Abstract-Hand detection is essential for many hand related tasks, e.g. parsing hand pose, understanding gesture, which are extremely useful for robotics and human-computer interaction. However, hand detection in uncontrolled environments is challenging due to the flexibility of wrist joint and cluttered background. We propose a deep learning based approach which detects hands and calibrates in-plane rotation under supervision at the same time. To guarantee the recall, we propose a context aware proposal generation algorithm which significantly outperforms the selective search. We then design a convolutional neural network(CNN) which handles object rotation explicitly to jointly solve the object detection and rotation estimation tasks. Experiments show that our method achieves better results than state-of-the-art detection models on widely-used benchmarks such as Oxford and Egohands database. We further show that rotation estimation and classification can mutually benefit each other.

The extracts from hulls, brans and flours of Fagopyrum esculentum Möench (FEM, three varieties) and Fagopyrum tartaricum L. Gaerth (FTG, seven varieties) were screened for free and bound phenolic content or total phenolic content (TPC) , as well as 1, 1 diphenyl-2-picryl hydrazyl (DPPH) free radical scavenging activity and reducing power. Free phenolics were predominant in buckwheat hulls, brans and flours. FEM hulls extract exhibited the highest reducing power and DPPH free radical scavenging activity with the average EC50 84.54μg/mL and IC50 11.54μg/mL respectively, FTG brans extract had the highest average TPC (24.87 mg GAE/g dwb), and FEM folurs extract showed the lowest TPC, reducing power and radical scavenging activity. Furthermore, the correlations among TPC, DPPH free radical scavenging activity and reducing power of all the samples were investigated. The rank correlation coefficient (rs) between reducing power and DPPH free radical scavenging activity of buckwheat hulls, between TPC and DPPH free radical scavenging activity of buckwheat flours were 0.76 and 0.79, respectively (p < 0.05). However, there is no significant correlation between the remaining indexes of hulls and flours, as well as the ten buckwheat brans. This result indicated that some non-phenolic compounds also contributed to the total antioxidant activity in hulls, brans and flours of buckwheats. This study demonstrated that buckwheat hulls and brans, rather than flours, are good source of antioxidants.

No abstract

No abstract