With the arrival of big data age, the deep convolutional neural networks (DCNNs) with more hidden layers have a more complex network structure and more powerful ability than traditional machine learning methods for feature learning and feature expression. This paper first proposes a model of the DCNN to discuss the basic structure of model, convolutional feature extraction and learning algorithm of convolutional neural network; then, mainly introduces several aspects, that is, the construction of the typical network structure, the training methods, and the parameter settings of network model to be improved and optimized. Moreover, the network model is applied to the classification and recognition of Antarctic hydrological features and compared with some existing classification methods. The novelty of this paper mainly includes two aspects, i.e., the one is that the design and construction of the structure of deep neural network based on deep learning method are performed, namely, connection, weight, calculator, learning training of network, and other design. The other is classifying hydrological characteristics of Pritz Bay in Antarctica's images by the DCNN. The results show that the correct recognition rate of the model method constructed by this paper is the highest. Finally, some problems in the current research are briefly summarized and discussed, and the new direction in the future development is forecasted. INDEX TERMS Deep learning, convolutional neural network, deep belief network, hydrological feature recognition.
Some algorithms of feature extraction in existing literature studied for image processing was the gray image with one-dimensional parameter. However, some feature points' extraction for three-dimensional color of polar image, such as the color edge extraction, inflection points, and so on, was urgently to be solved a polar color problem. For achieving quickly and accurately the color feature extraction to polar image, this paper proposed a similar region of color algorithm. The algorithm was compared to polar image, and the effect to color extraction was also described by the combination of the proposed and existing algorithms. Moreover, this paper gave the comparison of the proposed algorithm and an existing classical algorithm to extraction of color feature. These researches in this paper provided a powerful tool for polar image classification, color feature segmentation, precise recognition, and so on.
The extraction of certain characteristics points such as color edge, inflection points, etc., is an imaging problem which requires urgent attention. This paper proposes a similar color segment algorithm. The algorithm is analyzed in different color distribution situations, and the extraction effect to the color is shown. Additionally, experimental analysis of the algorithms is provided. Experimental results indicate that the similar color segment algorithm performs better than existing algorithms in relation to a more obvious color edge, as it has better edge detection, stronger anti-noise ability, a faster processing speed and other advantages. Moreover, this paper compares the proposed algorithm to existing classical feature extraction algorithms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.