作者: Rafał Grycuk , Michał Knop
DOI: 10.1007/978-3-319-23814-2_13
关键词:
摘要: In this paper we present a new method for video compression. Our approach is based on well known neural network image compression algorithm: predictive vector quantization (PVQ). of two different structures are exploited in the following elements proposed system: competitive networks quantizer and neuronal predictor. It important to correctly detect key frame order improve performance algorithm. For detection our uses SKFD SURF