In Taiwan, mushrooms are an agricultural product with high nutritional value and economic benefit. However, global warming and climate change have affected plant quality. As a result, technological greenhouses are replacing traditional tin houses as locations for mushroom planting. These greenhouses feature several complex parameters. If we can reduce the complexity such greenhouses and improve the efficiency of their production management using intelligent schemes, technological greenhouses could become the expert assistants of farmers. In this paper, the main goal of the developed system is to measure the mushroom size and to count the amount of mushrooms. According to the results of each measurement, the growth rate of the mushrooms can be estimated. The proposed system also records the data of the mushrooms and broadcasts them to the mobile phone of the farmer. This improves the effectiveness of the production management. The proposed system is based on the convolutional neural network of deep learning, which is used to localize the mushrooms in the image. A positioning correction method is also proposed to modify the localization result. The experiments show that the proposed system has a good performance concerning the image measurement of mushrooms.

One of the common methods for measuring distance is to use a camera and image processing algorithm, such as an eye and brain. Mechanical stereo vision uses two cameras to shoot the same object and analyzes the disparity of the stereo vision. One of the most robust methods to calculate disparity is the well-known census transform, which has the problem of conversion window selection. In this paper, three methods are proposed to improve the performance of the census transform. The first one uses a low-pass band of the wavelet to reduce the computation loading and a high-pass band of the wavelet to modify the disparity. The main idea of the second method is the adaptive size selection of the conversion window by edge information. The third proposed method is to apply the adaptive window size to the previous sparse census transform. In the experiments, two indexes, percentage of bad matching pixels (PoBMP) and root mean squared (RMS), are used to evaluate the performance with the known ground truth data. According to the results, the computation required can be reduced by the multiresolution feature of the wavelet transform. The accuracy is also improved with the modified disparity processing. Compared with previous methods, the number of operation points is reduced by the proposed adaptive window size method.

Surgeons determine the treatment method for patients with epiglottis obstruction based on its severity, often by estimating the obstruction severity (using three obstruction degrees) from the examination of drug-induced sleep endoscopy images. However, the use of obstruction degrees is inadequate and fails to correspond to changes in respiratory airflow. Current artificial intelligence image technologies can effectively address this issue. To enhance the accuracy of epiglottis obstruction assessment and replace obstruction degrees with obstruction ratios, this study developed a computer vision system with a deep learning-based method for calculating epiglottis obstruction ratios. The system employs a convolutional neural network, the YOLOv4 model, for epiglottis cartilage localization, a color quantization method to transform pixels into regions, and a region puzzle algorithm to calculate the range of a patient’s epiglottis airway. This information is then utilized to compute the obstruction ratio of the patient’s epiglottis site. Additionally, this system integrates web-based and PC-based programming technologies to realize its functionalities. Through experimental validation, this system was found to autonomously calculate obstruction ratios with a precision of 0.1% (ranging from 0% to 100%). It presents epiglottis obstruction levels as continuous data, providing crucial diagnostic insight for surgeons to assess the severity of epiglottis obstruction in patients.

This study aims to develop an artificial intelligence module for recognizing abnormal tension in textile weaving, The module can be used to address the time-consuming and inaccurate issues associated with traditional manual methods. Long short-term memory (LSTM) recurrent neural networks as the algorithm for identifying different types of abnormal tension are employed in this module. This study focuses on training and validating the model using five common patterns. Additionally, an approach involving the integration of plug-in modules and edge computing in deep learning is employed to achieve the research objectives without altering the original system architecture. Multiple experiments were conducted to search for the optimal model parameters. According to the experimental results, the average recognition rate for abnormal tension is 97.12%, with an average computation time of 46.2 milliseconds per sample. The results indicate that the recognition accuracy and computation time meet the practical performance requirements of the system.