Multi-view fuzzy clustering analysis is often used for medical image segmentation such as brain MR image segmentation. However, in traditional multi-view clustering, it assumes that each view plays the same role to the final partition result, which omits the negative influences caused by noisy or weak views. In this paper, a novel entropy weighting based centralized clustering technique is proposed for multi-view datasets where the Shannon entropy is hired for view weight learning. Moreover, the centralized strategy is employed for collaborate learning. Extensive experiments show that the promising performance of our proposed clustering technique. More importantly, a case study on brain MR image segmentation indicates the application ability of our clustering technique.

With the development of computer vision technology, the demand for deploying vision inspection tasks on edge mobile devices is becoming increasingly widespread. To meet the requirements of application scenarios on edge devices with limited computational resources, many lightweight models have been proposed that achieves good performance with fewer parameters. In order to achieve higher model accuracy with fewer parameters, a novel lightweight convolutional neural network CCNNet is proposed. The proposed model compresses the modern CNN architecture with “bottleneck” architecture and gets multi-scale features with downsampling rate 3, adopts GCIR module stacking and MDCA attention mechanism to promote the model performance. Compares with several benchmark lightweight convolutional neural network models on CIFAR-10, CIFAR-100 and ImageNet-1 K, the proposed model outperforms them. In order to verify its generalization, a fine-grained dataset for traditional Chinese medicine recognition named “TCM-100” is created. The proposed model applies in the field of traditional Chinese medicine recognition and achieves good classification accuracy, which also demonstrates it generalizes well. The bottleneck framework of the proposed model has some reference values for the design of lightweight model. The proposed model has some promotion significance for classification or recognition applications in other fields.

No abstract