English Abstract
|
Abstract
This thesis proposes a neural network approach to recognize the invariance of characters including Chinese and English letters. The character invariance recognition takes position, scale and rotation into account. To find the features invariant to a character, the statistical distance estimates between the pixels and the gravity of the recognizing character have been developed. The preprocessor takes and classifieds those invariant features that are recognized by the proposed neural system SimNet. After the experimental recognition, the accurate rates 100%, 99%, and 97% for position, scale and rotation, respectively, were found. The rate of the recognized accuracy for the variety of the invariance averages 92%. The high accurate recognition shows that SimNet is a potential character recognizer.
|
Reference
|
-
Chang, J.Y. and C. L. Lee, “Translation, Rotation, and Scaling Invariant Pattern Recognition by Fuzzy Neural Networks,” The 2nd Natl. Conf. on Fuzzy Theory & Appl.(Fuzzy’94), Taiwan, ROC.
連結:
-
Yuceer, C. and K. Oflazer, “A Rotation, Scaling, and Translation Invariant Pattern Classification System,” Pattern Recognition, vol.26, No.5, pp.687-710, 1993.
連結:
-
仲崇實,「影像處理及類神經乏晰於車輛牌照自動辨識之應用研究」,元智大學資訊研究所,碩士論文,1998。
連結:
-
許加文,「網際網路搜尋過澸系統」,元智大學資訊研究所,碩士論文,1998。
連結:
-
黃雅軒,「光學中文文字辨識技術及應用」,光學工程,第60期,23-28頁,1997。
連結:
-
Enke, D., H. C. Lee, A. M. Ozbayoglu, A. Thammano, and C. H. Dagli, “An Application to Speaker Identification Using SimNet,” Intelligent Engineering Systems Through Artificial Neural Networks, vol.5, ASME Press (ANNIE ’95) New York, 1995.
-
Lee, H. C., C. H. Dagli, F. Ercal, and A.M. Ozbayoglu, “SimNet: A Parallel Neuro-Fuzzy Paradigm for Data Clustering,” OAI Neural Networks Symposium and Workshop (OAINN ’95), Athens, Ohio, USA, 1995.
-
王駿發、楊宗憲,「可處理任意旋轉角度之手寫文字辨認」,影像與識別,vol.4,no.8,67-77頁,1998。
-
史靜芬,「OCR與文件重現」,第3波,167期,138-142頁,1996。
-
趙永正,「以特徵擷取作有限度旋轉文字之辨識」,台灣工業技術學院,碩士論文,1994。
-
顏林文,「利用筆劃傅利葉轉換之特徵做中文印刷字體辨識」,中央大學,碩士論文,1997。
|