developments.
- Published
- 2021
7. Reusable Fe 2 O 3 /TiO 2 /PVC Photocatalysts for the Removal of Methylene Blue in the Presence of Simulated Solar Radiation.
- Author
-
Jagodić I, Guth I, Lukić-Petrović S, Tamindžija D, Šojić Merkulov D, Finčur N, Bognár S, Putnik P, and Banić N
- Abstract
Currently, environmental pollution by various organic pollutants (e.g., organic dyes) is a serious, emerging global issue. The aqueous environment is highly exposed to the harmful effects of these organic compounds. Furthermore, the commonly applied conventional purification techniques are not sufficient enough. Heterogeneous photocatalysis and the photo-Fenton process are effective, low-cost and green alternatives for the removal of organic pollutants. In this study, different iron(III) oxide/titanium(IV) oxide/polyvinyl chloride (Fe
2 O3 /TiO2 /PVC) nanocomposites in tablet form were investigated in the photodegradation of methylene blue (MB) under simulated sunlight, and their possible antibacterial effects were examined. The newly synthesized nanocomposites were characterized by scanning electron microscope, X-ray diffraction, UV-Vis diffuse reflectance spectroscopy, and Raman spectroscopy. The results showed a hematite crystal form in the case of Fe2 O3(2) and Fe2 O3 samples, while the Fe2 O3(1) sample showed a combination of hematite and synthetic mineral akaganeite . The highest photocatalytic efficiency was achieved in the presence of Fe2 O3 /TiO2 /PVC, when 70.6% of MB was removed. In addition, the possible photo-cleaning and reuse of the mentioned photocatalyst was also examined. Based on the results, it can be seen that the activity did not decrease after five successive runs. Nanocomposites also exhibited mild antibacterial effects against the two tested Gram-positive bacteria ( S. aureus and B. cereus ).- Published
- 2023
- Full Text
- View/download PDF
8. Rapid Removal of Organic Pollutants from Aqueous Systems under Solar Irradiation Using ZrO 2 /Fe 3 O 4 Nanoparticles.
- Author
-
Banić N, Šojić Merkulov D, Despotović V, Finčur N, Ivetić T, Bognár S, Jovanović D, and Abramović B
- Subjects
- Ferrosoferric Oxide chemistry, Catalysis, Water, Environmental Pollutants, Nanoparticles, Pesticides
- Abstract
Pure water scarcity is an emerging, all-around problem that globally affects both the life quality and the world's economy. Heterogeneous photocatalysis under solar irradiation is a promising technique for the organic pollutants (e.g., pesticides, drugs) removal from an aqueous environment. Furthermore, the drawbacks of commercially available photocatalysts can be successfully overcome by using innovative nanoparticles, such as ZrO
2 /Fe3 O4 . Four ZrO2 /Fe3 O4 nanopowders with a different mass ratio of ZrO2 and Fe3 O4 were synthesized using the chemical co-precipitation method. XRD analysis showed the presence of magnetite and hematite Fe-oxide phases in all samples. The content of the magnetite phase increased with the addition of 19% ZrO2 . The efficiency of the newly synthesized ZrO2 /Fe3 O4 nanoparticles was investigated in the rapid removal of selected pollutants under various experimental conditions. Nevertheless, the influence of the water matrix on photocatalytic degradation was also examined. The obtained data showed that using ZrO2 /Fe3 O4 nanosystems, an appropriate removal rate of the selected pesticides and pharmaceuticals can be reached after 120 min of solar irradiation. Further, the total organic carbon measurements proved the mineralization of the target emerging pollutants. ZrO2 /Fe3 O4 nanoparticles are economically feasible, as their removal from the suspension can be easily achieved using affordable, environmentally-friendly magnetic separation.- Published
- 2022
- Full Text
- View/download PDF
9. Analysis of the Human Protein Atlas Weakly Supervised Single-Cell Classification competition.
- Author
-
Le T, Winsnes CF, Axelsson U, Xu H, Mohanakrishnan Kaimal J, Mahdessian D, Dai S, Makarov IS, Ostankovich V, Xu Y, Benhamou E, Henkel C, Solovyev RA, Banić N, Bošnjak V, Bošnjak A, Miličević A, Ouyang W, and Lundberg E
- Subjects
- Humans, Proteomics, Machine Learning, Proteins analysis
- Abstract
While spatial proteomics by fluorescence imaging has quickly become an essential discovery tool for researchers, fast and scalable methods to classify and embed single-cell protein distributions in such images are lacking. Here, we present the design and analysis of the results from the competition Human Protein Atlas - Single-Cell Classification hosted on the Kaggle platform. This represents a crowd-sourced competition to develop machine learning models trained on limited annotations to label single-cell protein patterns in fluorescent images. The particular challenges of this competition include class imbalance, weak labels and multi-label classification, prompting competitors to apply a wide range of approaches in their solutions. The winning models serve as the first subcellular omics tools that can annotate single-cell locations, extract single-cell features and capture cellular dynamics., (© 2022. The Author(s).)
- Published
- 2022
- Full Text
- View/download PDF
10. Environmental Photocatalytic Degradation of Antidepressants with Solar Radiation: Kinetics, Mineralization, and Toxicity.
