20.500.12556/DKUM-74576 Analiza uspešnosti optične prepoznave elementov BPMN magistrsko delo Analysis of the effectiveness of optical recognition of BPMN elements Magistrsko delo predstavlja postopek izdelave modela za prepoznavo ročno risanih BPMN elementov ter pridobitev rezultatov (%) uspešnosti njihove prepoznave. Za pomoč pri razvoju modela za prepoznavo elementov BPMN smo uporabili ogrodje TensorFlow. Opravili smo pregled literature, predstavili obstoječe rešitve, razvite na podlagi optične prepoznave in strojnega učenja. Razložili smo osnovne gradnike BPMN (standard BPMN 2.0.) in nekatere od teh elementov vključili v proces analize uspešnosti razpoznave s pomočjo mobilne aplikacije, izdelane v okviru naloge in razvite v okolju Angular.js, v katero smo vključili izdelani TensorFlow model, ki je zmožen prepoznavati BPMN elemente. V analizi smo zapisali ugotovitve, ki smo jih pridobili v raziskovalnemu delu na podlagi vprašalnikov. Ugotovitve, pridobljene v analizi, so pokazale da je mobilna aplikacija zmožna prepoznavati določene elemente BPMN, vendar ne vseh. Prav tako smo podali smernice za nadaljnje delo. The master thesis represents the process of creating a model capable of recognizing handwritten BPMN elements and receiving the results with percent precision (%) of recognition success. To create a model for identifying BPMN elements, we used the TensorFlow framework. We made a literature review, explored existing solutions for optical recognition and machine learning. We also explained the basic BPMN (BPMN 2.0. specification) elements and used some of those elements in the process of analyzing the recognition performance with the use of a mobile application, developed with Angular.js framework. In this application, we incorporated the TensorFlow model capable of detecting BPMN elements. In the analysis, we recorded the findings obtained in the research work based on a survey. The findings obtained in the analysis showed that the mobile application is capable of identifying certain BPMN elements, but not all. We also gave guidelines for further work. BPMN OCR strojno učenje TensorFlow BPMN OCR machine learning TensorFlow true true false [S. Jagečić] Slovenski jezik Angleški jezik Magistrsko delo/naloga 2019-08-30 20:04:28 2019-11-13 12:33:30 2022-08-09 09:15:59 2019-12-10 08:07:29 2019 0 Maribor 0 Maribor XI, 96 str. 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.424.3(043.2) 22839574 URN:SI:UM:DK:YZIIQ6KK MAG_Jagecic_Slavica_2019.pdf MAG_Jagecic_Slavica_2019.pdf 1 AD972EFEFD0C65B420DE91B216494668 14f764e40b57cb8768035950a520bb45644299e992abf627379b9a7155ac179b de83039a-7c10-11eb-bb7a-00155d0001ca 20.500.12556/dkum/e3971c0f-d7b6-47de-b7da-b084a7edc83a https://dk.um.si/Dokument.php?lang=slv&id=136713 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0