Abstract:Tongue diagnosis is a non-invasive, efficient, and accurate method for determining a person's physical condi-tion, and plays an essential role in disease diagnosis and health management. However, tongue diagnosis is easily influenced by the subjective experience of the practitioner and the light environment. In addition, tongue di-agnosis lacks clear quantitative indicators and objective records. This all limits the transmission and develop-ment of tongue diagnosis. Therefore, the acquisition and analysis of tongue information using image equipment, image processing and computer vision have become a hot research topic for the objectification of tongue di-agnosis. This paper reviews the research progress of tongue diagnosis objectification in Traditional Chinese medicine. The tongue image acquisition, color correction, segmentation, feature extraction and analysis, and disease prediction included in the study of tongue diagnosis objectification are reviewed. The shortcomings of current automated tongue diagnosis systems and future research ideas are also summarized to provide a ref-erence for further development of tongue diagnosis objectification.

Abstract:Speech recognition is a hot topic in the field of artificial intelligence. Generally, speech recognition models can only run on large servers or dedicated chips. This paper presents a keyword speech recognition system based on a neural network and a conventional STM32 chip. To address the limited Flash and ROM resources on the STM32 MCU chip, the deployment of the speech recognition model is optimized to meet the requirements of keyword recognition. Firstly, the audio information obtained through sensors is subjected to MFCC (Mel Fre-quency Cepstral Coefficient) feature extraction, and the extracted MFCC features are input into a CNN (Convolutional Neural Network) for deep feature extraction. Then, the features are input into a fully connected layer, and finally, the speech keyword is classified and predicted. Deploying the model to the STM32F429, the prediction model achieves an accuracy of 90.58%, a decrease of less than 1% compared to the accuracy of 91.49% running on a computer, with good performance.

Abstract:In order to solve the shortcomings of current fatigue detection methods such as low accuracy or poor real-time performance, a fatigue detection method based on multi-feature fusion is proposed. Firstly, the HOG face de-tection algorithm and KCF target tracking algorithm are integrated and deformable convolutional neural network is introduced to identify the state of extracted eyes and mouth, fast track the detected faces and extract con-tinuous and stable target faces for more efficient extraction. Then the head pose algorithm is introduced to detect the driver's head in real time and obtain the driver's head state information. Finally, a multi-feature fusion fatigue detection method is proposed based on the state of the eyes, mouth and head. According to the experimental results, the proposed method can detect the driver's fatigue state in real time with high accuracy and good ro-bustness compared with the current fatigue detection algorithms.

Abstract:With the rapid development of social economy, transportation has become faster and more efficient. As an important part of goods transportation, the safe maintenance of tunnel highways has become particularly im-portant. The maintenance of tunnel roads has become more difficult due to problems such as sealing, nar-rowness and lack of light. Currently, target detection methods are advantageous in detecting tunnel vehicles in a timely manner through monitoring. Therefore, in order to prevent vehicle misdetection and missed detection in this complex environment, we propose aYOLOv5-Vehicle model based on the YOLOv5 network. This model is improved in three ways. Firstly, The backbone network of YOLOv5 is replaced by the lightweight MobileNetV3 network to extract features, which reduces the number of model parameters; Next, all convolutions in the neck module are improved to the depth-wise separable convolutions to further reduce the number of model param-eters and computation, and improve the detection speed of the model; Finally, to ensure the accuracy of the model, the CBAM attention mechanism is introduced to improve the detection accuracy and precision of the model. Experiments results demonstrate that the YOLOv5-Vehicle model can improve the accuracy.

Abstract:Medical image fusion has been developed as an efficient assistive technology in various clinical applications such as medical diagnosis and treatment planning. Aiming at the problem of insufficient protection of image contour and detail information by traditional image fusion methods, a new multimodal medical image fusion method is proposed. This method first uses non-subsampled shearlet transform to decompose the source image to obtain high and low frequency subband coefficients, then uses the latent low rank representation algorithm to fuse the low frequency subband coefficients, and applies the improved PAPCNN algorithm to fuse the high frequency subband coefficients. Finally, based on the automatic setting of parameters, the optimization method configuration of the time decay factor 𝛼𝑒 is carried out. The experimental results show that the proposed method solves the problems of difficult parameter setting and insufficient detail protection ability in traditional PCNN algorithm fusion images, and at the same time, it has achieved great improvement in visual quality and objective evaluation indicators.

Abstract:As an important part of water level warning in water conservancy projects, often due to the influence of en-vironmental factors such as light and stains, the acquired water gauge images have sticky, broken and bright spot conditions, which affect the identification of water gauges. To solve this problem, a water gauge image denoising model based on improved adaptive total variation is proposed. Firstly, the regular term exponent in the adaptive total variational equation is changed to an inverse cosine function; secondly, the differential curvature is used to distinguish the image noise points and increase the smoothing strength at the noise points; finally, according to the characteristics of the gradient mode and adaptive gradient threshold after Gaussian filtering, the New model can adaptively denoise in the smooth area and protect the edge area, so as to have the characteristics of both edge-preserving denoising. The experimental results show that the new model has a great improvement in image vision, higher iteration efficiency and an average increase of 1.6 dB in peak signal-to-noise ratio, and an average increase of 9% in structural similarity, which is more beneficial to practical applications.