Adaptive dewarping of severely warped camera-captured document images based on document map generation.

Automated dewarping of camera-captured handwritten documents is a challenging research problem in Computer Vision and Pattern Recognition. Most available systems assume the shape of the camera-captured image boundaries to be anywhere between trapezoidal and octahedral, with linear distortion in areas between the boundaries for dewarping. The majority of the state-of-the-art applications successfully dewarp the simple-to-medium range geometrical distortions with partial selection of control points by a user. The proposed work implements a fully automated technique for control point detection from simple-to-complex geometrical distortions in camera-captured document images. The input image is subject to preprocessing, corner point detection, document map generation, and rendering of the de-warped document image. The proposed algorithm has been tested on five different camera-captured document datasets (one internal and four external publicly available) consisting of 958 images. Both quantitative and qualitative evaluations have been performed to test the efficacy of the proposed system. On the quantitative front, an Intersection Over Union (IoU) score of 0.92, 0.88, and 0.80 for document map generation for low-, medium-, and high-complexity datasets, respectively. Additionally, accuracies of the recognized texts, obtained from a market leading OCR engine, are utilized for quantitative comparative analysis on document images before and after the proposed enhancement. Finally, the qualitative analysis visually establishes the system's reliability by demonstrating improved readability even for severely distorted image samples.

Stochastic calculus-guided reinforcement learning: A probabilistic framework for optimal decision-making.

Stochastic Calculus-guided Reinforcement learning (SCRL) is a new way to make decisions in situations where things are uncertain. It uses mathematical principles to make better choices and improve decision-making in complex situations. SCRL works better than traditional Stochastic Reinforcement Learning (SRL) methods. In tests, SCRL showed that it can adapt and perform well. It was better than the SRL methods. SCRL had a lower dispersion value of 63.49 compared to SRL's 65.96. This means SCRL had less variation in its results. SCRL also had lower risks than SRL in the short- and long-term. SCRL's short-term risk value was 0.64, and its long-term risk value was 0.78. SRL's short-term risk value was much higher at 18.64, and its long-term risk value was 10.41. Lower risk values are better because they mean less chance of something going wrong. Overall, SCRL is a better way to make decisions when things are uncertain. It uses math to make smarter choices and has less risk than other methods. Also, different metrics, viz training rewards, learning progress, and rolling averages between SRL and SCRL, were assessed, and the study found that SCRL outperforms well compared to SRL. This makes SCRL very useful for real-world situations where decisions must be made carefully.•By leveraging mathematical principles derived from stochastic calculus, SCRL offers a robust framework for making informed choices and enhancing performance in complex scenarios.•In comparison to traditional SRL methods, SCRL demonstrates superior adaptability and efficacy, as evidenced by empirical tests.

TopoGeoFusion: Integrating object topology based feature computation methods into geometrical feature analysis to enhance classification performance.

This study used smartphone captured RGB images of gooseberries to automatically sort into standard, premium, or rejected categories based on topology. Main challenges addressed include, separation of touching or overlapping fruits into individual entities and new method called 'TopoGeoFusion' that combines basic geometrical features with topology aware features computed from the fruits to assess the grade or maturity. Quality assessment helps in grading the fruit to determine market suitability and intelligent camera applications. Computer Vision-based techniques have been applied to automatically grade the quality of gooseberries as standard, premium, or rejected according to fruit maturity. Smartphone-captured images of 1697 Indian Star Gooseberries are contributed to the study. This work acquired images consisting multiple fruits with overlapping and non-overlapping boundaries for concurrent quality assessment. Multiple classifiers such as Random Forest, SVM, Naive Bayes, Decision Tree, and KNN were applied to grade the gooseberry fruit. Random Forest classification with a fusion feature model resulted in an accuracy of 100 % towards reject, standard, and premium classes for test sets with four training strategies. The proposed segmentation model proves reliable in fruit detection & extraction with an average mAP of 0.56, resulting in an acceptable model for grade assessment.•The study highlights the effectiveness of TopoGeoFusion in automating the grading process of gooseberry fruits using topologically computed features.•The developed models exhibit high accuracy and reliability, even in challenging scenarios such as overlapping and touching fruits.•The method provides the technique to detect and extract the occluded objects and compute the features based on the partial object's topology.

AMDPWE: Alphonso Mango Dataset for Precision Weight Estimation.

