Search

Lossy image compression is likely to produce blurred images which leads to erroneous image-level understanding. The human visual system (HVS) is focused on the area of interest present in the image. Motivated by this fact, we propose a compression-decompression algorithm focusing on the important content present in different parts of the image. Using the concept of the Guided Grad-CAM (Gradient-weighted Class Activation Mapping) technique to produce heat maps with the help of a heat map generator trained on ResNet-50, a saliency-guided encoding–decoding algorithm is developed. A wider multi-scale saliency guided convolutional neural network (MsSG-CNN) is designed, in which the notion of convolution with different size filters helps to obtain unique but different features. The feature extraction followed by multilevel fusion of features helps deep neural network (DNN) to capture contextual information and obtain high quality, good resolution, visually pleasing images with fine details. The proposed algorithm is tested on the Kodak benchmark dataset, CLIC 2019 challenging dataset, and FDDB facial images dataset. At low bit rates, the MS-SSIM of the proposed algorithm is found to be superior to JPEG, JPEG2000, BPG, WebP, and Minnen’s approaches with approximately up to 60%, 24.80%, 11.43%, 23.08% & 75% gains respectively, which is quite a significant improvement, when tested on the Kodak dataset. Similarly, at high bit rates, the improvement in MS-SSIM is approximately up to 41.67%, 37.30%, 23.90% 34.21% & 13.33% when compared with JPEG, JPEG2000, BPG, WebP, and Minnen’s approaches respectively. The improvement in PSNR at low and high bit rates is approximately up to 11.32%, 5%, 5.26% and 5.6%, 10.29%, 8.7% as compared to JPEG, Balle’s, and Lee’s algorithms respectively. The PSNR-HVS has been improved by approximately up to 27.27%, 19.15%, and 28.33%, 28% as compared to JPEG and Toderici’s algorithms respectively at low and high bit-rates. A similar type of improvement is obtained with FDDB and CLIC 2019 datasets also, which is discussed in the paper.

The current investigation was undertaken to explore the physico-biochemical properties of sewage sludge (SS) and its feasible application in agricultural field as an organic manure as source of nutrients with to solve the environmental concern. Sewage sludge samples were collected from sewage treatment plants (STP), Bhagwanpur, Varanasi, Uttar Pradesh, India and passed through a 2 mm sieve for further analysis of different physical, chemical and biological parameters. The treated sewage sludge consists of both major and micro nutrients along with a good amount of organic matter. Application of this sewage sludge has the ability to enhance the physical, chemical and biological properties of soil which is beneficial for plant growth and development sustainable soil environment. However, it also contains some amount of toxic heavy metals and organic pollutants that can adversely affect soil environment depending on the origin source of sewage sludge, and treatment process of sewage sludge. Furthermore, the toxic elements go through the food chain due to its uptake and accumulation by crops posing a possible threat to human health. Sewage sludge application in soil offers essential nutrients particularly for plant growth, maintains the organic carbon in soil and decreases environmental concern with economic factors that restrict landfill or incineration disposal of sewage sludge. However, a careful assessment of the characteristics of sewage sludge is required prior to its soil application to improve the soil health without causing environmental hazard. The SS analyzed in the present study had heavy metals content but was within permissible limits as resulted its suitable for soil application as source of nutrients.

A field experiment was conducted to find out the effect of the conjoint application of sewage sludge (SS) and fertilizers on the yield of rice-wheat cropping system using a randomized block design. The grain yield ranged between 24.99 ± 4.24 to 66.32 ± 2.58 q ha-1 and 22.50 ± 0.55 to 50.37 ± 1.07 q ha-1 in Ist year grown rice and wheat, respectively. Among all the treatments, T3 (100% recommended dose of fertilizer (RDF) + 30 t ha-1 SS) recorded a significantly highest grain yield of rice crop (66.32 and 63.37 q ha-1) and wheat crop (50.37 and 46.91 q ha-1) during 2015-16 and 2016-17 years, respectively. The straw yield in Ist rice and Ist wheat ranged between 55.11 to 81.22 q ha-1 and 35.86 to 56.62 q ha-1, whereas straw yield in IInd rice and IInd wheat were noticed between 48.42 to 79.31 q ha-1 and 30.45 to 52.32 q ha-1, respectively. The finding clearly shows that the application of SS significantly enhances the yield of rice-wheat crops, and could be an option to a sustainable use of SS. However, the precautionary measure should be followed before use. In addition, the application of SS also indicates the improvement in soil health and sustainability.

In this work, we propose a Wavelet-based Deep Auto Encoder-Decoder Network (WDAED) based image compression which takes care of the various frequency components present in an image. Specifically, we demonstrate improvements over prior approaches utilizing this framework by introducing: (a) wavelet transform pre-processing for decomposing image into different frequencies for their separate processing (b) a very deep super-resolution network as a decoder of the convolutional autoencoder in order to achieve a good quality decompressed image. The end-to-end learning is performed for four wavelet sub-bands in parallel, minimizing the computational time. The encoder compresses the image by generating the latent space representations, whereas the decoder transforms the latent space to image space. The algorithm has been tested on various standard datasets i.e., ImageNet, Set 5, Set 14, Live 1, Kodak, Classic 5, General 100 and CLIC 2019 dataset. The proposed algorithm clearly exhibited the compression performance improvement of approximately 5%, 5.5%, and 13% in terms of PSNR, PSNRB and SSIM respectively.

