File Download
Supplementary
-
Citations:
- Appears in Collections:
postgraduate thesis: Artificial training samples for the improvement of pattern recognitionsystems
Title | Artificial training samples for the improvement of pattern recognitionsystems |
---|---|
Authors | |
Advisors | Advisor(s):Leung, CH |
Issue Date | 2012 |
Publisher | The University of Hong Kong (Pokfulam, Hong Kong) |
Citation | Ni, Z. [倪志博]. (2012). Artificial training samples for the improvement of pattern recognition systems. (Thesis). University of Hong Kong, Pokfulam, Hong Kong SAR. Retrieved from http://dx.doi.org/10.5353/th_b4784964 |
Abstract | Pattern recognition is the assignment of some sort of label to a given input value
or instance, according to some specific learning algorithm. The recognition
performance is directly linked with the quality and size of the training data.
However, in many real pattern recognition implementations, it is difficult or not so
convenient to collect as many samples as possible for training up the classifier,
such as face recognition or Chinese character recognition.
In view of the shortage of training samples, the main object of our research is to
investigate the generation and use of artificial samples for improving the
recognition performance. Besides enhancing the learning, artificial samples are
also used in a novel way such that a conventional Chinese character recognizer
can read half or combined Chinese character segments. It greatly simplifies the
segmentation procedure as well as reduces the error introduced by segmentation.
Two novel generation models have been developed to evaluate the effectiveness
of supplementing artificial samples in the training. One model generates artificial
faces with various facial expressions or lighting conditions by morphing and
warping two given sample faces. We tested our face generation model in three
popular 2D face databases, which contain both gray scale and color images.
Experiments show the generated faces look quite natural and they improve the
recognition rates by a large margin.
The other model uses stroke and radical information to build new Chinese
characters. Artificial Chinese characters are produced by Bezier curves passing
through some specified points. This model is more flexible in generating artificial
handwritten characters than merely distorting the genuine real samples, with both
stroke level and radical level variations. Another feature of this character
generation model is that it does not require any real handwritten character sample
at hand. In other words, we can train the conventional character classifier and
perform character recognition tasks without collecting handwritten samples.
Experiment results have validated its possibility and the recognition rate is still
acceptable.
Besides tackling the small sample size problem in face recognition and isolated
character recognition, we improve the performance of bank check legal amount
recognizer by proposing character segments recognition and applying Hidden
Markov Model (HMM).
It is hoped that this thesis can provide some insights for future researches in
artificial sample generation, face morphing, Chinese character segmentation and
text recognition or some other related issues. |
Degree | Doctor of Philosophy |
Subject | Pattern recognition systems. |
Dept/Program | Electrical and Electronic Engineering |
Persistent Identifier | http://hdl.handle.net/10722/174522 |
HKU Library Item ID | b4784964 |
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Leung, CH | - |
dc.contributor.author | Ni, Zhibo. | - |
dc.contributor.author | 倪志博. | - |
dc.date.issued | 2012 | - |
dc.identifier.citation | Ni, Z. [倪志博]. (2012). Artificial training samples for the improvement of pattern recognition systems. (Thesis). University of Hong Kong, Pokfulam, Hong Kong SAR. Retrieved from http://dx.doi.org/10.5353/th_b4784964 | - |
dc.identifier.uri | http://hdl.handle.net/10722/174522 | - |
dc.description.abstract | Pattern recognition is the assignment of some sort of label to a given input value or instance, according to some specific learning algorithm. The recognition performance is directly linked with the quality and size of the training data. However, in many real pattern recognition implementations, it is difficult or not so convenient to collect as many samples as possible for training up the classifier, such as face recognition or Chinese character recognition. In view of the shortage of training samples, the main object of our research is to investigate the generation and use of artificial samples for improving the recognition performance. Besides enhancing the learning, artificial samples are also used in a novel way such that a conventional Chinese character recognizer can read half or combined Chinese character segments. It greatly simplifies the segmentation procedure as well as reduces the error introduced by segmentation. Two novel generation models have been developed to evaluate the effectiveness of supplementing artificial samples in the training. One model generates artificial faces with various facial expressions or lighting conditions by morphing and warping two given sample faces. We tested our face generation model in three popular 2D face databases, which contain both gray scale and color images. Experiments show the generated faces look quite natural and they improve the recognition rates by a large margin. The other model uses stroke and radical information to build new Chinese characters. Artificial Chinese characters are produced by Bezier curves passing through some specified points. This model is more flexible in generating artificial handwritten characters than merely distorting the genuine real samples, with both stroke level and radical level variations. Another feature of this character generation model is that it does not require any real handwritten character sample at hand. In other words, we can train the conventional character classifier and perform character recognition tasks without collecting handwritten samples. Experiment results have validated its possibility and the recognition rate is still acceptable. Besides tackling the small sample size problem in face recognition and isolated character recognition, we improve the performance of bank check legal amount recognizer by proposing character segments recognition and applying Hidden Markov Model (HMM). It is hoped that this thesis can provide some insights for future researches in artificial sample generation, face morphing, Chinese character segmentation and text recognition or some other related issues. | - |
dc.language | eng | - |
dc.publisher | The University of Hong Kong (Pokfulam, Hong Kong) | - |
dc.relation.ispartof | HKU Theses Online (HKUTO) | - |
dc.rights | The author retains all proprietary rights, (such as patent rights) and the right to use in future works. | - |
dc.rights | This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. | - |
dc.source.uri | http://hub.hku.hk/bib/B47849642 | - |
dc.subject.lcsh | Pattern recognition systems. | - |
dc.title | Artificial training samples for the improvement of pattern recognitionsystems | - |
dc.type | PG_Thesis | - |
dc.identifier.hkul | b4784964 | - |
dc.description.thesisname | Doctor of Philosophy | - |
dc.description.thesislevel | Doctoral | - |
dc.description.thesisdiscipline | Electrical and Electronic Engineering | - |
dc.description.nature | published_or_final_version | - |
dc.identifier.doi | 10.5353/th_b4784964 | - |
dc.date.hkucongregation | 2012 | - |
dc.identifier.mmsid | 991033486089703414 | - |