- Author
-
Finčur N, Šojić Merkulov D, Putnik P, Despotović V, Banić N, Lazarević M, Četojević-Simin D, Agbaba J, and Abramović B
- Abstract
This work is focused on the kinetics, mineralization, and toxicological assessments of the antidepressant drug amitriptyline hydrochloride (AMI) in UV or solar illuminated aqueous suspensions of ZnO, TiO
2 Degussa P25, and TiO2 Hombikat. ZnO was proven to be the most effective photocatalyst, and it was used for all further experiments under solar irradiation. The highest reaction rate was observed at 1.0 mg/mL of catalyst loading. In the investigated initial concentration range (0.0075-0.3000 mmol/L), the degradation rate of AMI increased with the increase of initial concentration in the investigated range. The effects of H2 O2 , (NH4 )2 S2 O8 , and KBrO3 , acting as electron acceptors, along with molecular oxygen were also studied. By studying the effects of ethanol and NaI as a hydroxyl radical and hole scavenger, respectively, it was shown that the heterogeneous catalysis takes place mainly via free hydroxyl radicals. In the mineralization study, AMI photocatalytic degradation resulted in ~30% of total organic carbon (TOC) decrease after 240 min of irradiation; acetate and formate were produced as the organic intermediates; NH4 + , NO3 - , NO2 - ions were detected as nitrogen byproducts. Toxicity assessment using different mammalian cell lines, showed that H-4-II-E was the most sensitive one.- Published
- 2021
- Full Text
- View/download PDF
11. Smart light random memory sprays Retinex: a fast Retinex implementation for high-quality brightness adjustment and color correction.
- Author
-
Banić N and Lončarić S
- Abstract
Removing the influence of illumination on image colors and adjusting the brightness across the scene are important image enhancement problems. This is achieved by applying adequate color constancy and brightness adjustment methods. One of the earliest models to deal with both of these problems was the Retinex theory. Some of the Retinex implementations tend to give high-quality results by performing local operations, but they are computationally relatively slow. One of the recent Retinex implementations is light random sprays Retinex (LRSR). In this paper, a new method is proposed for brightness adjustment and color correction that overcomes the main disadvantages of LRSR. There are three main contributions of this paper. First, a concept of memory sprays is proposed to reduce the number of LRSR's per-pixel operations to a constant regardless of the parameter values, thereby enabling a fast Retinex-based local image enhancement. Second, an effective remapping of image intensities is proposed that results in significantly higher quality. Third, the problem of LRSR's halo effect is significantly reduced by using an alternative illumination processing method. The proposed method enables a fast Retinex-based image enhancement by processing Retinex paths in a constant number of steps regardless of the path size. Due to the halo effect removal and remapping of the resulting intensities, the method outperforms many of the well-known image enhancement methods in terms of resulting image quality. The results are presented and discussed. It is shown that the proposed method outperforms most of the tested methods in terms of image brightness adjustment, color correction, and computational speed.
- Published
- 2015
- Full Text
- View/download PDF
12. Thermochromism, stability and thermodynamics of cobalt(II) complexes in newly synthesized nitrate based ionic liquid and its photostability.
- Author
-
Banić N, Vraneš M, Abramović B, Csanádi J, and Gadžurić S
- Abstract
In this work a 1-(2-hydroxyethyl)-3-methylimidazolium nitrate ionic liquid, [HO(CH2)2mim]NO3, has been synthesized in order to serve as a new thermochromic material upon addition of cobalt(II) ions. Spectrophotometric measurements of a series of cobalt(II) nitrate and cobalt(II) chloride solutions in [HO(CH2)2mim]NO3 at 298.15, 308.15, 318.15, 328.15, and 338.15 K, were performed. Based on the recorded spectra, the overall stability constants and thermodynamic parameters for the cobalt(II) associations with chloride and nitrate ions were calculated. The thermodynamic calculations suggest that thermochromism is not observed in the ionic medium due to a small entropy change during the replacement of nitrate with chloride ions in the co-ordination sphere of cobalt(II). The absence of the molecular solvent was also the reason for the lack of thermochromism. Thus, cobalt(II) solutions in [HO(CH2)2mim]NO3 and water mixtures were studied as a new and green medium that can be used for the auto-regulation of the light intensity and shade protection. The investigated system with water upon addition of cobalt(II) was found to be a far more efficient and responsive thermochromic medium for all of the studied systems up until now. The structure of [HO(CH2)2mim]NO3 was confirmed by both (1)H NMR and IR spectroscopy. Also, the efficiency of different advanced oxidation processes (UV-induced photolysis, UV/H2O2 photolysis, heterogeneous photocatalysis using TiO2 Degussa P25 and TiO2 with 7.24%, w/w Fe catalysts) for [HO(CH2)2mim]NO3 degradation were investigated. The reaction intermediates formed during the photo-oxidation process were identified using LC-ESI-MS/MS and (1)H NMR techniques.
- Published
- 2014
- Full Text
- View/download PDF
13. [Archives of Industrial Hygiene and Toxicology. 50 years since the founding of the journal].
- Author
-
Banić N
- Subjects
- Croatia, History, 20th Century, Occupational Health history, Periodicals as Topic history, Toxicology history
- Published
- 1996
14. Institute for Medical Research and Occupational Health (1948-1978), Zagreb. List of publications 1968-1978.
- Author
-
Banić N
- Subjects
- Yugoslavia, Academies and Institutes, Bibliographies as Topic, Occupational Medicine
- Published
- 1979
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.