Colonoscopic screening and surveillance for colorectal cancer could be made safer and more efficient if endoscopists could predict histology without the need to biopsy and perform histopathology on every polyp. Elastic-scattering spectroscopy (ESS), using fiberoptic probes integrated into standard biopsy tools, can assess, both in vivo and in real time, the scattering and absorption properties of tissue related to its underlying pathology. The objective of this study was to evaluate prospectively the potential of ESS to predict polyp pathology accurately. We obtained ESS measurements from patients undergoing screening/surveillance colonoscopy using an ESS fiberoptic probe integrated into biopsy forceps. The integrated forceps were used for tissue acquisition, following current standards of care, and optical measurement. All measurements were correlated to the index pathology. A machine learning model was then applied to measurements from 367 polyps in 169 patients to prospectively evaluate its predictive performance. The model achieved sensitivity of 0.92, specificity of 0.87, negative predictive value (NPV) of 0.87, and high-confidence rate (HCR) of 0.84 for distinguishing 220 neoplastic polyps from 147 non-neoplastic polyps of all sizes. Among 138 neoplastic and 131 non-neoplastic polyps ≤ 5 mm, the model achieved sensitivity of 0.91, specificity of 0.88, NPV of 0.89, and HCR of 0.83. Results show that ESS is a viable endoscopic platform for real-time polyp histology, particularly for polyps ≤ 5 mm. ESS is a simple, low-cost, clinically friendly, optical biopsy modality that, when interfaced with minimally obtrusive endoscopic tools, offers an attractive platform for in situ polyp assessment.

In the present agricultural scenario, balanced nutrients application is a key to improved crop production without deteriorating soil health. Therefore, from environmental concern, there is need to ...

Background and Aims Artificial intelligence (AI)–based computer-aided diagnostic (CADx) algorithms are a promising approach for real-time histology (RTH) of colonic polyps. Our aim is to present a novel in situ CADx approach that seeks to increase transparency and interpretability of results by generating an intuitive augmented visualization of the model’s predicted histology over the polyp surface. Methods We developed a deep learning model using semantic segmentation to delineate polyp boundaries and a deep learning model to classify subregions within the segmented polyp. These subregions were classified independently and were subsequently aggregated to generate a histology map of the polyp’s surface. We used 740 high-magnification narrow-band images from 607 polyps in 286 patients and over 65,000 subregions to train and validate the model. Results The model achieved a sensitivity of .96, specificity of .84, negative predictive value (NPV) of .91, and high-confidence rate (HCR) of .88, distinguishing 171 neoplastic polyps from 83 non-neoplastic polyps of all sizes. Among 93 neoplastic and 75 non-neoplastic polyps ≤5 mm, the model achieved a sensitivity of .95, specificity of .84, NPV of .91, and HCR of .86. Conclusions The CADx model is capable of accurately distinguishing neoplastic from non-neoplastic polyps and provides a histology map of the spatial distribution of localized histologic predictions along the delineated polyp surface. This capability may improve interpretability and transparency of AI-based RTH and offer intuitive, accurate, and user-friendly guidance in real time for the clinical management and documentation of optical histology results.

Nickel (Ni) deficiency is common in intensively cultivated soils. As Ni is a costly input, thus, judicious use in agriculture is needed to address its deficiency economically. In view of deficiency...

Image illumination correction has been a long standing topic for research in the Computer Vision problem. However, all previous literature on this topic has either been statistical in nature in the sense that a specified algorithm has been developed for approaching a particular case of illumination normalization, or involves extremely complex deep learning methods for illumination correction of either one of over illuminated or under illuminated images. We present here a very simple deep learning based image illumination correction architecture which works on color images of paintings irrespective of whether they are under or over illuminated. We have tested the results using a synthetic database as well as on real world painting images of diverse nature.

Multi-secret image sharing techniques (MSS) extend the secret image sharing schemes. The paper reports a novel MSS scheme designed to be collusion resistant. It starts with a brief introduction of the concept thereafter discussing the related works in the domain. Security is an implicit requirement for MSS techniques. There should be no possibility of collusion among the shareholders. No less than k shareholders for (k, n) MSS scheme should be having even a slight view of the secret from their shares, n being the total number of shareholders. The paper reviews and highlights the security issues like possibility of collusion, randomness issues or robustness against tampering attack in the state-of-the-art works. It proposes a new (n, n) MSS scheme in order to rectify the issues. The algorithm encrypts N different secret images to generate N noisy share images. It resolves the existing problems in a secure, and time efficient manner. A range of experiments specifically time complexity, noise, tampering, collusion and histogram analysis are performed for rigorous security analysis. The results, thus obtained indicated that the algorithm is efficient and preserves the security requirements in a much better way than the existing MSS schemes.

Handwritten signatures are an undeniable and unique way to prove the identity of persons. Owing to the simplicity and uniqueness, it finds an essential place in the area of behavioral biometric. Signatures are the most widely accepted biometric trait by law enforcement agencies/personnel for verification purposes, especially in financial institutions, legal transactions, etc. and hence secured authentication becomes imperative. In the era of a digital age, numerous transactions are taking place, where handwritten signature verification is required by the agencies, e.g., banks, etc. In such scenarios, the process of signature verification, besides being accurate and secure, should be very fast, i.e., the real-time verification can be done. In this paper, we have proposed a convolutional neural network-based language-independent shallow architecture (sCNN(Shallow Convolutional Neural Network)) for signature verification. The proposed architecture is very simple but extremely efficient in terms of accuracy. A custom shallow convolution neural network is used to automatically learn the features of signature from the provided training data. Another contribution of the research work, which is the handwritten signature data collection for 137 subjects and 467 subjects, which are named as CVBLSig-V1 and CVBLSig-V2 respectively, has been reported in this paper. The performance of the proposed architecture has been evaluated on publicly available datasets, i.e., MCYT-75, MCYT-100, and GPDS, as well as CVBLSig-V1 and CVBLSig-V2. The performance was also compared with state of the art reported methods and shown improved, while considering the accuracy and equal error rate (EER) as performance metrics.

