An ultra-small (0.4 0.4 mm2) radio frequency identification (RFID) chip named µ -chip has been developed for use in a wide range of individual recognition applications. The chip is designed to be 0.06 mm thick so that it can be applied to paper and to thin paper-like media, which have been used widely in retailing to create certificates that have monetary value, as well as to token-type devices. The µ-chip has been designed and fabricated using 0.18 µm standard CMOS technology with 3-layer aluminum metallization. The chip has a 128-bit memory. The memory data is easily read by applying a 2.45 GHz microwave radio frequency identification circuit technique. The minimum operating voltage of the chip's digital circuits is 0.5 V. This chip has attached to a thin-film external antenna. The chip terminals are connected to the antenna by an anisotropic conductive film (ACF). This type of structure results in a 0.15 mm thin transponder. The maximum communication distance between the µ -chip and a reader is 300 mm at a reader power of 300 mW.

This paper discusses sign word segmentation methods and extraction of motion features for sign language recognition. Because Japanese sign language grammar has not yet been systematized and because sign language does not have prepositions, it is more difficult to use grammar and meaning information in sign language recognition than in speech recognition. Segmentation significantly improves recognition efficiency, so we propose a method of dividing sign language based on rests and on the envelope and minimum of motion speed. The sign unit corresponding to a sign word is detected based on the divided position using such features as the change of hand shape. Experiments confirmed the validity of word segmentation of sign language based on the temporal structure of motion.