The invention puts forward a potato surface defect detection method based on a convolutional neural network. Colored images of potatoes are obtained by industrial cameras, and an image processing module is used for conducting analysis processing on the obtained images. The method is characterized in that the convolutional neural network is adopted for detecting the surface defects of the potatoes,a training set serves as a sample for training the convolutional neural network, then a prediction set is input to the network after training, and a softmax classifier is adopted for achieving classification of the potatoes. According to the method, feature extraction is not required, there is no need to set specific detection algorithms according to defect types, the images are directly input tothe network, and therefore the potato surface defect detection method has the advantages of being high in accuracy, short in algorithm running time, high in feasibility and robustness and the like, and has a significant meaning in the potato processing industry.

Potato surface defect detection method based on convolutional neural network

The invention relates to the field of medical equipment, in particular to an intelligent transfusion monitoring alarm system which comprises an infusion monitoring terminal, a charging device, a management terminal, a server and a monitoring condition analysis module; wherein the management terminal is used for acquiring patient information needing to be subjected to infusion and sending the patient information to the server, the server is used for distributing an available bed to the patient after receiving the corresponding patient information, and then the server distributes an infusion monitoring terminal with high charging completion degree on the charging device according to the allocated bed information; the infusion monitoring terminal detects the dropping rate of the liquid medicine in an infusion tube dropping kettle and sending the detected rate information to the monitoring condition analysis module, the monitoring condition analysis module compares and judges whether the transfusion condition of the patient is normal or not according to the dropping rate of the liquid medicine detected by the transfusion monitoring terminal and the dropping rate of the liquid medicinedetected by the transfusion monitoring terminal when the transfusion monitoring terminal starts monitoring. According to the scheme, the problem that the infusion monitoring terminal is judged mistakenly due to human individual difference is solved.

Intelligent transfusion monitoring alarm system and method

The invention discloses a metal workpiece surface structure false detection result elimination method. The method comprises the steps of performing detection by adopting a conventional defect identification method to obtain an initial defect image set; calculating an information entropy Hp of a current defect image; calculating a gray-level co-occurrence matrix G of the current defect image at four angles of 0 degree, 45 degrees, 90 degrees and 135 degrees; calculating energy ASM, image local correlation COR, contrast CON and an edge ratio Re; and calculating complexity CP of the image, obtaining an experience threshold through an experiment, and when the currently detected image complexity is higher than the threshold, regarding that the current image is a normal image, and eliminating the current image from the initial defect image set. A falsely detected structure region can be eliminated after R-CNN-based defect detection, so that the defect detection accuracy is improved and the online defect detection can be carried out in an efficient and high-quality manner.

Metal workpiece surface structure false detection result elimination method

Installation et procede pour l’evaluation de la qualite d’un lot de produits alimentaires La presente invention concerne une installation (1) pour l’evaluation de la qualite d’un lot de produits alimentaires comportant un dispositif de lavage (3) du lot muni d’un tambour (30), des moyens d’ejection, de fractions du lot, au niveau d’une extremite de sortie (34), en face de laquelle est monte en rotation un volet (35) conforme pour interdire ou permettre un deversement des fractions a travers une ouverture de sortie (36) communiquant avec une zone (41) d’une table d’inspection (4) configuree pour se deplacer a une vitesse v le long d’un axe perpendiculaire a l’axe X du tambour (30), ladite zone (41) comportant une pluralite de gorge (42) de reception d’une rangee de produits issus de ladite fraction. Elle est caracterisee en ce qu’elle comporte des moyens pour garantir un deversement a travers l’ouverture de sortie (36) de fractions successives comportant une quantite sensiblement constante de produits, ainsi que des moyens pour assurer une repartition reguliere des produits le long de chacune des gorges (42). Fig. 1

Installation pour l’évaluation de la qualité d’un lot de produits alimentaires et procédé pour sa mise en œuvre

Disclosed are a guiding robot for guiding a patient put on a drip to move, and a guiding method. The guiding robot comprises a control unit (6), a moving unit (2) and a fixed unit (3), wherein the control unit (6) is constructed to receive and process instruction information, and to control the guiding robot according to the instruction information; the moving unit (2) is constructed to move according to a command from the control unit (6); and the fixed unit (3) is constructed into a fixed container, and the height of the fixed unit (3) can be adjusted.

Guiding robot and guiding method

The invention discloses a potato defect detection and recognition system design based on machine vision. The potato defect detection and recognition system design is characterized in that defected potatoes are identified and classified on a ZYNQ platform by utilizing a machine vision library Open CV of an embedded Linux system; characteristic factors of the defected potatoes with green peels, dry rot, crust and mechanical damages are extracted and R, G and B discrete degrees of variable defect factors are analyzed to realize detection and recognition of surface defects of the potatoes, and the algorithm precision is greatly improved. Wavelet transform is applied to analysis and detection of potato shapes of the potatoes, and ellipse radiuses of the potatoes are extracted and are subjected to normalization processing; grading is carried out through a RBF (Radial Basis Function) neural network, so that the efficiency and precision of recognizing the defected potatoes by grades are improved; potato images are pre-processed by utilizing an FPGA (Field Programmable Gate Array) and an algorithm in the Open CV is subjected to accelerated processing; a calculation speed and the algorithm efficiency are remarkably improved. A testing result shows that compared with an existing defected potato recognition and classification technology based on software image processing, an image processing algorithm is innovated and optimized by a novel method based on a hardware structure platform, and the processing speed and the algorithm efficiency are greatly improved; theories and experiments show that the design has relatively ideal detection efficiency and speed on the recognition and classification of the defected potatoes in an actual process. The design has very great significance on a potato processing industry.

Potato defect detection and recognition system design based on machine vision

The invention discloses an intelligent transfusion robot based on the internet of things. The intelligent transfusion robot comprises an ultrasonic following car, a transfusion frame, a transfusion device, a bracelet, a terminal control system, a remote control system and a transfusion control system; the transfusion control system comprises a control box, a transfusion controller, a liquid level sensor, a stepping motor drive circuit, a transfusion stop device, an audible and visual alarm, a control switch and a transfusion wireless communication module. According to the intelligent transfusion robot based on the internet of things, the technical problem that due to the fact that the transfusion robot shakes in the moving process, the liquid in a transfusion bottle shakes can be effectively solved, and therefore liquid medicine can be transferred into the body of a patient along a transfusion tube at a constant speed.

Yuan Xiaoping

Papers

Potato defect detection and recognition system design based on machine vision

Intelligent transfusion robot based on internet of things