A pot experiment was conducted in net house of the Department of Soil Science and Agricultural Chemistry, Institute of Agricultural Sciences, Banaras Hindu University, Varanasi, India during kharif 2017 and rabi 2017-18 to evaluate the direct effect boron (B) fertilizers on plant growth parameters of rice and their residual effect on subsequent wheat crop grown in B deficient soil (0.42 mg kg-1). The experiment comprised of 9 B levels i.e., 0, 0.5, 1.0, 1.5, 2.0, 2.5, 3.0, 3.5 and 4.0 kg B ha-1 in soil as borax (B:11%) along with basal dose of nitrogen, phosphorus and potassium as treatments in a completely randomized design (CRD) with three replications. The result showed that among the levels of boron the direct application of 1.5 kg B ha-1 soil along with RDF to rice was most beneficial and brought highest improvement in growth parameters and on succeeding wheat crop the most beneficial and highest yield was in residual B of 3.0 kg B ha-1. The yield increased due to residual effect of B was statistically lower than the direct effect of B. Boron concentration in soils ranged from 0.54 to 0.43 mg kg-1 in rice and 0.29 to 1.25 mg kg-1 in wheat. The plant growth attributes like plant height, Greenness index, and number of tillers along with yield were increased by the direct and residual effect of B levels. The application of boron did not increase grain yield of rice and wheat significantly over RDF. However, application of B @ 2 kg ha-1 or higher doses significantly decreased the rice grain yield. In, wheat, the grain yield was at par in all the treatments. A significant residual effect of B application in rice was noticed even after the harvest of wheat crop particularly at highest doses of application.

Aims: To investigate the direct and residual effect of boron application on yield and nutrient content under rice-wheat cropping system in middle Gangatic alluvial plan. Study Design: Completely random design (CRD). Place and Duration of Study: Net-house of the Department of Soil Science and Agricultural Chemistry, Institute of Agricultural Sciences, Banaras Hindu University, Varanasi, India during 2017-18. Methodology: The pot experiment was comprised with ten treatments among them eight for boron (ranges from 0.5 to 4.0 mg B kg-1) along with control and recommended dose of fertilizer (RDF). Rice (Oryza sativa L.) variety ARIZE 6444 was used as test crop and after harvesting of rice crop, wheat (Triticum aestivum L.) variety HUW 468 was grown in the same pot without fresh application B. The yield data was recorded after harvesting of rice and wheat. The nutrient content in grain and straw and post-harvest soil properties were analyzed using standard protocol. Results: The maximum grain yield in rice (44.07 g pot-1) was recorded in T5 (RDF + 1.5 kg B ha-1), whereas in wheat (19.70 g pot-1) was observed in T8 (RDF + 3 kg B ha-1). The maximum straw yield in rice (24.35 g pot-1) was recorded in T5 (RDF+ 1.5 kg B ka-1), whereas in wheat (48.65 g pot-1) was in T8 (RDF + 3 kg B ha-1). Application of RDF along with 1.5 kg B ha-1 was recorded the maximum (48.99%) harvest index in rice, whereas its (B) residual effect in wheat crop was maximum in RDF + 2 kg B ha-1. Application of B @ 1.5 kg B ha-1 significantly enhanced the Fe, Cu, Mn and Zn content in rice grain, whereas residual effect of 3 kg ha-1 B application has significantly improved the Fe, Cu and Mn content in wheat grain. Conclusion: It was found that application of B did not increased grain yield of rice and wheat significantly over RDF. A significant residual effect of B application in rice was noticed even after the harvest of wheat crop particularly at highest doses of B application.

In this letter, we are proposing $Bo$ CNN architecture framework for occluded thermal face recognition. We analyzed the performance of Pretrained models using transfer learning and they exhibit promising results for thermal faces without occlusion. The performance degrades with occlusion. We have used different decision level fusion strategies post transfer learning for the performance enhancement of the pretrained models. All the fusion strategies used in the proposed work give better results compared to any of the single CNN architecture.

Computer-aided histopathological image analysis for cancer detection is a major research challenge in the medical domain. Automatic detection and classification of nuclei for cancer diagnosis impose a lot of challenges in developing state-of-the-art algorithms due to the heterogeneity of cell nuclei and dataset variability. Recently, a multitude of classification algorithms have used complex deep learning models for their dataset. However, most of these methods are rigid, and their architectural arrangement suffers from inflexibility and non-interpretability. In this research article, we have proposed a hybrid and flexible deep learning architecture O L ConvNet that integrates the interpretability of traditional object-level features and generalization of deep learning features by using a shallower Convolutional Neural Network (CNN) named as CNN 3L . CNN 3L reduces the training time by training fewer parameters and hence eliminating space constraints imposed by deeper algorithms. We used F1-score and multiclass Area Under the Curve (AUC) performance parameters to compare the results. To further strengthen the viability of our architectural approach, we tested our proposed methodology with state-of-the-art deep learning architectures AlexNet, VGG16, VGG19, ResNet50, InceptionV3, and DenseNet121 as backbone networks. After a comprehensive analysis of classification results from all four architectures, we observed that our proposed model works well and performs better than contemporary complex algorithms.

