This paper presents a novel block segmentation method for document images ,which can be applied to various document formats. Some documents have complicated column structures, in ,which some figure areas have no surrounding rectangles and others cut QCTOSS text areas. I n OUT approach), in order to segment documents into text and figure areas, the text areas are analyzed first, and the figure areas are then detected by analyzing information on the text areas. The overall process as as follows: First, character strings are merged into text groups by analyzing regularity in text areas. Next, border h e s of colum,ns are detected by linking the edges of the text groups. After th,at, th,e ,urhole page is segmented into small blocks according to the border lines. The blocks are then unified by using the column information., and some unified blocks are detected. Finally, a projection profile method is applied to the unified blocks an order to detect text areas and figure areas. Th,is method was applied to sixty-om pages of Japanese technical papers and magazines, and 93.3 percent of the text areas and 93.2 percent of the figure areas were detected correctly.
Photography is closely tied with people's emotion. Therefore, the concept of emotion driven camera is a natural consequence of future photography. As for EEG emotion detection in research laboratories, there have been many works but it is considered difficult to apply such methodologies in generic environments. For measuring ERP (event related potential), some kinds of cues are typically used for knowing the exact time in which a stimulus given, but it is difficult to know such cues in real world. Therefore, we propose a cue detection mechanism based on the architecture of digital single lens reflex camera. It enables to reproduce an environment similar to research laboratories and is still a natural configuration for ordinary digital cameras.
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.