TY  - BOOK
AU  - Cabadsan, Mark Roger L., author
AU  - Nocon, Chrysolite A., author.
AU  - Dharma, John Michael A., adviser.
AU  - Nabablit, Karlo Jose E., critic.
TI  - Raspberry Pi-Based Multipurpose Optical Mark Recognition (OMR) Scanner
AV  - UM QA 76.9.S63 C33 2018
PY  - 2018///
CY  - Rosario, Cavite
PB  - Cavite State University-CCAT Campus
KW  - Optical Mark Recognition (OMR)
KW  - Raspberry Pi-based
KW  - Performing recognition
KW  - Acquisition
KW  - Storage and processing
KW  - Cost analysis
N1  - Design Project (BSCpE)--Cavite State University-CCAT Campus, 2018; Includes bibliographical references and appendices
N2  - CABADSAN, MARK ROGER L., NOCON, CHRYSOLITE A. Raspberry Pi-Based Multipurpose Optical Mark Recognition (OMR) Scanner. Design Project. Department of Engineering. Cavite State University-Cavite College of Arts and Trades Campus, Rosario, Cavite. June 2018. Adviser: Engr. John Michael A. Dharma. Mr. Karlo Jose K. Nabablit.

The study was conducted from August 2017 to June 2018 in order to design and develop a Raspberry Pi-based Multipurpose Optical Mark Recognition (OMR) Scanner for Cavite State University Cavite College of Arts and Trades (CCAT) that can automate the assessment of the Student Evaluation for Teachers (SET) and canvassing of Central Student Government (CSG) election votes. Specifically, the study aimed to: 1) design and develop a standalone Raspberry Pi-based OMR scanning device that is able of performing recognition, acquisition, storage and processing of all the necessary data or information and automatically assess and produce appropriate results; 2) evaluate the prototype technical performance in terms of accuracy, process time and over-all functionality; and 3) conduct a cost analysis of the research. 

Parameters measured are — 1) number of successful recognition per set, 2) number of accurate recognition per set and 3) process time per each cycle (seconds). These data were gathered to determine the probability of successful recognition, probability of producing an accurate result and the average processing time per cycle. 

The data were analyzed and the results showed that the Raspberry Pi-based Multipurpose Optical Mark Recognition (OMR) Scanner were able to automate the canvassing of CSG election votes and SET effectively and efficiently
ER  -