The oxidation of ammonium to nitrate by biological process is known as nitrification. This process of nitrification is accomplished by Nitrosomonas spp. and Nitrobacter spp. Current intensive agricultural systems, characterized by heavy-nitrification systems, are prone to greater losses of nitrogen through nitrate leaching and emissions of greenhouse gases (GHGs) such as nitrous oxide, contributing to the increment of global temperature and ozone layer depletion. Furthermore, nitrate, under anoxic or partially anoxic conditions, escapes into the atmosphere as gaseous forms of nitrogen (N2 and N2O) through denitrification. Synthetic nitrification inhibitors (NIs) are used to regulate nitrification process in soil. The NIs are compounds that regulate this process by inhibiting ammonia monooxygenase (AMO) enzymes. Ability of certain plant species to exudate certain organic compounds from roots that have regulatory effect on performance of nitrifying bacteria has been known as biological nitrification inhibition (BNI). It inhibits both AMO and HAO (hydroxylamine oxidoreductase) enzymatic pathway in that process. The compounds are also stable in soil and production of BNI compounds are localized mainly to the rhizosphere and therefore, their modes of action may be more efficient. Brachiaria humidicola, a tropical pasture grass capable of growing in acidic soils and humid environments, is a well-known BNI-capable species that produces biochemical compound known as brachialactone. Cropping system adoption with current move toward ecologically intensified cropping with high nutrient-use efficiency is found to be novel strategy for controlling nitrification process.

The soil-water-plant-atmosphere system (SWPAS) is a “physically integrated, dynamic system in which interacting processes of mass and energy are performed.” The SWPAS system is comprised of four different components with varying physical and chemical properties that ultimately poses a complex mechanism. Water stress is primarily caused due to nonuniform precipitation. The exhaustion of this reservoir by a crop requires its artificial reloading, which is the case of irrigation. Soil moisture has been shown to have major implications for carbon storage and related climatic feedbacks. Therefore, it is more important than ever to understand how the flow of water interacts with ecosystem health and the mechanisms controlling water fluxes at the land-atmosphere interface. Atmosphere acts as an upper buffer that takes up, transforms, and protects water, as a substance, in the climatic system. The soil-plant-atmosphere continuum (SPAC) is the pathway for water moving from soil through plants to the atmosphere. Movement of water occurs in response to differences in the potential energy of water. The flow path of water through SPAC is complex with a series of resistances offered by different components of the system. Different atmospheric, plant canopy, and soil factors affect the water flow through SPAC. With increasing water scarcity, improvement in crop water productivity will be vital in terms of food security for the future generation. As a result, the effect of soil-plant-atmosphere interactions on how ecosystems respond to and exert influence on, the global environment remains difficult to predict.

Facial features are defined as the local relationships that exist amongst the pixels of a facial image. Hand-crafted descriptors identify the relationships of the pixels in the local neighbourhood defined by the kernel. Kernel is a two dimensional matrix which is moved across the facial image. Distinctive information captured by the kernel with limited number of pixel achieves satisfactory recognition and retrieval accuracies on facial images taken under constrained environment (controlled variations in light, pose, expressions, and background). To achieve similar accuracies under unconstrained environment local neighbourhood has to be increased, in order to encode more pixels. Increasing local neighbourhood also increases the feature length of the descriptor. In this paper we propose a hand-crafted descriptor namely Centre Symmetric Quadruple Pattern (CSQP), which is structurally symmetric and encodes the facial asymmetry in quadruple space. The proposed descriptor efficiently encodes larger neighbourhood with optimal number of binary bits. It has been shown using average entropy, computed over feature images encoded with the proposed descriptor, that the CSQP captures more meaningful information as compared to state of the art descriptors. The retrieval and recognition accuracies of the proposed descriptor has been compared with state of the art hand-crafted descriptors (CSLBP, CSLTP, LDP, LBP, SLBP and LDGP) on bench mark databases namely; LFW, Colour-FERET, and CASIA-face-v5. Result analysis shows that the proposed descriptor performs well under controlled as well as uncontrolled variations in pose, illumination, background and expressions., Comment: arXiv admin note: text overlap with arXiv:2201.00504

In this paper a local pattern descriptor in high order derivative space is proposed for face recognition. The proposed local directional gradient pattern (LDGP) is a 1D local micropattern computed by encoding the relationships between higher order derivatives of the reference pixel in four distinct directions. The proposed descriptor identifies relationship between the high order derivatives of the referenced pixel in four different directions to compute the micropattern which corresponds to the local feature. Proposed descriptor considerably reduces the length of the micropattern which consequently reduces the extraction time and matching time while maintaining the recognition rate. Results of the extensive experiments conducted on benchmark databases AT&T, Extended Yale B and CMU-PIE show that the proposed descriptor significantly reduces the extraction as well as matching time while the recognition rate of the descriptor is almost similar to existing state of the art methods. Moreover the proposed descriptor is more resistant against the AWGN compared to the other state of the art descriptors used for face recognition problems.

The use of Deep Learning (DL) based methods in medical histopathology images have been one of the most sought after solutions to classify, segment, and detect diseased biopsy samples. However, given the complex nature of medical datasets due to the presence of intra-class variability and heterogeneity, the use of complex DL models might not give the optimal performance up to the level which is suitable for assisting pathologists. Therefore, ensemble DL methods with the scope of including domain agnostic handcrafted Features (HC-F) inspired this work. We have, through experiments, tried to highlight that a single DL network (domain-specific or state of the art pre-trained models) cannot be directly used as the base model without proper analysis with the relevant dataset. We have used F1-measure, Precision, Recall, AUC, and Cross-Entropy Loss to analyse the performance of our approaches. We observed from the results that the DL features ensemble bring a marked improvement in the overall performance of the model, whereas, domain agnostic HC-F remains dormant on the performance of the DL models.

