HEGM: A hierarchical elastic graph matching for hand gesture recognition

A hierarchical scheme for elastic graph matching applied to hand gesture recognition is proposed. The proposed algorithm exploits the relative discriminatory capabilities of visual features scattered on the images, assigning the corresponding weights to each feature. A boosting algorithm is used to determine the structure of the hierarchy of a given graph. The graph is expressed by annotating the nodes of interest over the target object to form a bunch graph. Three annotation techniques, manual, semi-automatic, and automatic annotation are used to determine the position of the nodes. The scheme and the annotation approaches are applied to explore the hand gesture recognition performance. A number of filter banks are applied to hand gestures images to investigate the effect of using different feature representation approaches. Experimental results show that the hierarchical elastic graph matching (HEGM) approach classified the hand posture with a gesture recognition accuracy of 99.85% when visual features were extracted by utilizing the Histogram of Oriented Gradient (HOG) representation. The results also provide the performance measures from the aspect of recognition accuracy to matching benefits, node positions correlation and consistency on three annotation approaches, showing that the semi-automatic annotation method is more efficient and accurate than the other two methods.     

手轮脉冲驱动均匀化控制

本文分析了数控系统手轮驱动存在的问题，提出了全新的手脉冲驱动均匀化控制法，这种方法基于运动控制芯片MCX314的“固定脉冲驱动过程中脉冲数可改变”这一性能来实现，在手轮大倍率快速放心转时驱动脉冲序列保持均匀高速输出，脉冲不会丢失，实现加减速控制和驱动速度控制，克服步进电机失步问题，解决了目前手轮驱动存在的一系列关键问题。     

Perception of Hand Force in Power Grip for Females

Borg's rating of perceived exertion (RPE) and category ratio (CR‐10) scales are commonly used to quantify perceived muscular exertion for body segments. Twenty females participated in an experiment to study the power grip force at four perceived exertion levels using either dominant or nondominant hand under two posture conditions. It was found that the subjects tended to apply a higher power grip force (100% of perceived maximum voluntary contraction) than the levels they were requested to apply. The power grip forces between dominant and nondominant hands at low hand exertion levels were negligible. The grip forces between the two hands were significantly different when the exertion level was nearly maximal. Linear regression models were established for the subjects to link the relationship between the perceived hand exertion and measured grip force, hand used, and hand/arm posture. All the models were statistically significant (p < 0.0001) with R² values 0.97 or higher. These models provided better estimates in perceived hand exertion for dominant hand than for nondominant hand. A follow‐up experiment was conducted to measure the subjective rating of both the CR‐10 and RPE when a 98 N grip force was applied. It was found that the subjects reported higher exertion levels when they were using the CR‐10 scale than when they were using the RPE scale. © 2011 Wiley Periodicals, Inc.     

Effects of gender differences on the subjective perceived intensity of steering wheel rotational vibration based on a multivariate regression model

The aims of this study were to determine equal sensation curves for hand–arm steering wheel rotational vibration and to investigate the effect of gender on the subjective perceived intensity of steering wheel hand–arm vibration. Psychophysical response tests of 40 participants (20 males and 20 females) were performed using a steering wheel rotational vibration simulator using the category-ratio Borg CR10 scale procedure for direct estimation of perceived intensity. The test stimuli were sinusoidal vibrations at 22 third octave band centre frequencies in the range from 3 to 400 Hz, with acceleration amplitudes in the range from 0.04 to 27 m/s² r.m.s. Multivariate regression procedures were applied to the experimentally acquired data in order to establish a regression model expressing the Borg CR10 perceived intensity values as a function of the two independent parameters of the frequency and amplitude of vibration. The equal sensation curves suggested a non-linear dependency of the subjective perceived intensity on both frequency and amplitude. Females were found to provide higher Borg CR10 perceived intensity values than males (p < 0.05), particularly at the higher intensity levels above approximately 1.0 m/s² r.m.s and at the higher frequencies above approximately 20 Hz.

Relevance to industry

For the manufacturers of steering systems and of other automobile components this study provides vibration perception curves and identifies the possible importance of gender towards the perception of vibration which arrives at the steering wheel.     

Application of the QFD as a design approach to ensure comfort in using hand tools: Can the design team complete the House of Quality appropriately?

