TEK KATLI DUVAR DEFORMASYONUNUN GÖRÜNTÜ İŞLEME TEKNİKLERİ KULLANILARAK BELİRLENMESİ

Image processing technique has been used frequently in the solution of engineering problems recently. In engineering studies, photographs are taken at certain intervals between the initial state of the material and the state after the change, and changes during the study are observed with the Image processing technique. Based on these photos, the change is transferred to numerical data and the change of the material is observed thanks to these data. Package program systems are used in Image processing technique applications. But these systems are quite expensive systems. In this study, a simpler and feasible system has been developed. The initial sliding test was carried out on 9 single-layer wall systems with natural stones in 20 * 30 * 10 cm dimensions. The displacement values formed on the walls under load during the experiments were measured with the help of potentiometric linear rulers. At the same time, photographs were taken at certain intervals from the baseline to the conclusion of the experiment. The photographs were digitized in the ArcGIS program and the changes on the wall were converted into numerical data. Experimental data and data obtained by photographs were compared. As a result of this comparison, 84% similarity is observed between experimental values and analytical values. It is observed that the image digitization application performed as a result of the study yielded very successful results. In this context, it is believed that the use of this system will be both fast and economically beneficial in larger scale experiments and the number of data.

Green Open Space Planning in Improving the Quality of Space in the Mamuju Urban Area

The increase in regional demographics certainly affects the use of energy for transportation and households which will ultimately have implications for greenhouse gas (CO2) emissions in the region. This study focuses on the planning of green open space in the Mamuju Urban Area in order to minimize the effects of greenhouse gases so that the quality of space in the area is maintained. This research is a type of quantitative descriptive research that explores the condition of green open space in the Mamuju Urban Area and takes into account the existing emission potential. The data analysis used is AHP (scoring and weighting) to determine the value and influence of each thematic, image digitization and field observations to determine the existing green open space in the Mamuju Urban Area, and overlay using the ArcGIS 10.8 application to combine maps that be a research indicator. The results obtained from this study are that the Mamuju Urban Area continues to grow from time to time, the distribution of existing green open space continues to decrease along with land use changes that continue to occur, and from the analysis of potential emissions, the largest green open space planning directive is private green open space planning with an area of 354, 14 Ha.

Smartpathk: a platform for teaching glomerulopathies using machine learning

Background With the emergence of the new coronavirus pandemic (COVID-19), distance learning, especially that mediated by information and digital communication technologies, has been adopted in all areas of knowledge and at all levels, including medical education. Imminently practical areas, such as pathology, have made traditional teaching based on conventional microscopy more flexible through the synergies of computational tools and image digitization, not only to improve teaching-learning but also to offer alternatives to repetitive and exhaustive histopathological analyzes. In this context, machine learning algorithms capable of recognizing histological patterns in kidney biopsy slides have been developed and validated with a view to building computational models capable of accurately identifying renal pathologies. In practice, the use of such algorithms can contribute to the universalization of teaching, allowing quality training even in regions where there is a lack of good nephropathologists. The purpose of this work is to describe and test the functionality of SmartPathk, a tool to support teaching of glomerulopathies using machine learning. The training for knowledge acquisition was performed automatically by machine learning methods using the J48 algorithm to create a computational model of an appropriate decision tree. Results An intelligent system, SmartPathk, was developed as a complementary remote tool in the teaching-learning process for pathology teachers and their students (undergraduate and graduate students), showing 89,47% accuracy using machine learning algorithms based on decision trees. Conclusion This artificial intelligence system can assist in teaching renal pathology to increase the training capacity of new medical professionals in this area.

