Crop leaf segmentation was one important research content in agricultural machine vision applications. In order to study and solve the segmentation problem of occlusive leaves, an improved watershed algorithm was proposed in this paper. Firstly, the color threshold component (G-R)/(G+R) was used to extract the green component of the cotton leaf image and remove the shadow and invalid background. Then the lifting wavelet algorithm and Canny operator were applied to extract the edge of the pre-processed image to extract cotton leaf region and enhance the leaf edge. Finally, the image of the leaf was labeled with morphological methods to improve the traditional watershed algorithm. By comparing the cotton leaf area segmented using the proposed algorithm with the manually extracted cotton leaf area, successful rates for all the images were higher than 97%. The results not only demonstrated the effectiveness of the algorithm, but also laid the foundation for the construction of cotton growth monitoring system.
The challenges associated with autonomous information processing and storage will be resolved by neuromorphic computing, which takes inspiration from neural networks in the human brain. To create suitable artificial synaptic devices for artificial intelligence, it is essential to look for approaches to improve device performance. In the present study, we suggest a method to address this problem by inserting an ultrathin AlOX layer at the side of ferroelectric film for the prepared ferroelectric organic effect transistor (Fe-OFET) to modify a ferroelectric polymer film with a low coercive field. The transistors parameters are greatly improved (large memory window exceeding 14 V, high on-off current ratio of 103, and hole mobility up to 10-2 cm2V-1s-1). Furthermore, the optimized high-performance Fe-OFET with 2 nm thickness of AlOX layer is found to have synaptic behaviors including postsynaptic current (PSC), term/long-term plasticity (STP/LTP), spike-amplitude-dependent plasticity (SADP), spike-duration-dependent plasticity (SDDP), paired-pulse facilitation (PPF), spike-rate-dependent plasticity (SRDP), and spike-number-dependent plasticity (SNDP). An outstanding learning accuracy of 87.5% is demonstrated by an imitated artificial neural network made up of Fe-OFET for a big image version of handwritten digits (28 × 28 pixel) from the Modified National Institute of Standards and Technology (MNIST) dataset. By improving synaptic transistor performance in this way, a new generation of neuromorphic computing systems is set to be developed.
This project tries to design a wireless intelligent pH sensor to monitor the pH value of nutrient solution in real time by using the analog front circuit LMP91200, microprocessor STM32F103c8t6 and WiFi module.The experiment shows : this equipment has a high accuracy, can be 0.01; it can access business cloud services platform to achieve the functions like accurate acquisition and calibration of pH value, Interactive with cloud platform through WiFi Networks; APP and PC for the remote measurement is stable, after 12 hours of testing there is no packet loss phenomenon;Because of high uploading speed, in 5 seconds it can complete the device networking and upload, besides, the cloud services have changed the traditional way of nutrient solution measurement.
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.