Projection Profile Research Articles

Entropy-based skew detection and correction for printed Meitei/Meetei script OCR system

In this paper, we have proposed a technique based on Horizontal Projection Profile (HPP) and Entropy for skew detection and correction for the printed Meitei/Meetei script document image which is an important step in the development of Optical Character Recognition (OCR) system for any script. This technique can be used to any script and the orientation of the document. The algorithm is implemented via MATLAB. The precise results of transforming various images with different skew angles at the rage of ± 30° with precision of 0.5° and different levels of complexity is shown.

An adaptive text-line extraction algorithm for printed Arabic documents with diacritics

The performance of document text recognition depends on text line segmentation algorithms, which heavily relies on the type of language, author’s writing style, pen type, and document quality. In this paper, we present a novel unsupervised text-line segmentation algorithm for printed Arabic documents with and without diacritics. The presented approach employs a projection profile along with connected components in an iterative manner to detect text-lines. The primary benefits of the presented algorithm are (i) it is not threshold dependent, (ii) it is not required a training phase for threshold selection, and (iii) it is robust towards page rotation, font type, size, and style variation for both with and without diacritics documents. The extensive computational simulations on manually collected dataset prove the efficiency of the proposed scheme compared with several baseline and states of the art methods, including, Voronoi, X-Y Cut, Docstrum, Smearing and Seam-carving methods. Computational time analysis also presented.

#CoveringClimateNow: A social journalism project profiling climate and health

Abstract Concerns about poor quality media reporting of climate change has led to many initiatives seeking to influence coverage. In 2019/2020, a global media collaboration was established with the aim of generating a sustained media focus on key climate-related events. This paper reports an analysis of an Australian health media organisation's contribution to the collaboration, and the opportunities this provided for public health advocates, Aboriginal and Torres Strait Islander researchers and communities, and the wider community. It presents key reflections from Croakey Health Media's contribution to the global #CoveringClimateNow collaboration, with the aim of providing practical advice to enable further such collaborations and activities in other countries. This project was run on a very small budget, and this presentation is likely to be particularly relevant for low-budget organisations and contexts. Key messages Poor quality media coverage of climate change has stimulated innovation. Collaboration locally and globally can convey solutions to climate change.

Comparative Analysis of Segmentation and Recognition Techniques for Offline Handwritten Words

A Pre-processing is the initial and vital phase in optical character recognition is the Pre-processing. Segmentation deals with the extraction of individual component from a document image. Number of techniques like projection profile, connected components, gaps between characters/components is reported in the literature for component extraction followed by feature extraction and recognition of the individual component. These techniques gives good results if components are isolated but fails if components are touched, shadowed or skewed. A novel technique is required to address such issues to enhance the recognition rate. The problem of segmentation for Roman script cursive handwriting is addressed by various authors but not enough addressed for Indian script especially Devanagari script. This paper is a review which is confined to offline handwritten script domain. It attempt to review various techniques for character segmentation considering touching characters for offline handwritten words in Devanagari script and scripts sharing similar characteristics (like Bangla, Gurumukhi), database used and their accuracy reported in the literature.

Anatomical factors associated with femoral neck fractures of elderly Beijing women.

We have developed a new approach to evaluate 2D femoral neck (FN) structure, the minimal model (MM). This model includes FNaBMD and FNWidth with two new internal structural measures, the standard deviation of normalized mineral mass projection profile distribution (FNSigma) and the displacement between center of mineral (CoM) mass and geometric center of mineral mass projection profile (FNDelta). Differences in these four structural measurements together with age, weight, and height were compared in the contralateral hip of 285 FN fracture Chinese female patients and 261 age-matched community controls. Structural variables were calculated from DXA equivalent 2D images obtained from QCT scans analyzed using Mindways Software. Review of FN scanned profiles of fracture patients and controls identified substantial reduction in mineral mass in the superior segment of FN. Fracture participants were taller, weighed less, and had lower FNaBMD and larger FNDelta, due to a larger inferior displacement in the CoM, consistent with greater reduction in superior segment bone. Logistic regression identified increased height, reduced FNaBMD, increased FNDelta, and reduced FNSigma per SD as significant independent contributors to differentiating fracture from non-fracture. Area under ROC analysis identified significant improvement in discrimination with the addition of FNDelta and FNSigma to the model including age, height, weight, and FNaBMD (C statistic 0.87 and 0.84 respectively). These data extend previous data that identified the benefit of 2D FN internal structural information in discriminating those at increased future fracture risk from recently fractured individuals. These data support continuing investigation of MM analysis as a straightforward analytical approach adding value to DXA hip aBMD in predicting fracture risk.