Alphonso Mango (Mangifera indica L.), is popularly known as king of mangoes in India. India is one of the leading countries in mango production. Automatic visual inspection systems for quality assessment using weight are intelligent interventions designed to evaluate fruit maturity based on various parameters. Automated systems utilize a combination of image analysis, computer vision, and artificial intelligence algorithms to estimate the weight of fruits precisely. One of the crucial quality parameters is weight, which measures the fruit's overall mass and potential quality. Integration of precision weighing mechanisms in fruit quality estimation leads to a quick and accurate method of measuring fruit weight in the marketplace. Furthermore, the fruit's demand in the market is directly connected to its size as it influences consumer preferences. Automatic precision weight estimation systems equipped with intelligent high-resolution assists in ensuring consistency in size across batches of fruits. The dataset samples consist of images of 71 Alphonso cultivars of mango fruit. The fruit is collected from the College of Horticulture Yalachahalli, Mysuru, India. The fruits were harvested in April/May 2022. The digital images of these fruits are captured using the acquisition setup with a controlled environment. Each image has a resolution of 2048×1536. The images include two orientations of each sample. The physical parameters such as the weight, fruit diameter, and width across the shoulder are also maintained. The digital images undergo pre-processing, and further, the vision-based features such as area, convex area, and minor axis for both orientations are captured.

DIMPSAR: Dataset for Indian medicinal plant species analysis and recognition.

Mobile-captured images of medicinal plants are widely used in various research investigations. Machine vision-based tasks such as the identification of plant species types for intelligent imaging device applications take a significant part in it. Botanists, farmers and researchers can reliably identify medicinal plants with the help of images captured using smartphones.  Mobile captured images can be used for quality control to make sure that the right plant species are being used in pharmaceutical products. In the field of education, pictures of medicinal plants and their usage can be used to educate learners, medical professionals, and the general public. Further, various research investigations in the area of chemistry, pharmacology, the therapeutic potential of medicinal plants, images can be employed. In this paper, we contribute a dataset of Indian medicinal plant species. The dataset is collected from different regions of Karnataka and Kerala. Datasets include characteristics such as multiple resolutions, varying illuminations, varying backgrounds, and seasons in the year. The datasets consist of 5900 images of forty plant species and single leaf images of eighty plant species consisting of 6900 samples obtained from real-time conditions using smartphones. The datasets contributed would be useful to researchers to investigate on development of algorithmic models based on image processing, machine learning, and deep learning concepts to educate about medicinal plants. The dataset can be accessed by anybody, without charge, at DOI:10.17632/748f8jkphb.2, 10.17632/748f8jkphb.3.

Identification and fine-mapping of Xa33, a novel gene for resistance to Xanthomonas oryzae pv. oryzae.

Broadening of the genetic base for identification and transfer of genes for resistance to insect pests and diseases from wild relatives of rice is an important strategy in resistance breeding programs across the world. An accession of Oryza nivara, International Rice Germplasm Collection (IRGC) accession number 105710, was identified to exhibit high level and broad-spectrum resistance to Xanthomonas oryzae pv. oryzae. In order to study the genetics of resistance and to tag and map the resistance gene or genes present in IRGC 105710, it was crossed with the bacterial blight (BB)-susceptible varieties 'TN1' and 'Samba Mahsuri' (SM) and then backcrossed to generate backcross mapping populations. Analysis of these populations and their progeny testing revealed that a single dominant gene controls resistance in IRGC 105710. The BC(1)F(2) population derived from the cross IRGC 105710/TN1//TN1 was screened with a set of 72 polymorphic simple-sequence repeat (SSR) markers distributed across the rice genome and the resistance gene was coarse mapped on chromosome 7 between the SSR markers RM5711 and RM6728 at a genetic distance of 17.0 and 19.3 centimorgans (cM), respectively. After analysis involving 49 SSR markers located between the genomic interval spanned by RM5711 and RM6728, and BC(2)F(2) population consisting of 2,011 individuals derived from the cross IRGC 105710/TN1//TN1, the gene was fine mapped between two SSR markers (RMWR7.1 and RMWR7.6) located at a genetic distance of 0.9 and 1.2 cM, respectively, from the gene and flanking it. The linkage distances were validated in a BC(1)F(2) mapping population derived from the cross IRGC 105710/SM//2 × SM. The BB resistance gene present in the O. nivara accession was identified to be novel based on its unique map location on chromosome 7 and wider spectrum of BB resistance; this gene has been named Xa33. The genomic region between the two closely flanking SSR markers was in silico analyzed for putatively expressed candidate genes. In total, eight genes were identified in the region and a putative gene encoding serinethreonine kinase appears to be a candidate for the Xa33 gene.

Diversity of global rice markets and the science required for consumer-targeted rice breeding.

