http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Yimin Zhou,Guangyao Li,Yunlan Tan 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.7
Photograph aesthetical evaluation has been widely investigated in these decades. The most used assessing methods are mainly classical data mining methods such as SVM, ANN(Artificial Neural Network), linear programming and so on. In this paper, we presented a method based on artificial neural network and deep learning methods which is also a hot research topic recently. We downloaded a medium and a large dataset from a well-known online photograph portal and trained on them. Results showed that the accuracy of classification was above 82.1%, which was better than all state-of-the-art methods as well as a moderate result from those methods never adopted up to now.
Image Completion Using Similarity Analysis and Transformation
Mang Xiao,Guangyao Li,Yunlan Tan,Jie Qin 보안공학연구지원센터 2015 International Journal of Multimedia and Ubiquitous Vol.10 No.4
Image completion is aim to fill the missing regions in images. A robust completion technique using similarity analysis and transformation is proposed to address this problem. Firstly, in order to decrease the search space of patches, random mapping method is used to analyze texture regions which have similar structure and texture with damaged regions. Secondly, geometric and photometric transformations of image are adopted to find the best patches. Thirdly, increasing the accuracy of the structure propagation, a priority calculation method is optimized based on confidence factor and edge information. Finally, a number of examples on real and synthetic images show the effectiveness of our algorithm for image completion.