Text and graphics segmentation of newspapers printed in Gurmukhi script: a hybrid approach

Newspapers are always a standard medium to convey important information to masses of people in recent time as well as in old time. An automated system is required to convert information into a processable form so that information could be searchable. Many efforts have been done on Gurmukhi script documents in typed or written form, but very few articles are present on Gurmukhi script newspaper text recognition or text and image segmentation. Image/graphics segmentation of text is mandatory before feeding newspaper text to OCR for accurate results. In the literature, many techniques have been proposed for segmenting images and text, but many are complex in nature. In this article, the authors have proposed a very simple and effective hybrid approach based on run length smoothing algorithm and projection profile to segment an image from text in Gurmukhi script newspaper articles. Both horizontal and vertical run length smearing algorithm is used for labeling the regions. Logical AND operator is applied to resultant images to identify the text and image regions. To segment the image region among the labeled regions, projection profile technique is implemented. The combination of these two techniques has produced very good results.

Structured Risk Modelling of Naval Aviation Program Life Cycle Integration and Operation

A strategic capability of contemporary naval ships is the ability to launch and recover embarked aircraft such as helicopters in a maritime environment. Such operations are enormously challenging due to deck motion, limited landing space, visibility, ship’s superstructure, etc. This places extreme pressure on the pilot, ship’s crew and the platforms alike, making such shipboard operations the most dangerous of all helicopter flight missions. Therefore, the design and integration of equipment, systems and aids to ensure such operations are done as safely as is practicably possible presents ship builders, aircraft manufacturers, engineers and pilots with some extremely demanding and complex problems. Major naval ship design/build programmes that include an aviation capability will inevitably need to engage resources across multiple disciplines that include, but not limited to, engineering, design, logistics, administration, procurement, legal, alliance partners and the customer to manage project risks from the outset. This research highlights the need for a holistic/Systems Engineering approach that recognises risks across the wider ship programme, which can only be managed/resolved by cross-discipline collaboration. This paper presents a novel methodology to elicit risks qualitatively and models the relative risk profile of an aviation project throughout the ship programme life cycle. The use of an enterprise model based on the three “P” element methodology (3PE), product, process, people within an environment, has been developed. Furthermore, the research outlines a continuous management and visualisation approach that enables a process of dynamic analysis to both reduce and mitigate residual risks progressively throughout the project lifecycle to acceptable levels.

Automatic SAR Image Registration via Tsallis Entropy and Iterative Search Process

Synthetic aperture radar (SAR) image registration is a process of geometrically aligning two or more remote sensing images, acquired at different times, from different viewpoints or from different sensors. To solve the problem that determines which transformation provides the most accurate match between two images, we propose a novel Tsallis entropy-based approach combined with a sequential search strategy to significantly reduce the computational complexity compared to the existing methods, while retaining excellent SAR registration performance. The Tsallis entropy can be considered as a kind of general version of similarity metric, depending on the order of Tsallis entropy. Thus, we use Tsallis entropy as a cost function to measure the degree of the focus of an average intensity projection profile of SAR image. The global optimum of the similarity metric should be reached if the reference and sensed images are correctly registered. The proposed method consists of coarse and fine registration steps, and each step is divided into two parts: range and azimuth domain processing. From the experimental results, we verify that the proposed method outperforms conventional methods in terms of computational complexity of the algorithm owing to the sensitivity of the cost function and efficiency of sequential search strategy.

Methodology for Energy Efficiency on Lighting and Air Conditioning Systems in Buildings Using a Multi-Objective Optimization Algorithm

The purpose of this article is to develop a methodology to apply to multi-objective optimization algorithms aimed at energy efficiency in buildings, considering aspects such as incremental cost, energy consumption, greenhouse gas emissions and energy efficiency levels of lighting and air conditioning system, according to the mandatory technical regulation in public buildings in Brazil. Presenting a solution to assist in the decision making of engineers, architects or building managers for the optimal arrangements’ choice for lighting and air conditioning equipment, considering each built environment and project profile. For the validation process, a basic building was created with 15 rooms spread over three floors, according to the most common construction parameters in the North of Brazil. First, different combinations of objective-function candidates were investigated to compose the multi-objective algorithm fitness function, analyzing its performance in two central scenarios: (1) adding some “baits” in air conditioning equipment files, and (2) without this inclusion. Thus, it was found that considering only three objective functions—incremental cost, energy consumption and the air conditioning energy efficiency coefficient—it is possible to get optimal non-dominated solutions in both scenarios, thus highlighting the robustness of the proposed methodology.

