Conventional Bag Research Articles

Investigations of the recycling of airbag filters from the cement industry into fabric/polymer or fabric/cement composite materials

The cement industry, an essential contributor to global infrastructure development, generates substantial amounts of airborne pollutants during cement production processes. Bag filters play a crucial role in mitigating these emissions by capturing particulate matter and improving air quality. However, conventional bag filters eventually wear out and need replacement, leading to a significant environmental burden from discarded filter materials. This study explores a sustainable approach to address this issue by investigating the potential of recycling used bag filters from the cement industry. The focus of the investigation is on fabric/polymer or fabric/cement composite materials, which exhibit promising properties for recycling applications. The research begins with an in-depth analysis of the discarded bag filters. This characterization enables the selection and optimization of suitable recycling processes for fabric/polymer or fabric/cement composites. Furthermore, the study evaluates the performance of recycled fabric/polymer or fabric/cement composites as alternatives to conventional methods of bag filters in cement recycling and mechanical parameters of the airbag filter when used as reinforcement in the polyester matrix or cementitious composites. In conclusion, recycling bag filters of the cement industry in fabric/polymer or fabric/cement composite materials offers a promising avenue for reducing waste generation and enhancing resource efficiency. The study underscores the importance of transitioning towards circular economy principles in industrial processes. Recycling bag filters in the cement industry is a sustainable approach that supports environmental responsibility and contributes to the circular economy. It helps conserve resources, reduce waste, and minimize industry’s impact on the environment.

Comparison of hermetic and conventional bags for maize seed preservation in Azad Kashmir, Pakistan

Maize (Zea mays L.) is a major cereal crop used as a staple food worldwide for decades. Farmers store their produce in porous polypropylene bags under humid conditions which negatively affects their quality. In this study, maize seeds were stored in hermetic and conventional bags with an initial seed moisture content of 13.5% (wet basis) and 96.3% germination for 8 months at four major maize growing districts (Athmuqam, Hattian Bala, Muzaffarabad and Rawlakot) of Azad Jammu and Kashmir, Pakistan. Due to high ambient relative humidity conditions (>80%), an increase in moisture was observed in seeds stored in porous conventional bags (14. 7%). This increase was because of high initial relative humidity conditions (79–85%) in conventional bags. Seed moisture content remained unchanged in hermetic bags and internal humidity was 59–60%. As a result of hermetic conditions, germination and seed integrity were maintained in hermetic bags compared to conventional woven bags. Germination drastically decreased in conventional bags and fell to 9 % (Athmuqam), 13 % (Hattian Bala), 11 % (Muzaffarabad) and 12 % (Rawlakot). Higher physical quality losses of maize in conventional bags were because of infestation activity of live insect pest populations (S. zeamais, R. dominica and T. castaneum) that initiated 21.7–23.7 % weight loss in polypropylene bags. Hermetic bags protected seeds from insect pest attack and maintained seed quality. Higher contamination of aflatoxin B1, G1, B2 and G2 (ppb) was recorded in seeds stored in conventional bags as compared to hermetic bags. Aflatoxin B1 was maximum in conventional bag at Hattian Bala (8.93 ppb) followed by Muzaffarabad (6.68 ppb), Athmuqam (5.02 ppb) and Rawlakot (0.71 ppb). In conclusion, the use of hermetic dry chain storage preserves maize seed quality and thus can have a significant impact on the livelihoods of smallholder farmers of humid areas.

Formulation Controls the Potential Neuromuscular Toxicity of Polyethylene Photoproducts in Developing Zebrafish.

Sunlight transforms plastic into water-soluble products, the potential toxicity of which remains unresolved, particularly for vertebrate animals. We evaluated acute toxicity and gene expression in developing zebrafish larvae after 5 days of exposure to photoproduced (P) and dark (D) leachates from additive-free polyethylene (PE) film and consumer-grade, additive-containing, conventional, and recycled PE bags. Using a "worst-case" scenario, with plastic concentrations exceeding those found in natural waters, we observed no acute toxicity. However, at the molecular level, RNA sequencing revealed differences in the number of differentially expressed genes (DEGs) for each leachate treatment: thousands of genes (5442 P, 577 D) for the additive-free film, tens of genes for the additive-containing conventional bag (14 P, 7 D), and none for the additive-containing recycled bag. Gene ontology enrichment analyses suggested that the additive-free PE leachates disrupted neuromuscular processes via biophysical signaling; this was most pronounced for the photoproduced leachates. We suggest that the fewer DEGs elicited by the leachates from conventional PE bags (and none from recycled bags) could be due to differences in photoproduced leachate composition caused by titanium dioxide-catalyzed reactions not present in the additive-free PE. This work demonstrates that the potential toxicity of plastic photoproducts can be product formulation-specific.

