We describe a new method to find and cluster recurrent keyplaces in a movie. It consists of an unsupervised classification of shots that are taking place in the same physical loca...
The geometric features of images, such as edges, are difficult to represent. When a redundant transform is used for their extraction, the compression challenge is even more dif...
Nowadays, the slanted lenticular display becomes a representative one among the commercially introduced autostereoscopic displays. The paper presents a simple method to correct th...
Han Shin Lim, Seok-Hoon Kim, Yun-Gu Lee, HyunWook ...
We consider approaches for exact similarity search in a high dimensional space of correlated features representing image datasets, based on principles of clustering and vector qua...
Software systems embed in them knowledge about the domain in which they operate. However, this knowledge is “latent”. Making such knowledge accessible could be of great value ...