The Nigeria Parkinson Disease Registry: Process, Profile, and Prospects of a Collaborative Project.

Clinical disease registries are useful for quality improvement in care, benchmarking standards, and facilitating research. Collaborative networks established thence can enhance national and international studies by generating more robust samples and credible data and promote knowledge sharing and capacity building. This report describes the methodology, baseline data, and prospects of the Nigeria Parkinson Disease Registry. This national registry was established in November 2016. Ethics approval was obtained for all sites. Basic anonymized data for consecutive cases fulfilling the United Kingdom Parkinson's Disease Brain Bank criteria (except the exclusion criterion of affected family members) are registered by participating neurologists via a secure registry website (www.parkinsonnigeria.com) using a minimal common data capture format. The registry had captured 578 participants from 5 of 6 geopolitical zones in Nigeria by July 2019 (72.5% men). Mean age at onset was 60.3 ± 10.7 years; median disease duration (interquartile range) was 36 months (18-60.5 months). Young-onset disease (<50 years) represented 15.2%. A family history was documented in 4.5% and 7.8% with age at onset <50 and ≥ 50, respectively. The most frequent initial symptom was tremor (45.3%). At inclusion, 93.4% were on treatment (54.5% on levodopa monotherapy). Per-capita direct cost for the registry was $3.37. This is the first published national Parkinson's disease registry in sub-Saharan Africa. The registry will serve as a platform for development of multipronged evidence-based policies and initiatives to improve quality of care of Parkinson's disease and research engagement in Nigeria. © 2020 International Parkinson and Movement Disorder Society.

Comparison of the Effects of Silver in Nanostructured and Ultrahigh Diluted Form on Growth and Volatile Compounds Produced by Escherichia coli and Staphylococcus aureus

Introduction: In this project, the growth and volatile metabolites profiles of Escherichia coli (E. coli ) and Staphylococcus aureus were monitored under the influence of silver base chemical, nanoparticle and ultra-highly diluted compounds. Materials &amp; Methods: The treatments were done for 12000 life cycles using silver nanoparticles (AgNPs) as well as ultra-highly diluted Argentum nitricum (Arg-n). Volatile organic metabolites analysis was performed using gas chromatography mass spectrometry (GC-MS). The results indicated that AgNPs treatment made the bacteria resistant and adapted to growth in the nanoparticle condition. The use of ultra-highly diluted Arg-n initially increased growth but it decreased later. Also, with the continuous usage of these materials, no more bacterial growth was observed. Results: The most important compounds produced by E. coli are Acetophenone, Octyl acetate, Styrene, 1,8-cineole, 4-t-butyl-2-(1-methyl-2-nitroethyl)cyclohexane, hexadecane and 2-Undecanol. The main compounds derived from S. aureus are Acetophenone,1,8-cineole, Benzaldehyde, 2-Hexan-1-ol, Tridecanol, Dimethyl Octenal and tetradecane. Acetophenone and 1,8-cineole were common and produced by both organisms. Conclusion: Based on the origin of the produced volatiles, main volatiles percentage of untreated sample is hydrocarbon (&gt;50%), while bacteria treatments convert the ratio in to aldehydes, ketones and alcohols in the case of AgNPs, (&gt;80%) and aldehydes, ketones and terpenes in the case of Arg-n (&gt;70%).

Segmentation and Recognition of Bengali Characters from Document Images

In this paper, a method to segment the Bengali character from document images and recognition of each character in multiple categories has been proposed. The proposed algorithm works in two stages. Firstly, characters are segmented from the document page from horizontal and vertical projection profile. Secondly, characters are recognized by a support vector machine (SVM) classifier using different features extracted from the characters. The proposed methodology has been evaluated by a number of document images and the experimental results demonstrate the efficiency of the proposed method.