GERMINAÇÃO DE SEMENTES E PRODUÇÃO DE MUDAS DE BURITI (Mauritia flexuosa L.f.)

ABSTRACT Swamp palm (Mauritia flexuosa L.f.) is a typical palm tree from the Amazon and Cerrado of Brazil, whose fruits are used in cooking and the pharmaceutical industry. Seed germination of this palm is slow, irregular and often low, which makes its cultivation limited, being exploited in extractive systems. Also, little is known about seedling development, and this knowledge is important to define a protocol for the production of seedlings of this species. This research aimed to develop a protocol for the seed germination of swamp palm under semi-aseptic conditions and to evaluate the seedling development of swamp palm under different production systems. There was no germination in treatments without scarification. The best germination protocol for swamp palm was scarification with operculum removal in seeds recently extracted from the fruit with application of gibberellic acid (plant growth regulator) because it increased the rate and accelerated germination. However, imbibition in aerated water (with H2O2) proved to be suitable up to two days. The best method for seedlings production of swamp palm is the use of conventional bag (20×30 cm) with soil and manure or for producers with greater investment capacity, the use of tubes (180 cm3) for two months and subsequent transplanting to a conventional bag with soil and manure until completing six months.

Storing Peanuts in Grain Bags

HighlightsExisting bag loading equipment may be used to load both in-shell and shelled oil stock peanuts.Grain bags can be loaded at 1.2 t/m of in-shell peanuts and 2.3 t/m of shelled oil stock peanuts.Existing extraction equipment requires modification to unload shelled oil stock peanuts due to poor flow characteristics.Grain bags not suitable for storing in-shell peanuts due to significant moisture migration and quality reduction under typical Georgia conditions.Abstract.Edible grade farmers’ stock peanuts and shelled oil stock peanuts were stored in hermetically sealed silo or grain bags to determine their suitability for short-term storage. The objectives of the study were to evaluate equipment for loading and unloading the grain bags, the capacity of the grain bags, and the changes in quality. In May 2015, approximately 90 Mg of farmers’ stock (in-shell) peanuts from the 2014 crop were unloaded from a commercial warehouse, transported to Dawson, Georgia, and loaded into two 2.7 m diameter grain bags. Similarly, 85 Mg of shelled oil stock peanuts were loaded into two 2.7 m diameter grain bags. Farmers’ stock bags were unloaded after 30 and 60-d storage. A vacuum extractor and a skid steer loader were used due to wet peanuts in the top of the bag. Both oil stock bags were unloaded after 60-d storage. A skid steer loader was used to unload the oil stock bags because shelled oil stock peanuts did not flow adequately to use the conventional bag extraction equipment. Oxygen content in the farmers’ stock peanuts decreased from ambient levels (21%) to an average of 8.6% after 15-d storage. After 20-d storage, the oxygen content in the oil stock had decreased to 14%. A layer of high moisture peanuts due to moisture migration and subsequent condensation in the top of both of the farmers’ stock bags resulted in the peanuts being unsuitable for human consumption and reduced the value from $342/Mg to approximately $125/Mg for oil stock, a 63% reduction in value. No moisture problems were observed in the oil stock bags when they were unloaded. Based on these studies, sealed grain bags would be unsuitable for temporarily storing farmers’ stock peanuts under typical Georgia conditions. Sealed grain bags could possibly be used to store oil stock peanuts for 60 d, but suitable unloading equipment would have to be found or developed. Keywords: Grain bag, Groundnut, Handling, Hermetic, Peanut, Silo bag, Storage.

