Disposable diaper has been used in order to handle urine and feces conveniently. At present the amount of disposable diaper waste increases gradually. Incineration and landfill have been the only ways to dispose of disposable diapers. However, if they are disposed by landfill, decomposition will take more than one hundred years. In addition, another way of dispose incineration has caused air pollution. Therefore, it is necessary to study recycling process for disposable diaper since plastic and wood fibers of diaper are useful materials to recycle. In this study, pulping condition of disposable diaper waste was studied in order to effectively separate the components. Recovery rates of plastic and fibers were analyzed under different pulping conditions. It was found that optimum pulping consistency was 5%, time was 60 minutes, temperature was 50°C, and cut size is 21 cm×21 cm. The recovery rate of plastic and fibers can be achieved above 70% under the optimum pulping condition.
This paper describes some of research results related to the development of a character recognizer appropriate for fast handwritten Korean address reading. Our goal is to design a handwritten Korean character recognizer retaining the following three characteristics: reliable recognition scores indicating probability, high speed, and naturally acceptable cumulative recognition rates. We have adopted two statistical classifiers to satisfy the first characteristic and proposed methods coupling the two classifiers to meet the s~cond and third ones. The superiority of the proposed combination methods has been proven through experiments done with the PE92 database.difficulty, the performance of handwritten Korean character recognition is still poor to be used in practical applications in spite of many steady studies [5].Conventional methods for recognizing Korean characters can be roughly divided into two categories: the grapheme segmentation free method and the grapheme segmentation based method. The latter separates character images into grapheme units and produces character recognition results by combing recognition results of graphemes. However, grapheme segmentation is another challenging problem. The former does not keep grapheme segmentation in mind. The method builds one or more models per character and assigns a given character image to the character class with the maximum (or minimum depending on an adopted classifier) recognition score. It becomes a reasonable approach only when a limited set of target classes can be provided [6,8], due to computational burden and absence of necessary data. The character recognizer developed by us is based on the grapheme segmentation free method. A detailed description of our recognizer is given in Section 2.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.