Journal of rehabilitation research and development
-
This study describes a computer vision approach for sensing the environment with the intent of helping people with a visual impairment. The principal goal in applying computer vision is to exploit, in an optimal fashion, the information acquired by the camera(s) to yield useful descriptions of the viewed environment. ⋯ In this research direction, the following problems are identified and addressed: 1) the vision system design; 2) establishment of the mapping principles between the two-dimensional (2-D) camera images and the three-dimensional (3-D) real world; 3) development of appropriate imaging techniques for the interpretation of the 2-D images; and, 4) establishment of a communication link between the vision system and the user. The soundness of this research direction is assessed by means of a theoretical framework and experimental evaluations.
-
The development and use of a two-step word segmentation method for automatic recognition of the speech produced by deaf persons are described in this paper. This method incorporates the segmental and temporal characteristics of deaf speech, particularly the intra- and inter-word pauses, to achieve accurate recognition. ⋯ This method was applied to recognition of isolated words and connected-speech utterances produced by two deaf speakers. Recognition rates of 93.01 percent and 81.81 percent were obtained in recognizing isolated words and connected speech, respectively.
-
Future progress in neuromuscular prostheses will depend on developing techniques for stimulating paralyzed muscle, especially utilizing neuromuscular stimulation. We have found nonlinear force versus stimulus amplitude characteristic (recruitment) curves in the gastrocnemius-soleus-plantaris muscle group of the cat in response to stimulation of the tibial nerve near the muscle entry point. Such response characteristics are undesirable in neuromuscular control systems. ⋯ Correlation coefficients between force and stimulated myoelectric response were very high (up to R2 = 0.99) when using a composite curve produced by averaging myoelectric response curves recorded from each of the active compartments. By dividing the tibial nerve into its component bundles or fascicles and stimulating each in turn, it was possible to show that individual bundles innervate non-overlapping groups of muscle compartments, and that recruitment of the nerve bundles over different threshold ranges could account for the nonlinear force/stimulus response curves initially observed. The presence of separate innervation of muscles or compartments by fascicles should be an important factor in designing functional neuromuscular stimulation (FNS) systems.