Assessing the environmental consequences of shelf life extension: Conventional versus active packaging for pastry cream

Shelf life extension can reduce food losses throughout the entire food chain and packaging can be an effective way to attain this goal. Along these lines, active packaging is an appealing alternative that uses natural antimicrobial compounds to inhibit the growth of microorganisms causing food spoilage. Specifically, a packaging was developed based on polyethylene film with a coating fully compatible with food (all components declared as food additive and food contact materials). This bag is monomaterial, which means that, after use, it can be considered fully recyclable. In this study, conventional and bioactive bags carrying viable Lactococcus lactis subsp. lactis and phytic acid with antimicrobial activity were used to pack pastry cream. The environmental implications of the packaging choice have been assessed applying life cycle assessment to both the empty packages and the complete food-packaging system. To assess the empty packages, a bag of 200 mL capacity was the functional unit, and all life cycle stages were included, from cradle to waste treatment. In that case, the active packaging implies an increase in all the impact categories, due to the application of the bacterial coating on the conventional bag film. When assessing the food-packaging systems, the functional unit was 218 g of packed pastry cream and the system boundaries included the whole life cycle of the pastry cream-package, considering also indirect effects in terms of shelf life and food waste. Under this perspective, the environmental load of the coating production is offset by the extension of product shelf life from 3 to 13 days, with the subsequent reduction in the waste generated along the food chain. In this way, a reduction in all the impact categories corresponding to the pastry cream in active packaging is observed, ranging from 45% for ionizing radiation to 75% for climate change. It can be concluded that, despite the limitations regarding waste estimation, extending the shelf life of foods is a key issue when assessing the environmental impacts of novel packages. Future research should focus on developing better models, based on empirical data, which relate product shelf life and potential waste. In addition, a holistic sustainability assessment should also consider economic issues under a life cycle approach.

Closed loop bioreactor system for the ex vivo expansion of human T cells

Background aimTranslation of therapeutic cell therapies to clinical-scale products is critical to realizing widespread success. Currently, however, there are limited tools that are accessible at the research level and readily scalable to clinical-scale needs. MethodsWe herein developed and assessed a closed loop bioreactor system in which (i) a highly gas-permeable silicone material was used to fabricate cell culture bags and (ii) dynamic flow was introduced to allow for dissociation of activated T-cell aggregates. ResultsUsing this system, we find superior T-cell proliferation compared with conventional bag materials and flasks, especially at later time points. Furthermore, intermittent dynamic flow could easily break apart T-cell clusters. ConclusionsOur novel closed loop bioreactor system is amenable to enhanced T-cell proliferation and has broader implications for being easily scaled for use in larger need settings.

Color–flavor locked strangelets with confinement and perturbative interactions

The properties of color–flavor locked (CFL) strangelets are investigated with the latest quark mass scaling that includes both linear confinement and leading-order perturbative interactions. With a self-consistent thermodynamics, we find that the perturbative interaction increases CFL strangelets’ radius and energy per baryon, while the one-gluon-exchange interaction has the opposite effects. With the increasing of the baryon number [Formula: see text], the energy per baryon decreases the electric charge per baryon and approaches to zero eventually. Specially at comparatively large [Formula: see text], the electric charge is nearly proportional to the two-third power of [Formula: see text] with the proportional coefficient to be about half of that in the conventional bag model.

Head to Head: Semantic Similarity of Multi–Word Terms

Terms are linguistic signifiers of domain–specific concepts. Semantic similarity between terms refers to the corresponding distance in the conceptual space. In this paper, we use lexico-syntactic information to define a vector space representation in which cosine similarity closely approximates semantic similarity between the corresponding terms. Given a multi–word term, each word is weighed in terms of its defining properties. In this context, the head noun is given the highest weight. Other words are weighed depending on their relations to the head noun. We formalized the problem as that of determining a topological ordering of a direct acyclic graph, which is based on constituency and dependency relations within a noun phrase. To counteract the errors associated with automatically inferred constituency and dependency relations, we implemented a heuristic approach to approximating the topological ordering. Different weights are assigned to different words based on their positions. Clustering experiments performed on such a vector space representation showed considerable improvement over the conventional bag–of–word representation. Specifically, it more consistently reflected semantic similarity between the terms. This was established by analyzing the differences between automatically generated dendrograms and manually constructed taxonomies. In conclusion, our method can be used to semi–automate taxonomy construction.

Effects of net house culture on the plant growth and fruit development of ‘Jen-Ju-Bar’ guava (Psidium guajava ‘Jen-Ju’)