Feature description is one of the most frequently studied areas in the expert systems and machine learning. Effective encoding of the images is an essential requirement for accurate matching. These encoding schemes play a significant role in recognition and retrieval systems. Facial recognition systems should be effective enough to accurately recognize individuals under intrinsic and extrinsic variations of the system. The templates or descriptors used in these systems encode spatial relationships of the pixels in the local neighbourhood of an image. Features encoded using these hand crafted descriptors should be robust against variations such as; illumination, background, poses, and expressions. In this paper a novel hand crafted cascaded asymmetric local pattern (CALP) is proposed for retrieval and recognition facial image. The proposed descriptor uniquely encodes relationship amongst the neighbouring pixels in horizontal and vertical directions. The proposed encoding scheme has optimum feature length and shows significant improvement in accuracy under environmental and physiological changes in a facial image. State of the art hand crafted descriptors namely; LBP, LDGP, CSLBP, SLBP and CSLTP are compared with the proposed descriptor on most challenging datasets namely; Caltech-face, LFW, Colour-FERET, and CASIA-face-v5. Result analysis shows that, the proposed descriptor outperforms state of the art under uncontrolled variations in expressions, background, pose and illumination.

Sewage sludge (SS) in the soil acts as a slow-release organic fertilizer, and its nutrient supplying capability and heavy metal release occur for a prolonged period depending upon the applied doses. Field experiment not only evaluated the direct impact of SS application on rice (Oryza sativa L.) but also tracked the accumulation of lead (Pb), cadmium (Cd), chromium (Cr), and nickel (Ni) content in succeeding wheat (Triticum aestivum L.) crop and next-season rice and wheat crop. The field experiment was conducted with different levels of SS (15, 30, and 45 t ha−1) alone and in combination with 100% and 50% recommended doses of fertilizers (RDF). The findings indicated that the addition of SS (45 t ha−1) alone and in combination with inorganic fertilizers increased heavy metal accumulation in grain and straw of rice–wheat system and also led to enhanced DTPA-extractable metal content in post-harvest soil. Heavy metal concentrations in crops (except Cr content in straw) and soil stay below the phytotoxic limits in all treatments. However, total Cd in the soil exceeds the permissible limit with the sole application of SS beyond 30 t ha−1. This study admitted that one-time application of SS at the lower dose and reaping its benefits in subsequent crops can be an effective strategy of SS utilization in rice–wheat system.

In the recent advancement of machine learning methods for realistic image generation and image translation, Generative Adversarial Networks (GANs) play a vital role. GAN generates novel samples that look indistinguishable from the real images. The image translation using a generative adversarial network refers to unsupervised learning. In this paper, we translate the thermal images into visible images. Thermal to Visible image translation is challenging due to the non-availability of accurate semantic information and smooth textures. The thermal images contain only single-channel, holding only the images’ luminance with less feature. We develop a new Cyclic Attention-based Generative Adversarial Network for Thermal to Visible Face transformation (TVA-GAN) by incorporating a new attention-based network. We use attention guidance with a recurrent block through an Inception module to reduce the learning space towards the optimum solution.

Biochar is considered as a potential substitute for soil organic matter (SOM). Considering the importance of biochar, the present review is based on the different benefits and potential risks of the application of biochar to the soil. Biochar addition to low organic carbon soils can act as a feasible solution to keep soil biologically active for the cycling of different nutrients. The application of biochar could improve soil fertility, increase crop yield, enhance plant growth and microbial abundance, and immobilize different contaminants in the soil. It could also be helpful in carbon sequestration and the return of carbon stock back to the soil in partially combusted form. Due to the large surface area of biochar, which generally depends upon the types of feedstock and pyrolysis conditions, it helps to reduce the leaching of fertilizers from the soil and supplies additional nutrients to growing crops. However, biochar may have some adverse effects due to emissions during the pyrolysis process, but it exerts a positive priming effect (a phenomenon in which subjection to one stimulus positively influences subsequent stimulus) on SOM decomposition, depletion of nutrients (macro- and micro-) via strong adsorption, and impact on soil physicochemical properties. In view of the above importance and limitations, all possible issues related to biochar application should be considered. The review presents extensive detailed information on the sustainable approach for the environmental use of biochar and its limitations.

Signature verification has been one of the major researched areas in the field of computer vision. Many financial and legal organizations use signature verification as access control and authentication. Signature images are not rich in texture; however, they have much vital geometrical information. Through this work, we have proposed a signature verification methodology that is simple yet effective. The technique presented in this paper harnesses the geometrical features of a signature image like center, isolated points, connected components, etc., and with the power of Artificial Neural Network (ANN) classifier, classifies the signature image based on their geometrical features. Publicly available dataset MCYT, BHSig260 (contains the image of two regional languages Bengali and Hindi) has been used in this paper to test the effectiveness of the proposed method. We have received a lower Equal Error Rate (EER) on MCYT 100 dataset and higher accuracy on the BHSig260 dataset.

