• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.3
• /
• pp.271-274
• /
• 2006

This paper deals with a similarity decision method between the shape of hand-postures and their structures to improve performance of the vision-based hand-posture recognition system. Hand-posture recognition by vision sensors has difficulties since the human hand is an object with high degrees of freedom, and hence grabbed images present complex self-occlusion effects and, even for one hand-posture, various appearances according to viewing directions. Therefore many approaches limit the relative angle between cameras and hands or use multiple cameras. The former approach, however, restricts user's operation area. The latter requires additional considerations on the way of merging the results from each camera image to get the final recognition result. To recognize hand-postures, we use both of appearance and structural features and decide the similarity between the two types of features by learning.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.3 s.309
• /
• pp.39-49
• /
• 2006

This paper proposes a hand-posture recognition method using reinforcement learning for the performance improvement of vision-based hand-posture recognition. The difficulties in vision-based hand-posture recognition lie in viewing direction dependency and self-occlusion problem due to the high degree-of-freedom of human hand. General approaches to deal with these problems include multiple camera approach and methods of limiting the relative angle between cameras and the user's hand. In the case of using multiple cameras, however, fusion techniques to induce the final decision should be considered. Limiting the angle of user's hand restricts the user's freedom. The proposed method combines angular features and appearance features to describe hand-postures by a two-layered data structure and reinforcement learning. The validity of the proposed method is evaluated by appling it to the hand-posture recognition system using three cameras.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.34 no.6
• /
• pp.955-968
• /
• 2010

Three-dimensional body data has been used in many industry fields including the apparel industry. This research used data from a study of the changes in lower body girth measurements from a 3D scan study of 25 female subjects aged 18 to 24 in four postures; a standing posture, a $120^{\circ}$ knee bend posture, a one pace stepping posture, and a sitting posture with a $90^{\circ}$ knee bend. We used the information on the difference between standing and seated measurements to adjust ease values for pants patterns an evaluation of the appearance, and the comfort of the pants. Waist girth in the sitting posture increased 8% compared to a standing posture and the hip girth measurement increased 7%. A basic pants pattern (pants A) with 2.4cm ease at the waist and 2.6cm ease at the hip was developed and a pants pattern (pants B) was developed using the rates of lower body girth change with a 5.7cm ease (8% change) at the waist and 7cm ease (7% change) at the hip. The appearance assessment items of pants A in a standing posture were higher than pants B. On the other hand, most appearance assessment items of pants B in a sitting posture were higher than pants A, especially the ease of pants back waistline and the appearance of the whole back. Comfort assessment items of pants B in both standing and sitting postures were higher than the comfort assessment items for pants A, especially the location of pants waistline, the ease of pants at the waistline, and the ease at the abdomen. In order to find the best level of ease for better appearance and comfort in both standing and sitting postures, 20 pants were constructed with ease values at the waist and hip in increments of 1.1cm in the range between the ease values of pants A and pants B. A fit test was conducted to compare the average appearance and comfort ratings that identified the pants with the best ease values at the waist and hip. The highest total mean was achieved in the pants with a waist ease of 4.6cm and hip ease of 4.8cm.