Guava (Psidium guajava L.) is a tropical fruit belonging to the family Myrtaceae. It is produced and exported all year round in Taiwan. Since Taiwan is an infestation area of the oriental fruit fly (Bactrocera dorsalis), the conventional solution to this problem involves bagging fruit with polyethylene (PE) bag containing expanded polystyrene net sleeve (EPNS). Previous report showed that the bagging process not only increases labor and material costs, but also generates agricultural wastes. Furthermore, summer fruit produced with this method often results in poor quality, such as flavor change and shortened storage life. The objective of this study was to investigate the potential of non-bagging culture in a net house to replace the conventional PE bag bagging culture in open field. Plants in the net house received 31-37% less photosynthetic active radiation and had lower photosynthetic rate compared to bagging culture in open field, while the transpiration rate, stomatal conductance and intercellular CO2 concentration were higher. After moderate pruning, plants in the net house had higher flowering percentage. The ambient temperature in the net house was 4-8°C, lower than that inside the PE bag used in bagging culture. Non-bagging fruit had lower fruit growth rate compared to the PE + EPNS bagged fruit in the summer season. After low temperature storage, non-bagging fruit had greater performance on the fruit firmness, total soluble solids, and ascorbic acid than the bagged fruit. In addition, non-bagging fruit had lower chilling injury index (core water-soaking) and higher quality during low temperature storage (1°C for 14 days).

Solid-State NMR Study of the Paramagnetic P2-Na0.67Mn0.95Mg0.05O2 Na-Ion Battery Cathode

Lithium-ion batteries have been preferred to their sodium-ion counterparts for their higher energy density and operating voltages, but concerns about lithium shortage and rising costs have encouraged the scientific community to turn its attention to the more sustainable sodium-ion batteries (NIBs). Layered sodium transition metal oxides, such as P2-Na0.67Mn1-xMgxO2 (0≤x≤1)1, have a high theoretical capacity and are promising NIB cathodes. The structural stability required for long-term cycling remains a major challenge due to the ionic size of Na+ (70% larger than Li+), whilst intermediate phases with particular Na+/vacancy ordering patterns tend to form upon cycling. An understanding of the underlying structural and electronic processes occurring on charge and discharge is a necessary step towards devising higher performance electrode materials2. Solid-state Nuclear Magnetic Resonance (ssNMR) allows the local distortions and variations in the electronic structure and in oxidation states upon cycling to be investigated3. We present both ex situ and in situ 23Na NMR results on the P2-Na0.67Mn0.95Mg0.05O2 cathode. Paramagnetic interactions in P2-Na0.67Mn0.95Mg0.05O2 lead to large NMR shifts and very broad resonances. Fast magic angle spinning (MAS) ex situ NMR was performed to enhance the resolution and allow the signals from different local environments (with different chemical and hyperfine shifts) to be distinguished4. In order to follow the electrochemical processes in real time, and to gain insight into the underlying Na (de)intercalation mechanisms, we performed in situ ssNMR experiments on a P2-Na0.67Mn0.95Mg0.05O2//Na(s) half-cell. A schematic of the in situ bag cell is shown in Figure 1a5,6,7. In order to excite the 100 kHz wide static 23Na NMR signal observed for the pristine cathode film, we made use of the recently developed Automatic Tuning Matching Cycler (ATMC) in situ NMR approach8. The low intensity, broad cathode signal is difficult to observe due to complete overlap with the more intense signals arising from the electrolyte (1M NaTFSI in PC) and the Na metal anode2. We carried out a so-called T1 filter NMR experiment which takes advantage of the different relaxation behaviors of the various components of the bag cell to discriminate between the overlapping 23Na NMR signals. This lead to significant enhancement of the broad feature arising from the cathode. 23Na in situ NMR data measured upon initial charge at a rate of C/50 reveals an expected increase of the Na metal peak intensity due to the formation of Na-metal dendrites, and the disappearance of the broad cathode feature (see Figure 1b). These encouraging results show that in situ NMR can be applied to even extremely difficult systems - from an NMR perspective - such as paramagnetic materials2. Ongoing work focuses on the optimization of the electrochemical performances of the in situ cell to allow for multiple cycles and higher rates to be investigated. The conventional bag cell is replaced by a new cell design with increased pressure and sample size. We expect the techniques developed in this work to enable us to investigate a greater range of electrode materials using in situ NMR.

On the classification of text documents taking into account their structural features

A modification of the conventional bag of words model that can take into account the structural features of text documents in their classification (categorization) using machine learning techniques is studied. It is proposed to describe these features by relations on the set of certain lexemes and use the relation names, along with the lexeme names, as features. This is a distinction from the conventional model in which only unary relations are used. The effectiveness of the proposed machine learning techniques is analyzed using computer experiments on the class of the Reuters-21578 collection with eight known classifiers. It is shown that it is reasonable to apply the proposed models to classify documents using simple classifiers.