Thirty bread wheat genotypes were tested by adopting Randomized Block Design with three replications during 2019-20, under two different environments, i.e. early and timely sown conditions. The ultimate goal was to determine the relationship between yield and yield contributing traits and classify traits that have the highest direct and indirect effects on grain yield under both environmental circumstances. Grain yield was positively and significantly correlated with no. of tiller/plant, no. of grains/spike, relative water content, spike fertility, harvest index, grain zinc content and chlorophyll content at the level of both genotype and phenotype; conversely, found significantly negative with canopy temperature and non-significant with days to 50 % flowering and seedling length. Under stress condition, the correlation for grain yield/plant was found significant, and it was correlated positively with no. of tiller/plant, spike fertility, relative water content, harvest index and grain zinc content and non-significantly with seedling length, no. of grain/spike, chlorophyll content, flag leaf area and thousand-grain weight. At the level of both genotype and phenotype, grain yield per plant had a high direct effect in the positive direction by harvest index followed by no. of tiller/plant, no. of grain/spike, relative water content. Thus, more weightage should be given towards these traits as selecting these traits can be rewarding to achieve high yielding wheat genotypes.

The sterility of drug products intended for parenteral administration is a critical quality attribute (CQA) because it serves to ensure patient safety, and is thus a key requirement by health authorities. Whilst sterility testing is a probabilistic test, the assurance of sterility is a holistic concept including adequate design of manufacturing facilities, process performance, and product design. Container closure integrity testing (CCIT) is necessary to confirm the integrity of a container closure system (CCS), until the end of a products’s shelf life. The new and revised United States Pharmacopeia (USP) informational chapter is a comprehensive guidance on CCI. Nevertheless, practical considerations including the choice of CCIT methods, the acceptance criteria, or the positive control samples (artificial leaks) must be addressed by the pharmaceutical manufacturer. This study is the first to provide a systematic comparison of four commonly used physical CCIT (pCCIT) methods [Helium (He) leak, vacuum decay, laser-based headspace analysis (HSA), and dye ingress] and four commonly used modes of creating artificial leaks (laser-drilled micro holes, copper wire introduced leaks, and two types of capillary leaks). The results from these experiments provide comprehensive data to allow a direct comparison of the capabilities of the individual methods. The results confirmed that the He leak detection method, which is considered the “gold-standard” for pCCIT regarding method sensitivity, indeed demonstrates the highest detection sensitivity (lowest detection limit). In comparison to the dye ingress method, HSA and vacuum decay, also demonstrated better detection sensitivity in our study. Capillary leaks with orifice diameter (capillary leak with flow according to an ideal orifice) and micro holes yielded similar leak rates, whereas capillaries with nominal diameters yielded significantly lower leak rates. In conclusion, method sensitivity cannot be compared by means of a leak diameter, but requires the consideration of multiple impacting factors (e.g. path length, uniformity).

Use of sewage sludge (SS) in crop production is a feasible strategy for its disposal; however, its application may pose an adverse impact on soil and human health. Therefore, identification of the permissible level of SS is essential to prevent soil contamination. This research not only evaluated the impact of SS application on spinach (Spinacia oleracea L.) biomass yield but also tracked the accumulation of heavy metals in soil and plants. A pot experiment was conducted on Inceptisol with different levels of SS (0, 5, 10, 15, 20, 25, 30, 35, and 40 t ha−1) with recommended dose of fertilizers (RDF). The applications of SS at 20 t ha−1 resulted in the highest biomass yield; however, the concentration of zinc (Zn) and cadmium (Cd) has exceeded the safe limit in leaves. Heavy metal accumulation in the plant was the highest in SS at 40 t ha−1. Spinach grown at 20 t ha−1 and higher dose of SS exceeded the safe limit of Zn and Cd concentration in leaves, and the translocation factor (TF) of lead (Pb) and Cd was found to be > 1. The hazard quotient (HQ) of Pb > 1 at higher doses of SS indicates health hazard if spinach is used for consumption. Assessment of health risk showed that there was a possibility of Pb hazard at a high dose of SS (HI > 1). Evaluation of various soil pollution indexes revealed that the addition of SS enhanced the buildup of Cd and chromium (Cr) in soil. This study advocated the use of SS at 10 t ha−1 to sustain soil quality with no risk of food chain contamination.

Widespread use of zinc oxide nanoparticles (ZnO-NPs) threatens soil, plants, terrestrial and aquatic animals. Thus, it is essential to explore the fate and behavior of NPs in soil and also its mechanism of interaction with soil microbial biodiversity to maintain soil health and quality to accomplish essential ecosystem services. With this background, the model experiment was conducted in the greenhouse to study the impact of ZnO-NPs on soil taking maize as a test crop. The X-ray diffraction, Fourier transform infrared spectroscopy, Scanning electron microscopy and Particles size analysis of engineered NPs confirmed that the material was ZnO-NPs (particle size—-65.82 nm). The application of ZnO-NPs resulted in a significant decrease in soil pH. Significantly high EC (0.13 dS m−1) was recorded where ZnO-NPs were applied at the rate of 2.5 mg Zn kg−1 soil over control (0.12 dS m−1). A significant increase in soil available phosphorus was observed on applying ZnO-NPs (15.29 mg kg−1 of soil) as compared to control (11.84 mg kg−1 of soil). Maximum soil available Zn (2.09 mg kg−1) was recorded in ZnO-NPs-amended soil (T11) which was significantly higher than control (0.33 mg kg−1) as well as treatments containing conventional zincatic fertilizers. The inhibition rates of dehydrogenase enzyme activity in the presence of 0.5 mg, 1.25 mg and 2.5 mg ZnO-NPs per kg soil were 31.3, 46.2 and 49.7%, respectively. Soil microbial biomass carbon was significantly reduced (103.33 µg g−1 soil) in soils treated with ZnO-NPs over control (111.33 µg g−1 soil). Soil bacterial count was also significantly lesser (12.33 × 105 CFU) in the case where 2.5 mg kg−1 ZnO-NPs were applied as compared to control (21.33 × 105 CFU). The corresponding decrease in fungal and actinomycetes colony count was 24.16, 37.35, 46.15% and 14.59, 17.97, 22.45% with the application of 0.5 mg, 1.25 mg and 2.5 mg ZnO-NPs per kg soil, respectively, as compared to control. Thus, the use of ZnO-NPs resulted in an increase in soil available Zn but inhibited soil microbial activity.