When Urban Environment Is Restorative: The Effect of Walking in Suburbs and Forests on Psychological and Physiological Relaxation of Young Polish Adults

Background and Objectives: Physical activity, recreation and walks successfully counteract negative symptoms of stress in people, especially in large cities, and have many positive psychological and physiological effects. There are many studies showing that contact with nature plays an important role in the regeneration of the human body. The city is not without green enclaves such as forests, parks or greenery along the streets. However, it is not entirely clear how the different physical characteristics of the urban space affect mood improvement, increase of positive feelings, vitality level, etc. Materials and Methods: In the study, two urban environments (apartment and green suburbs) were used, as well as two forests (coniferous and deciduous) to measure the impact of these environments on human physiological and psychological relaxation during a walk in a randomized experiment. The participants of the experiment were 75 young adult Poles studying in the largest Polish agglomeration, Warsaw. Before each experiment, the physiological and psychological state of the participant was measured indoors (pre-test). Four psychological questionnaires were used in the project (Profile of Mood States; Positive and Negative Affect Schedule; Restorative Outcome Scale; Subjective Vitality Scale), and physiological measurements (heart rate, blood pressure) before and after the short walking program were evaluated. Results: As a result of the analyses, it was shown that both staying in an urban environment with greenery and staying in a forest environment have a positive effect on the physiological and psychological relaxation of the subjects. A short walk in the suburbs was no less attractive than a walk in the forest in fall. The above indicates that various places with urban vegetation can be successfully used for recreation, just as in a forest where forest bathing is practiced. This indicates that different places with urban greenery can be successfully used for recreation, as can the forests where forest bathing is carried out.

Appropriate Employment for Segregated Roma: Mechanisms in a Public-Private Partnership Project.

Our earlier article showed that increased employability of segregated Roma may improve their well-being and health. To achieve that, appropriate employment based on a public–private partnership could be the key. For optimal design of such a partnership, we need insight into its potential mechanisms. Evidence on this is lacking, however. This paper builds on the previously published article by focusing on mechanisms for achieving better health. Therefore, our aim was to identify the potential mechanisms by which a public–private Roma employment project could increase employability. We investigated a Roma employment project called Equality of Opportunity established by a private company, U.S. Steel Kosice in eastern Slovakia. We conducted a multi-perspective qualitative study to obtain key stakeholders’ perspectives on the potential mechanisms of a public–private Roma employment project in terms of increased employability. We found three types of mechanisms. The first type regarded formal job mechanisms, such as an appropriate employment and salary offer and a bottom-up approach in capacity building. The second type involved sustainability mechanisms, such as the personal profile of project and work-shift coordinators, the continuous offer of training and cooperation with relevant stakeholders (municipalities, community centers, etc.). The third type was cultural mechanisms, such as personal contact with project participants, attention to less-voiced groups like children, the motivation of project participants, a counter-value reciprocity approach and respect for the specifics of Roma history. Our findings imply that policymakers could consider public–private partnerships for increasing the employability of segregated Roma, as they have the potential to address a wider range of social needs simultaneously.

Effect of Micropiles on Clean Sand Liquefaction Risk Based on CPT and SPT

Liquefaction is a hazardous seismic-based phenomenon, which causes an abrupt decrease in soil strength properties and can result in the massive destruction of the built environment. This research presents a novel approach to reduce the risk of soil liquefaction using jet-grouted micropiles in clean sands. The saturated soil profile of the study project mainly contains clean sands, which are suitable to more reliably employ simplified soil liquefaction analyses. The grouting is conducted using 420 micropiles to increase the existing soil properties. The effect of jet grouting on reducing the potential of liquefaction is assessed using the results of the cone penetration test (CPT) and the standard penetration test (SPT), which were conducted before and after jet grouting by implementing micropiles in the project sites. According to three CPT-based liquefaction analyses, the Juang method predicts the most effective improvement range of the factor of safety in the clean sand. The Boulanger and Idriss, and Eurocode methods show comparable evaluations. Results of the SPT-based analyses show the most considerable increase of the factor of safety following the Boulanger and Idriss, and NCEER approaches in the SP soil. CPT- and SPT-based analyses confirm the effectiveness of jet grouting by micropiles on enhancing soil properties and reducing the risk of liquefaction.