Quality Function Deployment is proposed as an effective design method to integrate ergonomics needs and comfort into hand tool design because it explicitly addresses the translation of customer needs into engineering characteristics. A crucial step during QFD concerns the linking of engineering characteristics to customer needs in the House of Quality by the design team. It is generally assumed (looking at all the QFD success stories) that design teams can accurately predict the correlations between customer needs and engineering characteristics (also referred to as “Whats”/“Hows” correlations). This paper explicitly tests this assumption by comparing the “Whats”/“Hows” correlations estimated by a design team with those observed in a systematic user evaluation study, which has not been done before. Testing the assumption is important, because inaccurate estimates may lead to ergonomically ineffective (re)design of hand tools and a waste of company resources. Results revealed that the design team's correlation estimates were not as accurate as is generally assumed. Twenty-five percent of the estimates differed significantly with those observed in the user evaluation study. Thus, QFD is a useful method to assist design teams in designing ergonomically more comfortable hand tools, but only on the condition that the correlations between customer needs and engineering characteristics are validated, preferably by means of a systematic user evaluation study.     

A model-based hand gesture recognition system

This paper introduces a model-based hand gesture recognition system, which consists of three phases: feature extraction, training, and recognition. In the feature extraction phase, a hybrid technique combines the spatial (edge) and the temporal (motion) information of each frame to extract the feature images. Then, in the training phase, we use the principal component analysis (PCA) to characterize spatial shape variations and the hidden Markov models (HMM) to describe the temporal shape variations. A modified Hausdorff distance measurement is also applied to measure the similarity between the feature images and the pre-stored PCA models. The similarity measures are referred to as the possible observations for each frame. Finally, in recognition phase, with the pre-trained PCA models and HMM, we can generate the observation patterns from the input sequences, and then apply the Viterbi algorithm to identify the gesture. In the experiments, we prove that our method can recognize 18 different continuous gestures effectively. Received: 19 May 1999 / Accepted: 4 September 2000     

基于图像处理的显微外科手术质量评价研究*

目前显微外科手术质量评定仍采用测角计进行手工测量,测量中有一定的随意性,测量误差大。针对该问题,提出了应用图像处理技术对显微外科接指手术进行分析和质量评价的方法。通过与手工测量进行对比,图像处理方法评价客观,测量精度高,得到了满意的结果。     

An investigation for determining the optimum length of chopsticks

Chopsticks are one of the most simple and popular hand tools ever invented by humans, but have not previously been investigated by ergonomists. Two laboratory studies were conducted in this research, using a randomised complete block design, to evaluate the effects of the length of the chopsticks on the food-serving performance of adults and children. Thirty-one male junior college students and 21 primary school pupils served as subjects for the experiment. The results showed that the food-pinching performance was significantly affected by the length of the chopsticks, and that chopsticks of about 240 and 180 mm long were optimal for adults and pupils, respectively. Based on these findings, the researchers suggested that families with children should provide both 240 and 180 mm long chopsticks. In addition, restaurants could provide 210 mm long chopsticks, considering the trade-offs between ergonomics and cost.     

Exploiting eye–hand coordination to detect grasping movements

Human beings are very skillful at reaching for and grasping objects under multiple conditions, even when faced with an object's wide variety of positions, locations, structures and orientations. This natural ability, controlled by the human brain, is called eye–hand coordination. To understand this behavior it is necessary to study both eye and hand movements simultaneously. This paper proposes a novel approach to detect grasping movements by means of computer vision techniques. This solution fuses two viewpoints, one viewpoint which is obtained from an eye-tracker capturing the user's perspective and a second viewpoint which is captured by a wearable camera attached to a user's wrist. Utilizing information from these two viewpoints it is possible to characterize multiple hand movements in conjunction with eye-gaze movements through a Hidden–Markov Model framework. This paper shows that combining these two sources makes it possible to detect hand gestures using only the objects contained in the scene even without markers on the surface of the objects. In addition, it is possible to detect which is the desired object before the user can actually grasp said object.     

A data mining technique for discovering distinct patterns of hand signs: implications in user training and computer interface design

Hand signs are considered as one of the important ways to enter information into computers for certain tasks. Computers receive sensor data of hand signs for recognition. When using hand signs as computer inputs, we need to (1) train computer users in the sign language so that their hand signs can be easily recognized by computers, and (2) design the computer interface to avoid the use of confusing signs for improving user input performance and user satisfaction. For user training and computer interface design, it is important to have a knowledge of which signs can be easily recognized by computers and which signs are not distinguishable by computers. This paper presents a data mining technique to discover distinct patterns of hand signs from sensor data. Based on these patterns, we derive a group of indistinguishable signs by computers. Such information can in turn assist in user training and computer interface design.