Concerning the problems of the lack of standard words， fuzzy semantics and feature sparsity in news topic text， a news topic text classification method based on Bidirectional Encoder Representations from Transformers（BERT） and Feature Projection network（FPnet） was proposed. The method includes two implementation modes. In mode 1： the multiple-layer fully connected layer features were extracted from the output of news topic text at BERT model， and the final extracted text features were purified with the combination of feature projection method， thereby strengthening the classification effect. In mode 2， the feature projection network was fused in the hidden layer inside the BERT model for feature projection， so that the classification features were enhanced and purified through the hidden layer feature projection. Experimental results on Toutiao， Sohu News， THUCNews-L、THUCNews-S datasets show that the two above modes have better performance in accuracy and macro-averaging F1 value than baseline BERT method with the highest accuracy reached 86.96%， 86.17%， 94.40% and 93.73% respectively， which proves the feasibility and effectiveness of the proposed method.

Traditional machine learning methods fail to fully dig out semantic information and association information when classifying the sentiment polarity of online comment text. Although the existing deep learning methods can extract the semantic information and contextual information， the process is often one-way and there are some deficiencies in the process of obtaining the deep semantic information of comment text. Aiming at the above problems， a text sentiment analysis method was proposed by combining generalized autoregressive pretraining for language understanding model （XLNet） and RCNN （Recurrent Convolutional Neural Network）. Firstly， XLNet was used to represent the text features. And by introducing the segment-level recurrence mechanism and relative position information encoding， the contextual information of comment text was fully considered， thereby improving the expression ability of text features effectively. Then， RCNN was used to train the text features in both directions and extract the context semantic information of the text at a deeper level， thereby improving the comprehensive performance in the sentiment analysis task. The experiments with the proposed method were carried out on three public datasets weibo-100k， waimai-10k and ChnSentiCorp. The results show that the accuracy reaches 96.4%， 91.8% and 92.9% respectively， which proves the effectiveness of the proposed method in the sentiment analysis task.

As the traditional Scale Invariant Feature Transform (SIFT) image matching algorithm has high false matching rate and eliminating the condition of mismatching points is unitary, an adaptive image matching method based on SIFT operator fused with maximum dissimilarity coefficient was proposed. Firstly, On the basis of Euclidean distance measurement, the optimal maximum dissimilarity coefficients values of the 128-dimensional feature vectors in SIFT algorithm were obtained. Then, the matching points were selected according to the obtained optimal values. Random Sample Consensus (RANSAC) was used to calculate the correct rate of matching. Finally, the stereo matching images of Daniel Scharstein and Richard Szeliski were used to verify the algorithm. The experimental results show that the correct matching rate of the improved algorithm is about 10 percentage points higher than that of the traditional SIFT algorithm. The improved algorithm effectively reduces the mismatches and is more suitable for image matching applications with similar regions. In terms of runtime, the proposed method has an average time of 1.236 s, which can be applied to the systems with low real-time requirements.