Re-Evaluation Method by Index Finger Position in the Face Area Using Face Part Position Criterion for Sign Language Recognition.

Several researchers have proposed systems with high recognition rates for sign language recognition. Recently, there has also been an increase in research that uses multiple recognition methods and further fuses their results to improve recognition rates. The most recent of these studies, skeleton aware multi-modal SLR (SAM-SLR), achieved a recognition rate of 98.00% on the RGB video of the Turkish Sign Language dataset AUTSL. We investigated the unrecognized parts of this dataset and found that some signs where the fingers touch parts of the face were not correctly recognized. The proposed method is as follows: First, those with slight differences in top-1 and top-2 evaluation values in the SAM-SLR recognition results are extracted and re-evaluated. Then, we created heatmaps of the coordinates of the index finger in one-handed sign language in the face region of the recognition result in the top-1 to top-3 training data of the candidates based on the face part criteria, respectively. In addition, we extracted four index finger positions from the test data where the index finger stayed longer and obtained the product of the heatmap values of these positions. The highest value among them was used as the result of the re-evaluation. Finally, three evaluation methods were used: the absolute and relative evaluation with two heatmaps and an evaluation method integrating the absolute and relative evaluation results. As a result of applying the proposed method to the SAM-SLR and the previously proposed model, respectively, the best method achieved 98.24% for the highest recognition rate, an improvement of 0.30 points.

Risk factors for knee osteoarthritis in Japanese men: a case-control study.

Risk of knee osteoarthritis (OA) was assessed in a population-based case-control study of Japanese men. The study covered three health districts in Wakayama and Osaka prefectures, Japan. Subjects were male individuals >or=45 years old diagnosed radiographically with knee OA, and who did not display any established causes of secondary OA. Controls selected randomly from the general population were individually matched to cases for age, sex, and residential district. Subjects were interviewed using structured questionnaires to determine medical history, physical activity, socio-economic factors, and occupation. Interviews were obtained from 37 cases and 37 controls. In univariate analysis, heaviest weight in the past and physical work such as factory, construction, agricultural, or fishery work as the principal occupation significantly raised the risk of male knee OA (P<0.05). Odds ratios (OR) were determined using conditional logistic regression analysis mutually adjusted for potential risk factors using the results of univariate analysis. Heaviest weight in the past (OR 6.01, 95% confidence interval (CI) 1.18-30.5, P<0.05), past knee injury (OR 6.25, 95% CI 1.13-34.5, P<0.05), and physical work as the principal occupation (OR 6.20, 95% CI 1.40-27.5, P<0.05) represented independent factors associated with knee OA after controlling for other risk factors. Physical work is associated with knee OA, demonstrating the influence of working activity on the development of OA. The present study suggests that risk factors for knee OA in men resemble those in women.

Risk factors for knee osteoarthritis in Japanese women: heavy weight, previous joint injuries, and occupational activities.

OBJECTIVE: Risk of knee osteoarthritis (OA) associated with constitutional factors, history of joint injuries, and occupational factors was assessed in a case-control study among women in Japan. Results were contrasted with a comparable study in Britain. METHODS: The study covered 3 health districts in Japan. Cases were women aged >/= 45 years old, diagnosed with knee OA by orthopedic physicians utilizing radiography. No cases displayed established causes of secondary OA. Controls selected randomly from the general population were individually matched to each case for age, sex, and residential district. Subjects were interviewed using structured questionnaires to determine medical history, including history of joint injury, physical activity, socioeconomic factors, and occupation. Height and weight were measured. RESULTS: Interviews were obtained from 101 female cases and controls. The highest third of heaviest body weight in the past [high (> 62.0 kg) vs low (< 55 kg) odds ratio = 4.42, 95% confidence interval 1.17-16.64], previous injury to the knee (OR 7.11, 95% CI 2.40-21.09), sedentary work during initial employment (OR 0.35, 95% CI 0.15-0.84), and total working years (OR 1.05, 95% CI 1.01-1.08) represented independent factors associated with knee OA, after controlling for other potential risk factors. CONCLUSION: Heavy weight in the past appears to represent a risk factor for knee OA among women in Japan, as reported in Britain. Constitutional factors may represent important determinants for knee OA, regardless of race. Previous injury to the knee and occupational factors are also associated with knee OA in both Britain and Japan, although characteristic activities for work vary.