Using Convolutional Neural Networks to Efficiently Extract Immense Phenological Data From Community Science Images

Community science image libraries offer a massive, but largely untapped, source of observational data for phenological research. The iNaturalist platform offers a particularly rich archive, containing more than 49 million verifiable, georeferenced, open access images, encompassing seven continents and over 278,000 species. A critical limitation preventing scientists from taking full advantage of this rich data source is labor. Each image must be manually inspected and categorized by phenophase, which is both time-intensive and costly. Consequently, researchers may only be able to use a subset of the total number of images available in the database. While iNaturalist has the potential to yield enough data for high-resolution and spatially extensive studies, it requires more efficient tools for phenological data extraction. A promising solution is automation of the image annotation process using deep learning. Recent innovations in deep learning have made these open-source tools accessible to a general research audience. However, it is unknown whether deep learning tools can accurately and efficiently annotate phenophases in community science images. Here, we train a convolutional neural network (CNN) to annotate images of Alliaria petiolata into distinct phenophases from iNaturalist and compare the performance of the model with non-expert human annotators. We demonstrate that researchers can successfully employ deep learning techniques to extract phenological information from community science images. A CNN classified two-stage phenology (flowering and non-flowering) with 95.9% accuracy and classified four-stage phenology (vegetative, budding, flowering, and fruiting) with 86.4% accuracy. The overall accuracy of the CNN did not differ from humans (p = 0.383), although performance varied across phenophases. We found that a primary challenge of using deep learning for image annotation was not related to the model itself, but instead in the quality of the community science images. Up to 4% of A. petiolata images in iNaturalist were taken from an improper distance, were physically manipulated, or were digitally altered, which limited both human and machine annotators in accurately classifying phenology. Thus, we provide a list of photography guidelines that could be included in community science platforms to inform community scientists in the best practices for creating images that facilitate phenological analysis.

Colour Detection of Agriculture Products for State Analysis

The present market demands recognition of state analysis of an agricultural product automatically rather than conventionally checking the maturity stage and ripeness of an agricultural product which is mundane . In this project we are going to determine the state of an agricultural product using machine learning algorithm with the aid of colour detection. Image processing has been a great help in all kinds of fields which also extended its applicability in agriculture as well . Determining the maturity of an agricultural product at the right time will be very much helpful for the farmers . So by implementing this algorithm the colour as well as the state of the fruit will be determined automatically when we click on the image. Libraries we have used are open CV and Pandas which will help to work with images and the statistical data we are using to convert them into RGB colour models through different functions in the jupyter notebook platform. The two important parts in a project are the prepossessing and the state analysis stages. Firstly, the pre-processing stage determines the colour by calculating the distance to tell how close we are to the actual colour and we will choose the one which has the minimum distance. The second stage is mainly to classify the ripeness and state of an agricultural product. This technique also finds its application in detecting synthetic colours in the edible products . Colour detection is the initial set in any image processing technique. In the future it helps the cashier to determine the quality of the agricultural product effectively and quickly by reducing the effort they put in the traditional method .

USE OF DYNAMIC BLOCKS FOR CREATION OF ELECTRONIC IMAGE LIBRARIES OF TYPICAL FIXING ELEMENTS BY AUTO CAD RESOURCES

The use of electronic libraries of parameterized images of objects made in the form of dynamic blocks in the practice of design work refers to resource-saving technologies that are actively used in modern production. The article considers an example of creating parameterized simplified images of fasteners using dynamic blocks of the computer-aided design system AutoCAD. Dynamic blocks can be used to create electronic image libraries of technological, design, electrical and other elements. The algorithm considered in the article to create dynamic blocks of simplified images of fasteners is introduced into the educational process at the Kyiv Polytechnic Institute named after Igor Sikorsky in the course "Engineering and Computer Graphics" and can be used in design practice. The testing of this algorithm in the training process yielded a positive result. When using parameterized drawings, students understand more deeply the impact of each parameter on the design of the object.

Diversity of Skin Images in Medical Texts: Recommendations for Student Advocacy in Medical Education

Foundational academic medical texts facilitate foundational understanding of disease recognition in medical students. Significant underrepresentation of darker skin tones and overrepresentation of lighter skin tones in dermatologic texts, general medical texts, and scientific literature is observed. This compromises the clinical tools of trainees when it comes to darker skin tones. Text publishers and editors are steadily beginning to address these disparities, but bottom-up change from trainees is necessary to comprehensively address this issue. In this article the authors propose institutional review panels as a framework for building awareness of underrepresentation of darker skin tones and ensuring that faculty intentionally share diverse presentations in didactics. They also propose trainee engagement in building diverse medical image libraries and including texts on skin of color in institutional libraries. Empowering trainees to be advocates and call out any implicit or explicit biases in image selection can engender change in this area of medical education.