The area of face recognition is one of the most widely researched areas in the domain of computer vision and biometric. This is because the non-intrusive nature of face biometric makes it comparatively more suitable for application in area of surveillance at public places such as airports. The application of primitive methods in face recognition could not give very satisfactory performance. However, with the advent of machine and deep learning methods and their application in face recognition, several major breakthroughs were obtained. The use of 2D convolution neural networks(2D CNN) in face recognition crossed the human face recognition accuracy and reached to 99%. Still, robust face recognition in the presence of real-world conditions such as variation in resolution, illumination and pose is a major challenge for researchers in face recognition. In this work, we used video as input to the 3D CNN architectures for capturing both spatial and time domain information from the video for face recognition in real-world environment. For the purpose of experimentation, we have developed our own video dataset called CVBL video dataset. The use of 3D CNN for face recognition in videos shows promising results with DenseNets performing the best with an accuracy of 97% on CVBL dataset.

With the advent of 2-dimensional Convolution Neural Networks (2D CNNs), the face recognition accuracy has reached above 99%. However, face recognition is still a challenge in real world conditions. A video, instead of an image, as an input can be more useful to solve the challenges of face recognition in real world conditions. This is because a video provides more features than an image. However, 2D CNNs cannot take advantage of the temporal features present in the video. We therefore, propose a framework called \(Sf_{3}CNN\) for face recognition in videos. The \(Sf_{3}CNN\) framework uses 3-dimensional Residual Network (3D Resnet) and A-Softmax loss for face recognition in videos. The use of 3D ResNet helps to capture both spatial and temporal features into one compact feature map. However, the 3D CNN features must be highly discriminative for efficient face recognition. The use of A-Softmax loss helps to extract highly discriminative features from the video for face recognition. \(Sf_{3}CNN\) framework gives an increased accuracy of 99.10% on CVBL video database in comparison to the previous 97% on the same database using 3D ResNets.

Nanotechnology had a wide potential of its novel applications in the fields of plant nutrition to meet the future demands of the growing population because nanoparticles (NPs) have unique physicochemical properties, i.e., high surface area, high reactivity, tunable pore size, and particle morphology. Management of optimum nutrients for sustainable crop production is a priority area of research in agriculture. In this regard, nanonutrition concerns with the provision of nanosized nutrients for sustainable crop production. The application of nanomaterials for delivery of nutrients and growth-promoting compounds to plants has become more and more popular and their utilization at the proper place, at the proper time, in the proper amount and of the proper composition affects the use efficacy of fertilizers. Using this technology, we can increase the efficiency of micronutrients delivery to plants. In the literature, various NPs and nanomaterials (NMs) have been successfully used for better nutrition of crop plants compared to the conventional fertilizers. This review summarizes the synthesis of nanofertilizers, characterization of nanofertilizers, NPs, and NMs as micronutrient fertilizers and describing their role in improving growth and yield of crops, uptake, translocation, and fate of nanofertilizers in plants and environmental hazard of NPs and NMs application.

Rhizobia in association with legumes form an effective symbiosis and fix atmospheric nitrogen for uptake by plants. Nitrogen fixation in leguminous crops contributes significantly in maintaining fertility of soil. For the growth of rhizobia and legume-rhizobial association, drought stress is one of the limiting factors, among different stress factors in the environment. Under the arid/semi-arid conditions, establishment of an effective rhizobium-legume interaction is very sensitive. Drought conditions affect root development, nodulation, chlorophyll content, changes in cell volume and concentration of solutes and other properties which are important for biological nitrogen fixation. Thus, interactions of rhizobia and legumes to drought are very sensitive in maximizing the benefits of nitrogen fixation. Various studies have been conducted on different aspects to overcome the shortcomings of drought stress on biological nitrogen fixation. These strategies include screening of germplasms, genetic multiplication of drought-tolerant genotypes, tissue culture, biological approach and biotechnological interventions. Rhizobia play vital role in the production of plant’s metabolites, molecular responses, adjustment of hormones and dissolution and utilization of nutrients, to evade moisture stress conditions. Present chapter elaborates the detailed studies on the impact of drought stress on rhizobia and legumes grown in different moisture levels. Different strategies and techniques to overcome the shortcomings of drought stress on biological nitrogen fixation are also presented and discussed in logical manner.

Climate is a major factor that governs several things starting from the origin of the different animals, and food availability for human and animals. The growth of crops species is becoming more vulnerable due to the climate now. The living ecosystem of every creature depends on the climate. Climate change is the prime threat to the sustainability of our ecosystem and continuous emission of the greenhouse gases is making it more perilous. As a consequence, an unanticipated shift in the dynamics of plant–soil cross-talk is encountered. Nevertheless, gradual escalation of mean earth surface temperature can potentially curtail the duration of the growth period, yield, and water productivity. Every major crop are expected to decline due to erratic precipitation and higher water demands under elevated temperature. In this chapter, we mainly highlight the impact of fluctuating climatic elements on terrestrial flora, edaphic conditions, and their mutual interactions. Surging air temperature is detrimental for the soil carbon stock and its depletion hampers the rhizospheric processes, biochemical cycles, and ultimately affects plant species. We have also discussed different processes involved in plant–soil interactions at different stages of primary or secondary succession.

