Model construction method and system for high-speed TDI CCD camera image dark stripe noise recognition
A stripe noise and construction method technology, applied in neural learning methods, character and pattern recognition, biological neural network models, etc., can solve problems such as low efficiency and accuracy, difficult threshold selection, etc., and achieve the effect of improving the detection effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment approach 1
[0044] Embodiment 1. A model construction method for the recognition of dark and weak stripe noise in high-speed TDI CCD camera images described in this embodiment, refer to figure 1 This embodiment can be better understood, including the following steps:
[0045] Step S1, collecting TDI CCD camera sample image data, and manually classifying and labeling the collected sample image data;
[0046] Step S2, the binarized image obtained after preprocessing the manually classified and labeled sample image data is used as the input sample set of the convolutional neural network, and the sample set is divided into a training sample set, a verification sample set and a test sample set;
[0047] Step S3, constructing a convolutional neural network classifier, and inputting the training sample set and the verification sample set into the convolutional neural network for model training and parameter tuning;
[0048] Step S4, the test sample set is input into the convolutional neural net...
Embodiment approach 2
[0050] Embodiment 2. This embodiment further defines the model construction method for the recognition of dark and weak streak noise in high-speed TDI CCD camera images described in Embodiment 1. In this embodiment, in step S1, the acquisition of TDI The conditions for the sample image data of the CCD camera are:
[0051] Performed under dark room conditions to reduce the interference of other noise in the image to the faint fringe noise.
[0052] In this embodiment, under darkroom test conditions, N>1000 camera darkfield images are acquired. Obtained sample images such as figure 2 As shown in the figure, due to the small amplitude of the dark interference fringes, it is difficult to directly distinguish them in the original image. Therefore, the given example images are all contrast stretched and brightness adjusted to enhance the recognition of the dark interference fringes in the image.
[0053] Specifically, manually classify and label the sample data according to wheth...
Embodiment approach 3
[0054] Embodiment 3. This embodiment further defines the model construction method for the recognition of dark streak noise in high-speed TDI CCD camera images described in Embodiment 1. In this embodiment, in step S2, the sample image The data preprocessing is based on the Sobel operator to detect and extract the edge of the sample image data to enhance the recognition of the dark and weak stripe noise in the image.
[0055] In this embodiment, in order to solve the problem that the amplitude of the fringe interference in the image is usually small compared to the background signal, which affects the identification effect of the algorithm, the edge detection and extraction of the sample data is performed based on the Sobel edge extraction operator, and the dark and weak fringes of the interference are enhanced. Recognition in the image. After the sample image data is operated by the Sobel operator, the result is a binarized edge image.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More