Feature Extraction and Image Retrieval of Landscape Images Based on Image Processing

Facing the existing digital image libraries on landscape, researchers need to urgently solve a challenging problem: how to realize rational management and accurate retrieval of landscape images that contain feature information like hierarchy, layout, color system, and color matching. For accurate organization and labeling of landscape Images, this paper presents a novel method for feature extraction and image retrieval of landscape images based on image processing. Firstly, a color quantization process was designed for landscape images, and used to analyze the color composition and color space pattern (CSP) of such images. Next, the existing methods, which are suitable for the extraction of color features from landscape Images, were briefly reviewed, and the basic flows of our improved algorithm and division method of landscape color blocks (LCBs) were explained. Finally, the retrieval performance of landscape images was improved by matching of weighted color blocks of regional landscape, based on the multi-dimensional color eigenvectors of landscape image. The experimental results demonstrate the effectiveness of our algorithm. The research results shed light on the feature extraction from other types of color images.

PERAN PERPUSTAKAAN DALAM MEMBANGUN CITRA PERPUSTAKAAN DI ERA TEKNOLOGI INFORMASI

<p>Library as a source of information is expected to become a life-long learning for<br />pemustakanya. Currently, the library has adopted a variety of information technology development in order to provide various services to the pemustakanya. Therefore, the image of the library should be built in order to thrive in this era of globalization. A good library can be seen and measured on their success in meeting the needs of the user and can serve with the capabilities to society user. By building a positive image of the library, where the library will bring and develop the image of the institution, both within and outside of their parent institutions. In meeting the needs of improving<br />the image of the college library, then the library must have a strategy three (3) pillars of the main image. First, build an image library (image building), both improve the image of the librarian (librarian image), and the three libraries based on information and communication technology or Information and Communication Technology (ICT based). With developed a library based on information and communication technology. or Information and Communication Technology (ICT), both in the management information system of the library and digital library, then the library can provide services to the maximum, comfort, convenience to library users, convenience to the librarian staffs, good in service and processing as well in implementing strategies for, library development. This of course will improve the image of the library in providing convenience facilities library services provided to the user. </p><p>Keywords: the role of libraries, image libraries, ICT</p><p> </p>

Global 15-Meter Mosaic Derived from Simulated True-Color ASTER Imagery

This work proposes a new methodology to build an Earth-wide mosaic using high-spatial resolution ( 15 m ) Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) images in pseudo-true color. As ASTER originally misses a blue visible band, we have designed a cloud of artificial neural networks to estimate the ASTER blue reflectance from Level-1 data acquired by the Moderate Resolution Imaging Spectroradiometer (MODIS) on the same satellite Terra platform. Next, the granules are radiometrically harmonized with a novel color-balancing method and seamlessly blended into a mosaic. We demonstrate that the proposed algorithms are robust enough to process several thousands of scenes acquired under very different temporal, spatial, and atmospheric conditions. Furthermore, the created mosaic fully preserves the ASTER fine structures across the various building steps. The proposed methodology and protocol are modular so that they can easily be adapted to similar sensors with enormous image libraries.

“Critter of the Week”: Wikipedia as a Museum Outreach Tool

Many museums spend time and money fruitlessly competing with Wikipedia, creating online information resources and image galleries that will be mostly ignored, as Wikipedia is usually the highest ranked search result for any query. Wikimedia Commons can host searchable, downloadable images and Wikipedia can be easily edited by volunteers and specialists; both cost nothing to use and have a global audience. Yet most museums have no Wikipedia strategy, and often their institutional copyright policies – needlessly, for most natural history collections – prevent them from engaging and openly sharing collection information. I’ll illustrate this with the case study of the Critter of the Week project, a collaboration between Radio NZ and the Department of Conservation that relies on the open image libraries of Auckland Museum and Landcare Research. There are simple institutional policies and procedures any museum can take that will support the work of the 70,000 volunteer Wikipedia editors. An institution can also directly host edit-a-thons and Wikipedia events, organise backstage tours for local Wikipedians, and host a Wikipedian in Residence. Subject specialists in a museum can even edit and update Wikipedia themselves, reaching a larger audience than almost any other science communication medium. In some ways, this is the opposite of how GLAM (Galleries, Libraries, Archives and Museums) institutions are used to working: collaborating with non-experts, releasing imperfect and unfinished content, abandoning branding opportunities, and no longer being the single voice of authority. But if we’re serious about being relevant to our public, we need to meet them where they are – which is on Wikipedia.

From Space to Place: Place-Based Explorations of Text

New data sources, for example in the form of geotagged image libraries and digitised archives of historical text documents, provide us with new opportunities for exploring how place is described. Using a framework derived from work in human geography and information science, we illustrate how there is more to place than names and coordinates. Through a set of case studies we explore different aspects of the seemingly trivial query ‘mountains in the Alps’ addressing a range of issues including ambiguity, the use of vernacular names, ways in which concepts such as mountain are used in different locations and by different groups, approaches to automatically generating macro-maps in space and time and, finally, techniques allowing regions to be characterised and compared based on the terms used to describe them. The use of all these methods in combination allows us to come closer to a meaningful representation of place in the sense of human geography within the context of Geographic Information Science. However, our approaches focus on the naming of places and their material or perceivable properties, and there is still much work to do to properly represent place, and particularly sense of place. Nonetheless, we suggest that such approaches have considerable potential for those working in the digital humanities, and especially those concerned with contributing to a spatial turn therein.