With the ever-increasing global demand for high quality rice in both local production regions and with Western consumers, we have a strong desire to understand better the importance of the different traits that make up the quality of the rice grain and obtain a full picture of rice quality demographics. Rice is by no means a 'one size fits all' crop. Regional preferences are not only striking, they drive the market and hence are of major economic importance in any rice breeding / improvement strategy. In this analysis, we have engaged local experts across the world to perform a full assessment of all the major rice quality trait characteristics and importantly, to determine how these are combined in the most preferred varieties for each of their regions. Physical as well as biochemical characteristics have been monitored and this has resulted in the identification of no less than 18 quality trait combinations. This complexity immediately reveals the extent of the specificity of consumer preference. Nevertheless, further assessment of these combinations at the variety level reveals that several groups still comprise varieties which consumers can readily identify as being different. This emphasises the shortcomings in the current tools we have available to assess rice quality and raises the issue of how we might correct for this in the future. Only with additional tools and research will we be able to define directed strategies for rice breeding which are able to combine important agronomic features with the demands of local consumers for specific quality attributes and hence, design new, improved crop varieties which will be awarded success in the global market.

Different isoforms of starch-synthesizing enzymes controlling amylose and amylopectin content in rice (Oryza sativa L.).

Starch, composed of amylose and amylopectin, greatly influences rice cooking and textural quality, which in turn is controlled by various isoforms of several enzymes. Activity of one or more isoforms of starch-synthesizing enzymes results in various forms of starch structure based on the amylopectin chain length and average external, internal and core chain length distribution and hence results in varying physicochemical and cooking quality. Since the synthesis of starch is highly complex, it is crucial but essential to understand its biosynthetic pathway, starch structure and effects on the physicochemical properties that control eating and cooking quality, and alongside conduct research on gene/QTL mapping for use in marker-assisted selection (MAS) with a view to improve and select cultivars with most desirable range and class of rice starch properties. This article presents the updates on current understanding of the coordination among various enzymes/isoforms towards rice starch synthesis in endosperm and their effect on rice grain physicochemical, cooking and eating qualities. The efforts in identifying regions responsible for these enzymes by mapping the gene/QTLs have provided a glimpse on their association with physicochemical and cooking properties of rice and, hence, improvement is possible by modifying the allelic pattern, resulting in down or nil regulation of a particular enzyme. The clear understanding of the tissue specific coordination between enzyme isoforms and their subsequent effect in controlling eating and cooking properties will enhance the chances to manipulate them for getting desired range of amylose content (AC) and gelatinization temperature (GT) in improved cultivars through combining desired alleles through MAS.

Allele mining in crops: prospects and potentials.

Enormous sequence information is available in public databases as a result of sequencing of diverse crop genomes. It is important to use this genomic information for the identification and isolation of novel and superior alleles of agronomically important genes from crop gene pools to suitably deploy for the development of improved cultivars. Allele mining is a promising approach to dissect naturally occurring allelic variation at candidate genes controlling key agronomic traits which has potential applications in crop improvement programs. It helps in tracing the evolution of alleles, identification of new haplotypes and development of allele-specific markers for use in marker-assisted selection. Realizing the immense potential of allele mining, concerted allele mining efforts are underway in many international crop research institutes. This review examines the concepts, approaches and applications of allele mining along with the challenges associated while emphasizing the need for more refined 'mining' strategies for accelerating the process of allele discovery and its utilization in molecular breeding.

Introduction of bacterial blight resistance into Triguna, a high yielding, mid-early duration rice variety.

Bacterial blight (BB) is a serious disease of rice in India. We have used molecular marker-assisted selection in a backcross breeding program to introgress three genes (Xa21, xa13, and xa5) for BB resistance into Triguna, a mid-early duration, high yielding rice variety that is susceptible to BB. At each generation in the backcross program, molecular markers were used to select plants possessing these resistance genes and to select plants that have maximum contribution from the Triguna genome. A selected BC3F1 plant was selfed to generate homozygous BC(3)F(2) plants with different combinations of BB resistance genes. Plants containing the two-gene combination, Xa21 and xa13, were found to exhibit excellent resistance against BB. Single plant selections for superior agronomic characteristics were performed on the progeny of these plants, from BC(3)F(3) generation onwards. The selected plants were subjected to yield trials at the BC(3)F(8) generation and were found to have a significant yield advantage over Triguna. The newly developed lines are being entered into national multi-location field trials. This work represents a successful example of the application of molecular marker-assisted selection for BB resistance breeding in rice.