A numerical coding method based on Pinyin and Strokes for inputting Chinese characters is presented, which improves the numeric coding method based on Strokes presented before. This coding method encodes Chinese chara...A numerical coding method based on Pinyin and Strokes for inputting Chinese characters is presented, which improves the numeric coding method based on Strokes presented before. This coding method encodes Chinese characters with Basic Unit-Stroke, the first Pinyin and sometimes with a few high-frequency components. This method makes the response speed higher and makes the coincident-code rate lower. So it is a high efficiency input method which is easy to learn, remember and to apply. Firstly the encod- ing rules for words of this input method are discussed in the beginning of the article. Secondly, pressed key distribution and coinci- dent-code rate are deeply discussed statistically in it. Thirdly, it deeply analyzes and proves the advantage of low coincident code rate of this encoding method. What's more, the article will introduce the encoding rules for phrases and the Error-Resilient Encoding. It will also briefly introduce the implements of this input method on several current platforms. Finally it summarizes and expounds some merits of this encoding method, such as innovative human-computer interface, etc.展开更多
The classification for handwritten Chinese character recognition can be viewed as a transformation in discrete vector space. In this paper, from the point of discrete vector space transformation, a new 4-corner codes ...The classification for handwritten Chinese character recognition can be viewed as a transformation in discrete vector space. In this paper, from the point of discrete vector space transformation, a new 4-corner codes classifier based on decision tree inductive learning algorithm ID3 for handwritten Chinese characters is presented. With a feature extraction controller, the classifier can reduce the number of extracted features and accelerate classification speed. Experimental results show that the 4-corner codes classifier performs well on both recognition accuracy and speed.展开更多
Korean characters consist of 2 dimensional distributed consonantal and vowel graphemes. The purpose of reducing the 2 dimensional characteristics of Korean characters to linear arrangements at early stage of character...Korean characters consist of 2 dimensional distributed consonantal and vowel graphemes. The purpose of reducing the 2 dimensional characteristics of Korean characters to linear arrangements at early stage of character recognition is to decrease the complexity of following recognition task. By defining the identification codes for the vowel graphemes of Korean characters, the rules for combination of vowel graphemes are established, and a recognition algorithm based on the rules for combination of vowel graphemes, is therefore proposed for vertical vowel graphemes. The algorithm has been proved feasilbe through demonstrating simulations.展开更多
摘要A numerical coding method based on Pinyin and Strokes for inputting Chinese characters is presented, which improves the numeric coding method based on Strokes presented before. This coding method encodes Chinese characters with Basic Unit-Stroke, the first Pinyin and sometimes with a few high-frequency components. This method makes the response speed higher and makes the coincident-code rate lower. So it is a high efficiency input method which is easy to learn, remember and to apply. Firstly the encod- ing rules for words of this input method are discussed in the beginning of the article. Secondly, pressed key distribution and coinci- dent-code rate are deeply discussed statistically in it. Thirdly, it deeply analyzes and proves the advantage of low coincident code rate of this encoding method. What's more, the article will introduce the encoding rules for phrases and the Error-Resilient Encoding. It will also briefly introduce the implements of this input method on several current platforms. Finally it summarizes and expounds some merits of this encoding method, such as innovative human-computer interface, etc.
摘要The classification for handwritten Chinese character recognition can be viewed as a transformation in discrete vector space. In this paper, from the point of discrete vector space transformation, a new 4-corner codes classifier based on decision tree inductive learning algorithm ID3 for handwritten Chinese characters is presented. With a feature extraction controller, the classifier can reduce the number of extracted features and accelerate classification speed. Experimental results show that the 4-corner codes classifier performs well on both recognition accuracy and speed.
摘要Korean characters consist of 2 dimensional distributed consonantal and vowel graphemes. The purpose of reducing the 2 dimensional characteristics of Korean characters to linear arrangements at early stage of character recognition is to decrease the complexity of following recognition task. By defining the identification codes for the vowel graphemes of Korean characters, the rules for combination of vowel graphemes are established, and a recognition algorithm based on the rules for combination of vowel graphemes, is therefore proposed for vertical vowel graphemes. The algorithm has been proved feasilbe through demonstrating simulations.