A Massive Image Recognition Algorithm Based on Attribute Modelling and Knowledge Acquisition

In this paper, an in-depth study and analysis of attribute modelling and knowledge acquisition of massive images are conducted using image recognition. For the complexity of association relationships between attributes of incomplete data, a single-output subnetwork modelling method for incomplete data is proposed to build a neural network model with each missing attribute as output alone and other attributes as input in turn, and the network structure can deeply portray the association relationships between each attribute and other attributes. To address the problem of incomplete model inputs due to the presence of missing values, we propose to treat and describe the missing values as system-level variables and realize the alternate update of network parameters and dynamic filling of missing values through iterative learning among subnets. The method can effectively utilize the information of all the present attribute values in incomplete data, and the obtained subnetwork population model is a fit to the attribute association relationships implied by all the present attribute values in incomplete data. The strengths and weaknesses of existing image semantic modelling algorithms are analysed. To reduce the workload of manually labelling data, this paper proposes the use of a streaming learning algorithm to automatically pass image-level semantic labels to pixel regions of an image, where the algorithm does not need to rely on external detectors and a priori knowledge of the dataset. Then, an efficient deep neural network mapping algorithm is designed and implemented for the microprocessing architecture and software programming framework of this edge processor, and a layout scheme is proposed to place the input feature maps outside the kernel DDR and the reordered convolutional kernel matrices inside the kernel storage body and to design corresponding efficient vectorization algorithms for the multidimensional matrix convolution computation, multidimensional pooling computation, local linear normalization, etc., which exist in the deep convolutional neural network model. The efficient vectorized mapping scheme is designed for the multidimensional matrix convolution computation, multidimensional pooling computation, local linear normalization, etc. in the deep convolutional neural network model so that the utilization of MAC components in the core loop can reach 100%.