|
|
Automatic Delivery Note Transcription
Necpál, Dávid ; Kišš, Martin (referee) ; Hradiš, Michal (advisor)
This bachelor thesis aims to create a system for automatic transcription of delivery notes - documents with a fixed structure. The solution is divided into two parts. The first part is table lines detection and subsequent detection and extraction of cells, that contain required data. The second part is handwritten numeric characters recognition in the images of the cutted cells. The resulting system can detect cells with the required data with 100 % accuracy with well-scanned delivery notes, while the success rate of numerical character recognition is more than 95 % for individual characters and more than 92 % for entire character sequences. The benefit of this work is a system for automatic transcription of delivery notes, which provides faster and easier otherwise lengthy rewriting of the contents of delivery notes to the information system in the retail. By using this system, the employee saves more than 50 % of the time on each delivery note.
|
|
|
Predictive Control of DHW and Household Heating Using Machine Learning Methods
Necpál, Dávid ; Zemčík, Pavel (referee) ; Materna, Zdeněk (advisor)
The thesis is devoted to the development of a system for the control of domestic hot water (DHW) and heating. The system uses machine learning methods to predict future data - learning and predicting repetitive routines of people in the home, predicting hot water consumption and temperature trends in the home. The work is divided into two parts, where the first part is the control of domestic hot water heating, and the second part is the control of home heating. Both parts of the system use established hardware devices that implement the data collection and the actual control of the given activities. The devices collect water temperatures from the electric boiler, air temperatures from the rooms of the household and information about the presence of people in the household. The measured data is used to create a model for data prediction, which is used for the final decision on whether DHW heating or home heating should be implemented. The first subsystem for DHW heating achieves energy savings of 20 to 24 %, the second subsystem for domestic heating 18 to 30 %. The benefit of the developed system is the possibility of predictive automatic control of domestic hot water heating and heating, which leads to a reduction of energy consumption required for the above-mentioned activities, as well as a possible increase in comfort in the home.
|
|
|
Automatic Delivery Note Transcription
Necpál, Dávid ; Kišš, Martin (referee) ; Hradiš, Michal (advisor)
This bachelor thesis aims to create a system for automatic transcription of delivery notes - documents with a fixed structure. The solution is divided into two parts. The first part is table lines detection and subsequent detection and extraction of cells, that contain required data. The second part is handwritten numeric characters recognition in the images of the cutted cells. The resulting system can detect cells with the required data with 100 % accuracy with well-scanned delivery notes, while the success rate of numerical character recognition is more than 95 % for individual characters and more than 92 % for entire character sequences. The benefit of this work is a system for automatic transcription of delivery notes, which provides faster and easier otherwise lengthy rewriting of the contents of delivery notes to the information system in the retail. By using this system, the employee saves more than 50 % of the time on each delivery note.
|
guest ::
