Artificial Neural Networks for Document Analysis and Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
EURASIP Journal on Applied Signal Processing
Vector Quantization of Images Using a Fuzzy Clustering Method
Cybernetics and Systems
Classification of Audio Signals Using a Bhattacharyya Kernel-Based Centroid Neural Network
PAKDD '09 Proceedings of the 13th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining
Centroid Neural Network with Spatial Constraints
PAKDD '09 Proceedings of the 13th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining
Centroid neural network with chi square distance measure for texture classification
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Centroid neural network for face recognition
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Compression of remote sensing images based on ridgelet and neural network
ISNN'05 Proceedings of the Second international conference on Advances in neural networks - Volume Part II
Heterogeneous centroid neural networks
ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
Gradient-based local descriptor and centroid neural network for face recognition
ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part II
Classification of MPEG video content using divergence measure with data covariance
PCM'05 Proceedings of the 6th Pacific-Rim conference on Advances in Multimedia Information Processing - Volume Part I
Content-Based classification of images using centroid neural network with divergence measure
AI'06 Proceedings of the 19th Australian joint conference on Artificial Intelligence: advances in Artificial Intelligence
Hi-index | 0.00 |
An edge preserving image compression algorithm based on an unsupervised competitive neural network is proposed. The proposed neural network, the called weighted centroid neural network (WCNN), utilizes the characteristics of image blocks from edge areas. The mean/residual vector quantization (M/RVQ) scheme is utilized in this proposed approach as the framework of the proposed algorithm. The edge strength of image block data is utilized as a tool to allocate the proper code vectors in the proposed WCNN. The WCNN successfully allocates more code vectors to the image block data from edge area while it allocates less code vectors to the image black data from shade or non-edge area when compared to conventional neural networks based on VQ algorithm. As a result, a simple application of WCNN to an image compression problem gives improved edge characteristics in reconstructed images over conventional neural network based on VQ algorithms such as self-organizing map (SOM) and adaptive SOM