Image Quality Degradation Caused by Color Transformations in Multispectral Imaging—A Practical Review

The still imaging portion of FADGI [1] continues to be a living document that has evolved from its theoretical digital imaging principles of a decade ago into adaptations for the realities of day-to-day cultural heritage workflows. While the initial document was a bit disjointed, the 2016 version is a solid major improvement and has proven very useful in gauging digital imaging goodness. [2] With coaching, encouragement and focused attention to detail many users, even the unschooled, have achieved 3-star compliance, sometimes with high-speed sheet-fed document scanners. 4-star levels are not far behind. This is a testimony to an improved digital image literacy for the cultural heritage sector that the authors articulated at the beginning of the last decade. This objective and science based literacy has certainly evolved and continues to do so. It is fair to say that no other imaging sector has such comprehensive objective imaging guidelines as those of FADGI, especially in the context of high volume imaging workflows. While initial efforts focused on single instance device benchmarking, future work will concentrate on performance consistency over the long term. Image digitization for cultural heritage will take on a decidedly industrial tone. With practice, we continue to learn and refine the practical application of FADGI guidelines in the preservation of meaningful information. Like rocks in a farm field, every year new issues and errors with current practices surface that were previously hidden from view. Some are incidental, others need short term resolution. The goal of this paper is to highlight these and make proposals for easier, less costly, and less frustrating ways to improve imaging goodness through the FADGI guidelines.

Automated Toll Booth using Morphological Edge Detection Algorithm

In order to reduce the traffic jam, save time and to diminish the money loss of 300 crores/year, an automated system is proposed; The intelligent traffic control management systems which explains the installation of automation in toll plazas, which is a step towards improving the monitoring of vehicles. The main purpose of this arrangement is to implement a system, which automatically identifies an approaching vehicle and records the vehicles number and time. If the vehicle belongs to an authorized person, the toll gate opens automatically and a predetermined amount is deducted from the user account, which leads to reduce the Traffic clogging at toll plazas. The vehicle number plate recognition is done only for authorized members. The proposed model consists of image digitization, edge detection, character detection and recognition with the payment transaction. The proposed method uses morphological edge detection , for the system to identify the character recognition and it uses template matching; it is done for license plates of 6 characters. The license plate character recognition system can be used in vehicle check -in and checkout monitoring system in hotels, malls and can be used to track vehicles on normal roads other than toll booths to avoid thefts.

Digitization of Documented Ecg Signals using Image Processing

In order to implement the heart disease prediction algorithms, the scanned ECG images need to be digitized. The ECG image digitization from ECG images deals with converting the ECG images in to digital format which can be processed by heart disease prediction algorithms. To present the Heart disease prediction algorithms, the digital signals can be directly applied. In this paper we have presented an effective ECG digitization technique using Dijikstraw’s shortest path algorithm. The scanned ECG images are oversampled 8 times. Then ECG curve is traced using Dijikstraw’s shortest path algorithm. The shortest path computed represents the scanned ECG signal in digitized form which can be directly used for heart disease prediction. The proposed method gives the accurate digitization by reducing the complications of the digitization process

Business Process Automation: A Workflow Incorporating Optical Character Recognition and Approximate String and Pattern Matching for Solving Practical Industry Problems

Companies are relying more on artificial intelligence and machine learning in order to enhance and automate existing business processes. While the power of OCR (Optical Character Recognition) technologies can be harnessed for the digitization of image data, the digitalized text still needs to be validated and enhanced to ensure that data quality standards are met for the data to be usable. This research paper focuses on finding and creating an automated workflow that can follow image digitization and produce a dictionary consisting of the desired information. The workflow introduced consists of a three-step process that is implemented after the OCR output has been generated. With the introduction of each step, the accuracy of key-value matches of field names and values is increased. The first step takes the raw OCR output and identifies field names using exact string matching and field-values using regular expressions from an externally maintained file. The second step introduces index pairing that matches field-values to field names based on the location of the field name and value on the document. Finally, approximate string matching is introduced to the workflow, which increases accuracy. By implementing these steps, the F-measure for key-value pair matches is measured at 60.18% in the first step, 80.61% once index pairing is introduced, and finally 90.06% after approximate string matching is introduced. The research proved that accurate usable data can be obtained automatically from images with the implementation of a workflow after OCR.