Chinese-medicinal-material identification method based on deep neural networks
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of deep neural network, recognition method
Inactive Publication Date: 2018-04-24
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 35 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0007] However, due to the particularity of the application, applications such as face recognition, emotion recognition, car mod
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0048]A method for identifying Chinese medicinal materials based on a deep neural network, comprising the steps of:
[0049] S1. Collect pictures of Chinese medicinal materials as the input of the data set, and preprocess the collected pictures of Chinese medicinal materials;
[0050] In the above step S1, collect pictures of Chinese herbal medicines as the input of the data set, wherein the picture data set of Chinese herbal medicines is obtained through web crawlers and manual photography methods, and manually screens and labels the image data sets, and the size is normalized to 256*256, and According to the neural network algorithm, the data set needs to be divided into training set and test set, with a ratio of 7:2. Due to the small number of pictures of medicinal materials in some categories, the whole data set is unbalanced in quantity. In order to prevent overfitting in the training process, the training set is replicated to make each category consistent in quantity; an...
Embodiment 2
[0099] This embodiment specifically introduces a method for identifying Chinese herbal medicines based on a deep neural network from the aspects of framework construction, data set preparation, model training, and actual testing. The specific process is introduced as follows.
[0100] 1. The framework construction process is as follows:
[0101] 1. Install the GPU driver and computing environment;
[0102] 2. Install the deep learning framework Caffe environment.
[0103] 2. The data set preparation process is as follows:
[0104] 1. Use the Python language to write a web crawler tool for Chinese herbal medicine picture data, use this tool to collect Chinese herbal medicine pictures on the network under multi-threaded conditions and automatically record the labels of Chinese herbal medicines, and perform preliminary manual screening on the collected pictures of Chinese herbal medicines;
[0105] 2. Use a high-definition camera to go to the medicinal material store to take vi...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
The invention discloses a Chinese-medicinal-material identification method based on deep neural networks. The method includes the following steps: using Chinese-medicinal-material pictures, which arecollected by a web crawler and artificial photographing, as input of a data set, and carrying out preprocessing; and adopting a Bagging method of ensemble learning for training and prediction processes, namely adopting a random sampling method to generate multiple sub-training-sets, utilizing classical convolutional neural network models and all the sub-training-sets to carry out fine-tuning training to generate multiple weak classifiers, wherein the adopted convolutional neural network models include AlexNet, SqueezeNet and GoogleNet, and finally cooperate with a Softmax classification algorithm, and using an ensemble-learning combination strategy to obtain a strong classifier to obtain a classification result, wherein a voting method is adopted for the ensemble-learning combination strategy. The method of the invention is used for auxiliary identification of Chinese medicinal materials, reduces amateur errors appearing in identification, and can analyze the Chinese medicinal materials in a manner of high accuracy, fast identification speed and stable performance.
Description
technical field [0001] The invention relates to the technical field of applying image recognition and integrated learning to the identification of Chinese herbal medicines, in particular to a method for identifying Chinese herbal medicines based on a deep neural network. Background technique [0002] Traditional Chinese medicine takes yin and yang and five elements as the theoretical basis, and regards the human body as a unity of qi, shape, and spirit. Through the method of "seeing, hearing, asking, and feeling", the four diagnosis methods are used to explore the etiology, nature, location, pathogenesis, and internal organs of the human body. , meridians, joints, changes in qi, blood and body fluids, judging the growth and decline of evil, positive and negative, and then get the name of the disease, summarize the disease type, and use the principle of dialectical treatment to formulate "sweating, vomiting, descending, harmonizing, warming, clearing, nourishing, and eliminati...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.