http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Robust Face Recognition under Limited Training Sample Scenario using Linear Representation
( Omer Iqbal ),( Waqas Jadoon ),( Zia Ur Rehman ),( Fiaz Gul Khan ),( Babar Nazir ) 한국인터넷정보학회 2018 KSII Transactions on Internet and Information Syst Vol.12 No.7
Recently, several studies have shown that linear representation based approaches are very effective and efficient for image classification. One of these linear-representation-based approaches is the Collaborative representation (CR) method. The existing algorithms based on CR have two major problems that degrade their classification performance. First problem arises due to the limited number of available training samples. The large variations, caused by illumintion and expression changes, among query and training samples leads to poor classification performance. Second problem occurs when an image is partially noised (contiguous occlusion), as some part of the given image become corrupt the classification performance also degrades. We aim to extend the collaborative representation framework under limited training samples face recognition problem. Our proposed solution will generate virtual samples and intra-class variations from training data to model the variations effectively between query and training samples. For robust classification, the image patches have been utilized to compute representation to address partial occlusion as it leads to more accurate classification results. The proposed method computes representation based on local regions in the images as opposed to CR, which computes representation based on global solution involving entire images. Furthermore, the proposed solution also integrates the locality structure into CR, using Euclidian distance between the query and training samples. Intuitively, if the query sample can be represented by selecting its nearest neighbours, lie on a same linear subspace then the resulting representation will be more discriminate and accurately classify the query sample. Hence our proposed framework model the limited sample face recognition problem into sufficient training samples problem using virtual samples and intra-class variations, generated from training samples that will result in improved classification accuracy as evident from experimental results. Moreover, it compute representation based on local image patches for robust classification and is expected to greatly increase the classification performance for face recognition task.
Ali Raza,Anam Omer,Sara Iqbal,Vineet Gudsoorkar,Pramoda Koduru,Kumar Krishnan 대한소화기내시경학회 2019 Clinical Endoscopy Vol.52 No.2
Background/Aims: Bile leak is one of the most common complications of liver transplantation. The treatment options for bile leaksinclude conservative management, surgical re-intervention, percutaneous drainage and endoscopic drainage. We aimed to perform asystematic review to identify the effcacy of endoscopic treatment in the resolution of post-transplant bile leaks. Methods: Two independent reviewers performed systematic literature search in PubMed, ISI Web of Science, grey literature andrelevant references in May 2017. Human studies in English with documented post-liver transplant bile leaks were included. Results: Thirty-four studies were included in the final analysis. The pooled effcacy of biliary stents for the resolution of post-transplantbile leaks was 82.43% compared with 87.15% effcacy of nasobiliary tubes. The effcacy of biliary stents was lower for anastomotic leaks(69.23%) compared to T-tube (90.9%) or cut-surface/ cystic duct stump related leaks (92.8%). Similarly, the effcacy of nasobiliary tubewas also lower for anastomotic leaks (58.33%) compared to T-tube or cut-surface related leaks (100%). Conclusions: In this systematic review, the overall effcacy was 82.43% in biliary stent group, and 87.15% in nasobiliary tube group. Both biliary stent and nasobiliary tube were more effective in managing non-anastomotic leaks compared to anastomotic leaks.