The pot experiment was conducted to explore the phytoremediation potential of two different marigold species grown in heavy metals contaminated red, black, alluvial, recent river clay, sewage irrigated, sewage sludge, and garden soil. Different soil types were treated uniformly with lead (20 mg Pb kg−1 soil), cadmium (5 mg Cd kg−1 soil), chromium (30 mg Cr kg−1 soil) and nickel (10 mg Ni kg−1 soil). Completely randomized design (CRD) was used with three replications. African marigold (Tagetes erecta) recorded ∼89.4% more dry matter yield over French marigold (Tagetes patula) when grown under metals treated soils. Both the marigold species were highly effective for removing Cd and Ni from contaminated soils (TF >1) however, Ni (TF ∼14.9) was more efficiently accumulated by T. patula and Cd (TF ∼12.1) by T. erecta. Higher biomass yield in T. erecta resulted higher accumulation of heavy metals (except Cr) compared to T. patula. Assessment of contamination factor (CF) and geo-accumulation index (Igeo) of heavy metals indicates that post-harvest soils had moderate to high degree of contamination by different metals, Cr being the highest. It may be concluded that T. erecta was more efficient in extracting heavy metals from different heavy metals contaminated soils. Novelty statement Contamination of land with heavy metals poses severe environmental threats. Physical and chemical remediation techniques are generally used for remediating metals contaminated sites. These methods are cost-intensive and therefore, commercially non-viable, besides being disruptive in nature and causing deterioration of soil. Alternatively, bio-remediation techniques are cost-effective and environment friendly. Among the various phytoremediation techniques, hyperaccumulator plants are most commonly used for the remediation of the contaminated sites. It has been found that different species of the same plant (marigold) differ in their ability to accumulate metals under various contaminated soils having different properties. Thus, this experiment provided an unique opportunity to investigate the effect of various soil properties on metal accumulation efficacy of marigold under metal-spiked soils. Marigold plants can grow rapidly by developing a robust root system which helps them to survive under contaminated soil environment. Thus, marigold being ornamental plant could be used to decontaminate polluted sites while providing ornamental value and may serve as a source of commercially valuable products extracting metals from biomass by way of incineration. However, meager information is available about the usage of various marigold species for phytoremediation of heavy metals under different metal-polluted soils. In the current experiment, we intend to evaluate the potential use of two different marigold species (Tagetes patula and Tagetes erecta) in remediating heavy metals under nine soils of different nature spiked with metals and assessing heavy metals pollution load indexes in these polluted soils.

A large proportion of world’s agricultural land is becoming less productive or completely unproductive due to different environmental factors. Drought is one of the major agriculture constraints which is caused by insufficient rainfall, prolonged and frequent dry spells or changes in rainfall patterns. Drought impairs growth, water relations and water use efficiency of plants, which further alters their morphological, physiological and biochemical activities. Crop growth models predict that occurrence and intensity of drought will be more severe in future. In the current scenario, to meet global food demands, various strategies have been formulated to cultivate the crops under drought-affected area. Among them, the use of different microbial community could be a viable strategy, which enables plants to combat with water stress through various direct and indirect ways. The use of microbial inoculation for drought stress management is considered as cost-effective and more eco-friendly approach than traditional methods. Various rhizospheric soil microbes, including arbuscular mycorrhizal (AM) fungi, N-fixing bacteria and plant growth promoting microbes (PGPMs), help in stress resistance and better plant performance. PGPMs represent a broad range of archaea, bacteria and fungi, which are having excellent root association ability to produce different enzymes and metabolites for various abiotic stress tolerances. In the present chapter, the exploration of potential soil and root microbiome and their mechanism of actions for drought tolerance in relation to better plant growth and development have been discussed.

We developed an architecture considering the problem of the presence of various objects like glasses, scarfs, masks, etc. on the face. These types of occluders greatly impact recognition accuracy. Occluders are simply treated as a source of noise or unwanted objects in an image. Occlusion affects the appearance of the image significantly. In this paper, a novel architecture for the occlusion removal of specific types like glasses is dealt with. A synthetic mask for this type of occlusion is created and facial landmarks are generated which are further used for image completion method is used to complete the image after removing the occluder. We have trained the model on celebA dataset, which is available publicly. The experimental results show that the proposed architecture for the occlusion removal effectively worked for the faces covered with glasses or scarfs.

In today’s world, where the need for security is paramount and biometric access control systems are gaining mass acceptance due to their increased reliability, research in this area is quite relevant. Also with the advent of IOT devices and increased community support for cheap and small computers like Raspberry Pi its convenient than ever to design a complete standalone system for any purpose. This paper proposes a Facial Biometric System built on the client-server paradigm using Raspberry Pi 3 model B running a novel local descriptor based parallel algorithm. This paper also proposes an extended version of Local Gradient Hexa Pattern with improved accuracy. The proposed extended version of LGHP improved performance as shown in performance analysis. Extended LGHP shows improvement over other state-of-the-art descriptors namely LDP, LTrP, MLBP and LVP on the most challenging benchmark facial image databases, i.e. Cropped Extended Yale-B, CMU-PIE, color-FERET, LFW, and Ghallager database. Proposed system is also compared with various patents having similar system design and intent to emphasize the difference and novelty of the system proposed.