Javascript must be enabled for the correct page display

Autonomous feedback-based preprocessing using classification likelihoods

Baptist, J. (2014) Autonomous feedback-based preprocessing using classification likelihoods. Bachelor's Thesis, Artificial Intelligence.

[img]
Preview
Text
AI_BA_2014_JOOSTBAPTIST.pdf - Published Version

Download (694kB) | Preview
[img] Text
toestemming.pdf - Other
Restricted to Backend only

Download (22kB)

Abstract

In pattern recognition and optical character recognition (OCR) specifically, input images are presented to the classification system, they are preprocessed, features are extracted and then the image is classified. This is a sequential process in which decisions made during early preprocessing affect the outcome of the classification and potentially decrease performance. Hand-tuning the preprocessing parameters is often undesirable, as this can be a complex task with many parameters to optimize. Moreover, it is often desirable to minimize the amount of human intelligence that ends up in an autonomous system, if it can be expected that new variants of the data would require new human knowledge-based labor. A different approach to preprocessing in OCR is proposed, in which preprocessing is performed autonomously and depends on computed likelihood of classification outcomes. This paper shows that by using this approach, color, scale and rotation invariance can be achieved, as well as high accuracy and precision. The performance is solid and reaches a plateau even when noise in the data is not fully accounted for.

Item Type: Thesis (Bachelor's Thesis)
Degree programme: Artificial Intelligence
Thesis type: Bachelor's Thesis
Language: English
Date Deposited: 15 Feb 2018 07:58
Last Modified: 15 Feb 2018 07:58
URI: https://fse.studenttheses.ub.rug.nl/id/eprint/12113

Actions (login required)

View Item View Item