21st EANN 2020, 5 -7 June 2020, Greece

Deep Learning-Based Computer Vision Application with Multiple Built-In Data Science-Oriented Capabilities

Sorin Liviu Jurj, Flavius Opritoiu, Mircea Vladutiu


  This paper presents a Data Science-oriented application for image classifica-tion tasks that is able to automatically: a) gather images needed for training Deep Learning (DL) models with a built-in search engine crawler; b) remove duplicate images; c) sort images using built-in pre-trained DL models or us-er’s own trained DL model; d) apply data augmentation; e) train a DL classi-fication model; f) evaluate the performance of a DL model and system by using an accuracy calculator as well as the Accuracy Per Consumption (APC), Accuracy Per Energy Cost (APEC), Time to closest APC (TTCAPC) and Time to closest APEC (TTCAPEC) metrics calculators. Experimental re-sults show that the proposed Computer Vision application has several unique features and advantages, proving to be efficient regarding execution time and much easier to use when compared to similar applications.  

*** Title, author list and abstract as seen in the Camera-Ready version of the paper that was provided to Conference Committee. Small changes that may have occurred during processing by Springer may not appear in this window.