바이오매스 가스화 발전설비의 목질계 타르폐수 응집 처리 특성

There are difficulties in removing wood tar wastewater coming from the power plants that use wood-based fuels due to its intermittent occurrences and severe changes in the amount and concentration. This study investigated the treatment characteristics through physicochemical treatment, an improved method from the existing ones using bag filters and activated carbons to treat wood tar wastewater. In the case of chemical properties of wood tar wastewater, the content of phenols was found to be more than two times higher than that of guaiacols and carbohydrates. Installation is done to ensure that NaOH and PAC are injected automatically according to the change of pH, and then pH, turbidity and SS of the final treated water were examined. The results were 5.9, 12.6 NTU and 15.1 mg/L respectively, which confirmed the possibility of the treated water as circulation water of power plants. In the physical treatment process using a conventional bag filter, removal efficiency of chemicals was about 20%, but the treatment efficiency was improved to show chemical removal efficiency of about 80% through flocculation and sedimentation.

Bag of Visual Words Method based on PLSA and Chi-Square Model for Object Category

The problem of visual words’ synonymy and ambiguity always exist in the conventional bag of visual words (BoVW) model based object category methods. Besides, the noisy visual words, so-called “visual stop-words” will degrade the semantic resolution of visual dictionary. In view of this, a novel bag of visual words method based on PLSA and chi-square model for object category is proposed. Firstly, Probabilistic Latent Semantic Analysis (PLSA) is used to analyze the semantic co-occurrence probability of visual words, infer the latent semantic topics in images, and get the latent topic distributions induced by the words. Secondly, the KL divergence is adopt to measure the semantic distance between visual words, which can get semantically related homoionym. Then, adaptive soft-assignment strategy is combined to realize the soft mapping between SIFT features and some homoionym. Finally, the chi-square model is introduced to eliminate the “visual stop-words” and reconstruct the visual vocabulary histograms. Moreover, SVM (Support Vector Machine) is applied to accomplish object classification. Experimental results indicated that the synonymy and ambiguity problems of visual words can be overcome effectively. The distinguish ability of visual semantic resolution as well as the object classification performance are substantially boosted compared with the traditional methods.

The laryngeal tube - a helpful tool for cardiopulmonary resuscitation in the dental office?

Supraglottic airway adjuncts such as the laryngeal tube (LT) have been recommended to be used by cardiopulmonary resuscitation (CPR) first responders.Objective This study aims to evaluate the performance characteristics of dental students and dentists using the LT in comparison to a conventional bag valve mask device (BVM) within manikin CPR training. A group of eight dentists and 12 dental students performed randomised crossover CPR training using LT and BVM. Time intervals needed to perform five CPR cycles were recorded, as well as tidal and total gastric inflation volumes. Median tidal volumes 0-1025 ml (median 462.5 ml) were observed using BVM and 100-500 ml (median 237.5 ml) with LT (p = 0.02). Total gastric inflation of 0-2900 ml was measured using BVM, no gastric inflation using LT (p = 0.0005). Time intervals needed to perform five CPR cycles did not differ between BVM (range 87.5-354.5 s, median 112 s) and LT (range 84.7-322.3 s, median 114 s) (p = 0.55). A median delay of 37.6 s (range 0-82.1 s) before starting CPR was observed using LT. Lower tidal volumes but also lower or even no gastric inflation may be observed when dentists use a laryngeal tube during CPR. Respective training must focus on chest compressions. These must be started before inserting the LT or a different supraglottic airway adjunct and be delivered continuously during insertion. It is recommended to use a supraglottic airway such as an LT only after having been trained in its use.

Exploiting high level feature for dynamic textures recognition

In this paper, a novel framework is proposed for dynamic textures (DTs) recognition by learning a high level feature using deep neural network (DNN). The insight behind the method is that a DT appearing in different videos should share similar features, which can be learned for better recognition performance. Unlike many prior works only focus on low level or middle level features, we propose a novel high level feature learning method using DNN. Our goal is to construct a compact and discriminative semantic feature. The conventional bag of features approach using k-means is not semantically meaningful since the clustering criterion is based on appearance similarity. The proposed framework can effectively overcome the problem by capturing the semantic relations of the middle level by DNN. Extensive experiments with qualitative and quantitative results demonstrate the efficacy of our approach.