Character Segmentation Of Degraded Odia Script

Optical Character Recognition (OCR) is a field which converts printed text into computer understandable format that is editable in nature. Odia is a regional language used in Odisha, West Bengal &amp; Jharkhand. It is used by over forty million people and still counting. With such large dependency on a language makes it important, to preserve its script, get a digital editable version of odia script. We propose a framework that takes computer printed odia script image as an input &amp; gives a computer readable &amp; user editable format of same, which eventually recognizes the characters printed in input image. The system uses various techniques to improve the image &amp; perform Line segmentation followed by word segmentation &amp; finally character segmentation using horizontal &amp; vertical projection profile.

An efficient method for extraction and recognition of bangla characters from vehicle license plates

Recognition of characters from vehicle license plate plays a vital role in vehicle tracking, controlling, and maintaining traffic on the roads and high ways. This paper presents an automatic system to detect plate area and recognize characters. The research is carried out on Bangladeshi vehicle license plates because this is a demandable research area in the present age. The method has been implemented using the five consecutive steps such as license plate detection, extraction, character localization, extraction of characters, and recognition of extracted characters. We have introduced an algorithm to detect the Region of Interest (ROI) from the input image. It is performed by applying morphological operation and histogram analysis of vertical and horizontal projection profiles. A dynamic threshold is used to filter out both horizontal and vertical histogram values and ROI is extracted from the license plate image using different geometric properties such as area, bounding box, and aspect ratio. Character segmentation is performed by applying the method of connected component analysis and bounding box technology. Finally, character recognition is carried out using Support Vector Machine (SVM) classifier where extracted Histogram of Oriented Gradient (HOG) features are used as input. The proposed algorithm is applied to 630 images of license plates of different categories of vehicles and achieved 91% accuracy in the extraction of ROI and 94.6% accuracy in the extraction of characters. We have also achieved 100% accuracy in recognition of Bangla characters from a total of 4725 Bangla characters extracted from 630 images of license plates.

The functional architecture, receptive field characteristics, and representation of objects in the visual network of the pigeon brain.

We provide an extensive review of the pigeon visual system, focussing on the known cell types, receptive field characteristics, mechanisms of perception/visual attention, and projection profiles of neurons in the thalamofugal and tectofugal pathways. The similarities and differences with the primate visual system at each stage of the visual hierarchy are highlighted. We conclude with a discussion of object and face processing in birds, as well as the current state of knowledge in the search for face-selective neurons in the avian visual system.

Nom document digitalization by deep convolution neural networks

Nom is an ancient script used in Vietnam until the current Latin-based Vietnamese alphabet became common, and a large number of ancient Nom documents are in existence. Due to the gradual degradation of Nom documents and a decrease in the number of scholars who can understand them, a system to digitalize Nom documents is urgently necessary. This paper presents a segmentation-based method for digitalizing Nom documents using deep convolution neural networks. Nom pages are preprocessed, segmented into isolated characters, and then recognized by a single-character OCR. The structure of the U-Net is applied to create segmentation maps and extract character regions from them. Subsequently, we propose coarse and fine combined classifiers to recognize each character pattern. The results by the best classifier are revised by a decoder using a langue model. The decoder is the same as the connectionist temporal classification decoder used in end-to-end text recognition systems. Compared with the traditional segmentation method using projection profiles and the Voronoi diagram (IoU = 81.23%), the segmentation method using the deep convolution neural network produces a better result (IoU = 92.08%) for detecting character regions. The proposed CNN models for recognizing segmented character patterns outperforms the traditional models using the modified quadratic discriminant function and the learning vector quantization with the recognition rate of 85.07%. The combination of coarse and fine classifiers, the training dataset with salt and pepper noises, and the attention layer are the key factors in the recognition rate improvement.

Skew decision process based on machine learning content analysis and clustering

This paper presents a robust and fast skew detection approach based on content analysis and projection profile clustering. The proposed approach is quite generic and therefore, could detect skew angle for various types of documents such as graphics, charts, postal labels, handwritten text, forms, drawings and their possible combination. The proposed approach is robust that could deal up to ±89 degree skew angle even scanned at least resolution of 50 dots per inch. Additionally, it is language independent. The proposed technique consists of mainly two steps. In the first step, corners are located except top corner. The skew angle is estimated using the cross correlation of located corners with minimum computational complexity. However, to verify the alignment, horizontal projection profile is analysed. The proposed approach is examined using open access benchmark database of scanned document images. Success rate approaching 100% within a confidence range of 0.3 degrees is reported.