Multi-Label Text Classification （MLTC） is one of the important subtasks in the field of Natural Language Processing （NLP）. In order to solve the problem of complex correlation between multiple labels， an MLTC method TLA-BERT was proposed by incorporating Bidirectional Encoder Representations from Transformers （BERT） and label semantic attention. Firstly， the contextual vector representation of the input text was learned by fine-tuning the self-coding pre-training model. Secondly， the labels were encoded individually by using Long Short-Term Memory （LSTM） neural network. Finally， the contribution of text to each label was explicitly highlighted with the use of an attention mechanism in order to predict the multi-label sequences. Experimental results show that compared with Sequence Generation Model （SGM） algorithm， the proposed method improves the F value by 2.8 percentage points and 1.5 percentage points on the Arxiv Academic Paper Dataset （AAPD） and Reuters Corpus Volume I （RCV1）-v2 public dataset respectively.

Color coded structured light based on De Bruijn sequence is a kind of spatial code method that is characterized by rapid shape measurement. The recognition of color stripes is a key issue. Considering projected De Bruijn stripe pattern combining four colors with high and low intensity, segmentation of high and low intensity stripes was implemented by using linear filter of second derivative of L channel in L*a*b* color space. Adaptive color clustering was designed by employing Principal Component Analysis (PCA) and K-means clustering. The recognition of four colors with two intensities was finished. The experimental results indicate that the proposed method is robust to factors such as ambient light and it satisfies demand for high precision and simple extraction of information to structured light vision measurement.