Showing papers by "Masaki Nakagawa published in 2000"
TL;DR: The results show that the proposed method selects about one-fourth as many candidates with accuracy preserved compared to the conventional method that selects a fixed number of candidates.
Abstract: This paper proposes a precise candidate selection method for large character set recognition by confidence evaluation of distance-based classifiers. The proposed method is applicable to a wide variety of distance metrics and experiments on Euclidean distance and city block distance have achieved promising results. By confidence evaluation, the distribution of distances is analyzed to derive the probabilities of classes in two steps: output probability evaluation and input probability inference. Using the input probabilities as confidences, several selection rules have been tested and the rule that selects the classes with high confidence ratio to the first rank class produced best results. The experiments were implemented on the ETL9B database and the results show that the proposed method selects about one-fourth as many candidates with accuracy preserved compared to the conventional method that selects a fixed number of candidates.
59 citations
01 Sep 2000
TL;DR: Experimental results show that the incorporation of the character size likelihood increases the character recognition rate for Japanese text.
Abstract: An online writing-box free method for recognizing handwritten Japanese text is proposed. This method is achieved by the following procedure. First, the average character size of input handwritten text is estimated. Second, candidates for character segmentation are detected using geometric features between two adjacent strokes. Finally, a search is performed by dynamic programming for the string that maximizes evaluation score (acceptability as Japanese text). The evaluation score reflects the likelihood of character segmentation, recognition, context and the size of each character. The size is a newly introduced factor since alphabets, numerals, symbols, Japanese phonetic characters, simple Chinese characters and compound Chinese characters are all written in different sizes even in a single line of text. Experimental results show that the incorporation of the character size likelihood increases the character recognition rate for Japanese text.
36 citations
04 Dec 2000
TL;DR: A whiteboard-based environment that extends the functionality of the blackboard in a traditional classroom without losing any of its natural advantages, namely, ease of expression for the teacher, focusing of students' attention and visual feedback of students’ facial expressions is described.
Abstract: We describe a whiteboard-based environment that extends the functionality of the blackboard in a traditional classroom without losing any of its natural advantages, namely, ease of expression for the teacher, focusing of students' attention and visual feedback of students' facial expressions. The computer-based whiteboard environment offers additional features such as direct pointing and manipulation of contents by an electronic marker, and processing of contents by computer. We articulate design principles for developing educational software for this environment. Two examples of such software developed in our laboratory, are presented. We also describe experimental use of the system in actual classrooms at two elementary schools. In the experiments, the teachers and the students both responded positively, to this new environment. We also verified that many of the design goals were met in the implementation.
11 citations
21 Dec 2000
TL;DR: A new technology that detects handwritten marks without restricting the way to write correction marks or forcing the users to use a pen of a specific color and a specific scanner is presented.
Abstract: This paper describes pattern processing and recognition for a user interface with real papers rather than display, keyboard and mouse for document editing. We call this UI (User Interface) as 'Paper based User Interface.' In order to realize this UI, we need a technology to detect and recognize correction marks written on printouts of documents. This paper presents a new technology that detects handwritten marks without restricting the way to write correction marks or forcing the users to use a pen of a specific color and a specific scanner. At first, documents are printed out with dotted characters, and they can be easily dropped out to detect correction marks and also they can be easily emphasized to detect where each correction mark is applied. We made a prototype on a PC and verified that the method can extract almost all correction marks correctly.
2 citations