No abstract

Studies on Gait Recognition are mostly based on the assumption that walking direction is parallel to the camera, and the person's side view is extracted. Recently, walking direction has becoming one of the gait recognition challenge problems. In this work we explore gait recognition considering any directions of walking which is not definitely parallel to the camera. We propose a novel approach to computing the walking direction and extracting features by employing a human model. Furthermore, a Support Vector Machine (SVM) is performed allowing us to investigate and evaluate the recognition power of any walking directions. We applied our method to the real human walking video data, and achieved high recognition rate. Our approach finds out how changes in walking direction affect gait parameters in terms of recognition performance. As it is entirely based on human gait, our approach is robust to different type of clothes and different walking directions.

Image denoising is a challenging task due to possible data bias and prediction variance. Existing approaches usually suffer from high computational cost. In this work, we propose an unsupervised image denoiser, dubbed as adaptIve Dual sElf-Attention Network (IDEA-Net), to handle these challenges. IDEA-Net benefits from a generatively learned image-wise dual self-attention region where the denoising process is enforced. Besides, IDEA-Net is not only robust to possible data bias but also helpful to reduce the prediction variance by applying a simplified encoder-decoder with Poisson dropout operations on a single noisy image merely. The proposed IDEA-Net demonstrated the outperformance on four benchmark datasets compared with other single-image-based learning and nonlearning image denoisers. IDEA-Net also shows an appropriate choice to remove real-world noise in low-light and noisy scenes, which in turn, contribute to more accurate dark face detection. The source code is available at https://github.com/zhemingzuo/IDEA-Net.

Feature parameters extraction is critical for speaker recognition research. The paper presents the function of pitch, formant and Mel frequency central coefficient (MFCC) in speaker recognition. It can increase the identification rate effectively for feature parameter sorts the speech corpus. Using Euclid Distance to compare feature parameters is very effective.

: The complete assignments of 1H and 13C NMR data for a series of synthesized diosgenyl saponin analogs are described, viz. The assignments were achieved using homo-and heteronuclear two-dimensional NMR techniques.