Video compression algorithm based on neural network structures
M Knop, R Cierniak, N Shah - … , ICAISC 2014, Zakopane, Poland, June 1-5 …, 2014 - Springer
M Knop, R Cierniak, N Shah
Artificial Intelligence and Soft Computing: 13th International Conference …, 2014•SpringerThe presented here paper describes a new approach to the video compression problem.
Our method uses the neural network image compression algorithm which is based on the
predictive vector quantization (PVQ). In this method of image compression two different
neural network structures are exploited in the following elements of the proposed system: a
competitive neural networks quantizer and a neuronal predictor. For the image compression
based on this approach it is important to correctly detect scene changes in order to improve …
Our method uses the neural network image compression algorithm which is based on the
predictive vector quantization (PVQ). In this method of image compression two different
neural network structures are exploited in the following elements of the proposed system: a
competitive neural networks quantizer and a neuronal predictor. For the image compression
based on this approach it is important to correctly detect scene changes in order to improve …
Abstract
The presented here paper describes a new approach to the video compression problem. Our method uses the neural network image compression algorithm which is based on the predictive vector quantization (PVQ). In this method of image compression two different neural network structures are exploited in the following elements of the proposed system: a competitive neural networks quantizer and a neuronal predictor. For the image compression based on this approach it is important to correctly detect scene changes in order to improve performance of the algorithm. We describe the image correlation method and discuss its effectiveness.
Springer
以上显示的是最相近的搜索结果。 查看全部搜索结果