Qualidade de Sementes de Soja Submetidas ao Armazenamento no Oeste de Santa Catarina, Brasil

QUALITY OF SOYBEAN SEEDS UNDER STORAGE IN WESTERN SANTA CATARINA, BRAZIL High quality seeds are considered those showing good genetic, physiological, physical and sanitary properties. Quality control is of great importance for the maintenance of high quality seeds from the field to processing and storage of soybean seeds. The objective of this study was to evaluate the physiological quality of seeds of transgenic (BMX Potencia RR, BMX Energia RR, BMX Forca RR, SYN 3358 RR) and conventional soybean (BRS 284) stored in conventional bag conditions until the time of selling. The seeds were obtained in the 2009/2010 growing season and stored for seven months in Campos Novos – SC, Brazil. For this study a representative sample of the batch was collected before being submitted to storage and after seven months of storage, and was split into four replications to obtain the working samples, where tests for germination, accelerated aging, cold test, tetrazolium and electrical conductivity were performed. Analysis of variance by the F-test indicated significant differences (P <0.05) among genotypes for all variables. Considering germination after storage, only the cultivars BMX Potencia RR, BMX Energia RR and BMX Forca RR could be marketed. According to the vigor tests it was shown that only BMX Potencia RR had a high vigor, which concluded that the efficiency of conventional storage was dependent on the cultivar. Mechanical damage was potentially a major cause of viability and vigor loss in all cultivars, which is strongly associated with damage to the seed during harvesting and processing.

QUALIDADE DE SEMENTES DE SOJA SUBMETIDAS AO ARMAZENAMENTO NO OESTE DE SANTA CATARINA, BRASIL - DOI: 10.13083/1414-3984.v22n04a01

São consideradas sementes de alta qualidade aquelas que apresentam ótimas características genéticas, fisiológicas, físicas e sanitárias. O controle de qualidade assume importância fundamental para assegurar a obtenção de sementes de alta qualidade, a partir da fase de campo, do beneficiamento e armazenamento das sementes de soja. O objetivo deste trabalho foi avaliar a qualidade fisiológica de sementes de cultivares de soja transgênicas (BMX Potência RR, BMX Energia RR, BMX Força RR, SYN 3358 RR) e convencional (BRS 284) armazenadas em condições convencionais de sacaria até o momento de sua comercialização. As sementes foram obtidas na safra 2009/2010 e armazenadas por sete meses, no município de Campos Novos - SC. Coletou-se uma amostra média representativa de cada lote antes de submetê-los ao armazenamento e após sete meses, subdividiu-se em quatro repetições para obter a amostra de trabalho, onde se realizaram as determinações de germinação, envelhecimento acelerado, teste de frio, condutividade elétrica e tetrazólio. A análise de variância pelo teste F indicou diferenças significativas (P

Fisher tensors for classifying human epithelial cells

Analyzing and classifying Human Epithelial type 2 (HEp-2) cells using Indirect Immunofluorescence protocol has been the golden standard for detecting connective tissue diseases such as Rheumatoid Arthritis. However, this suffers from numerous shortcomings such as being subjective as well as time and labor intensive. Recently, several studies explore the advantages of artificial systems to automate the process, not only to reduce the test turn-around time but also to deliver more consistent results. In this paper, we extend the conventional bag of word models from Euclidean space to non-Euclidean Riemannian manifolds and utilize them to classify the HEp-2 cells. The main motivation comes from the observation that HEp-2 cells can be efficiently described by symmetric positive definite matrices which lie on a Riemannian manifold. With this motivation, we first discuss an intrinsic bag of Riemannian words model. We then propose Fisher tensors which can in turn encode additional information about the distribution of the signatures in a bag of word model. Experiments on two challenging HEp-2 images datasets, namely ICPRContest and SNPHEp-2 show that the proposed methods obtain notable improvements in discrimination accuracy, in comparison to baseline and several state-of-the-art methods. The proposed framework, while hand-crafted towards cell classification, is a generic framework for object recognition. This is supported by assessing the performance of our proposal on a challenging texture classification task.

Structured representations in a content based image retrieval context

Here, we propose an automatic system to annotate and retrieve images. We assume that regions in an image can be described using a vocabulary of blobs. Blobs are generated from image features using clustering. Features are locally extracted on regions to capture Color, Texture and Shape information. Regions are processed by an efficient segmentation algorithm. Images are structured into a region adjacency graph to consider spatial relationships between regions. This representation is used to perform a similarity search into an image set. Hence, the user can express his need by giving a query image, and thereafter receiving as a result all similar images. Our graph based approach is benchmarked to conventional Bag of Words methods. Results tend to reveal a good behavior in classification of our graph based solution on two publicly available databases. Experiments illustrate that a structural approach requires a smaller vocabulary size to reach its best performance.